Academic Positions

  • Present

    Tenure-Track Assistant Professor

    University of Florida J. Crayton Pruitt Family Department of Biomedical Engineering

  • Present 2017

    Affliated Faculty

    University of Florida Department of Electrical and Computer Engineering

  • Present 2019

    Affiliated Faculty

    University of Florida Department of Computer & Information Science & Engineering

  • Present 2018

    Affiliated Faculty

    University of Florida Department of Radiology, College of Medicine

Education

  • Ph.D. 2014

    Ph.D. in Electrical and Computer Engineering

    Cornell University, Ithaca, NY.

  • B.E.2009

    B.E. in Information Engineering

    Zhejiang University, Hangzhou, China

News

  • 2/25/2020: SMILer Garret Fullerton has been accepted into UF University Scholars Program to work on machine learning for medical image optimization. [News]
  • 12/4/2019: Dr. Fang presented at the Annual Conference of Radiological Society of North America (RSNA) on “Multimodal CT Image Super-Resolution via Transfer Generative Adversarial Network” with Ph.D. student Yao Xiao as the leading author.
  • 9/9/2019: Dr. Fang receives an NSF award entitled "III:Small: Modeling Multi-Level Connectivity of Brain Dynamics". [News]
  • 8/30/2019: Congrats to Peng Liu on passing his dissertation qualification!
  • 8/26/2019: Kudos to Peng Liu and Dr. Fang for their first patent at UF. A Software Using a Genetic Algorithm to Automatically Build Convolutional Neural Networks for Medical Image Denoising! [News]
  • 8/20/2019: Congrats to our STTP students on their fantastic project presentations!
  • 7/26/2019: 'Development and Validation of Automated Imaging Differentiation in Parkinsonism: A Multi-Site Machine Learning Study' accepted for publication in The Lancet Digital Health. Congrats to SMiLE Lab and Dr. David Vaillancourt!
  • 8/20/2019: Two SSTP high school students Imaan Randhawa and Aarushi Walia successfully completed their summer research in SMiLE Lab under the supervision of Dr. Fang and PhD student Yao Xiao.
  • 6/28/2019: Dr. Fang recieves UF Informatics Institute Seed Fund Grant for research in smartphone based Diabetic Retinopath detection. [News]
  • 6/13/2019: Kyle See is awarded an NIH CTSI TL1 Predoctoral Fellowship to study methods and mechanisms of cognition and motor control through data science. [News]
  • 5/10/2019: Dr. Fang receives collaborative CTSI Pilot Award to study cancer therapy-induced cardiotoxicity. [News]
  • 5/7/2019: Congrats to Yao Xiao for successfully defending her proposal
  • 4/16/2019: Congrats to Peng Liu for his paper ,'Deep Evolutionary Networks with Expedited Genetic Algorithms for Medical Image Denoising', being accepted for publication in Medical Image Analysis! [News]
  • 4/16/2019: Kudo to Yao Xiao for her paper, 'STIR-Net: Spatial-Temporal Image Restoration Net for CTPerfusion Radiation Reduction', being accepted for publication in Frontiers in Neurology, section Stroke. [News]
  • 4/16/2019: SMiLE Lab's Senior Design group presents their final project for Smartphone Based Diabetic Retinopathy Diagnosis.
  • 3/7/2019: Maximillian Diaz accepted to UF University Scholars Program to work on retina based Parkinson's diagnosis. [News]
  • 1/10/2019: Dr. Fang named a senior member of IEEE. [News]
  • 5/17/2018: Dr. Fang awarded University of Florida Informatics Institute and the Clinical and Translational Science Institute (CTSI) pilot funding for precision medicine. [News]
  • 4/24/2018: SMiLE Lab recieves two first place awards at the Diabetic Retinopathy Segmentation and Grading Challenge. [News]
  • 3/26/2018: Akash and Akshay Mathavan accepted to UF University Scholars Program to work on environmental risk factors for ALS. [News]
  • 10/30/2017: Two master students, Yangjunyi Li and Yun Liang, join SMILE Group. Welcome!
  • 10/1/2017: Two UF BME senior students Kyle See and Daniel El Basha join SMILE lab to work on big biomedical data anlytics research supported by NSF REU. Welcome! [News]
  • 08/2017: Yao is awarded MICCAI 2017 Student Travel Award. Congrats to Yao! [News]
  • 08/2017: Four papers from SMILE Lab will be presented at BMES 2017 in Pheonix, Arizona.
  • 08/2017: SMILE Lab will move to J. Crayton Pruitt Family Department of Biomedical Engineering at University of Florida.
  • 07/2017: One paper is accepted by Machine Learning and Medical Imaging (MLMI) Workshop at MICCAI 2017. Congrats to Yao!
  • 07/16/2017: Dr. Fang is invited to give a talk at the 4th Medical Image Computing Seminar (MICS) held at Shanghai Jiaotong University, Shanghai, China.
  • 06/2017: Yao won the NSF Travel Award to attend CHASE 2017 in Philadelphia, PA. Congrats to Yao! [News]
  • 05/2017: Dr. Fang is invited by NSF as a panelist of Smart and Connect Health.
  • 05/2017: One paper is accepted by CHASE 2017. Congrats to Yao!
  • 04/2017: One paper is accepted by MICCAI 2017. Congrats to Ling!
  • 04/2017: Dr. Fang is invited to give a talk at the Society for Brain Mapping and Therapeutics Annual Meeting in Los Angeles, CA.
  • 03/2017: Dr. Fang attended NSF Smart and Connected Health PI Meeting held in Boston, MA.
  • 10/2016: PhD student Maryamossadat Aghili has been awarded travel grants from NIPS WiML 2016 Program Committee and FIU GPSC to attend WiML of NIPS 2016 in Barcelona.
  • 09/2016: Dr. Fang is invited by NIH to review in BDMA study section.
  • 09/2016: One paper is accepted by Pattern Recognition!
  • 08/2016: Dr. Fang is selected as an Early Career Grant Reviewer by NIH.
  • 08/2016: SMILE REU and RET students and teachers won the 2016 Best REU and RET Poster Awards at SCIS of FIU.
  • 07/2016: Our paper "Abdominal Adipose Tissues Extraction Using Multi-Scale Deep Neural Network" is accepted by NeuroComputing!
  • 04/2016: PhD student Maryamossadat Aghili has been awarded travel grants to attend Grad Cohort Conference (CRAW).
  • 05/2016: Dr. Fang's research appeared on FIU News: Professor uses computer science to reduce patients' exposure to radiation from CT scans!
  • 05/2016: Dr. Fang has been selected to receive the 2016 Ralph E. Powe Junior Faculty Enhancement Award from Oak Ridge Associated Universities!
  • 05/2016: Dr. Fang received funding from NSF on CRII (Pre-CAREER) Award on "Characterizing, Modeling and Evaluating Brain Dynamics"!
  • 04/2016: Our paper "TENDER: TEnsor Non-local Deconvolution Enabled Radiation Reduction in CT Perfusion" is accepted by NeuroComputing!
  • 04/09/2016: Dr. Fang is awarded the first Robin Sidhi Memorial Young Scientist Award from the Annual Congress of Society of Brain Mapping and Therapeutics for recognizing her continuous devotion to bridge information technology and health informatics.
  • 03/2016: Our paper ""Computational Health Informatics in the Big Data Age: A Survey" is accepted by the prestigous ACM Computing Survey!
  • 01/2016: Dr. Fang is invited by NSF as a panel reviewer of Smart and Connect Health.
  • 12/2015: Dr. Fang serves as the Publicity Chair of the 14th IEEE International Conference on Machine Learning and Applications 2015.
  • 04/2015: Dr. Fang is invited by NSF as a panel reviewer of Smart and Connect Health.

Honors, Awards and Grants

  • August 2016
    2016 Best REU and RET Poster Awards
    image
    Dr. Fang's mentee, Paul Naghshineh from George Washington University, won the Best REU Poster Award at the annual REU Symposium at FIU. Christian McDonald with Edda I. Rivera, teachers from Miami Jackson Senior High School and John A. Ferguson Senior High School, under Dr. Fang's mentorship, won the Best RET Poster Award. Congratulations to Paul, Christian and Edda!
  • May 2016
    2016 Ralph E. Powe Junior Faculty Enhancement Award
    image
    Dr. Fang has been selected to receive the 2016 Ralph E. Powe Junior Faculty Enhancement Award from Oak Ridge Associated Universities (two nominations from each institute, 35 awardees out of 132 applicants).
  • April 2016
    NSF CRII Award on "Characterizing, Modeling and Evaluating Brain Dynamics"
    image

    Brain dynamics, which reflects the healthy or pathological states of the brain with quantifiable, reproducible, and indicative dynamics values, remains the least understood and studied area of brain science despite its intrinsic and critical importance to the brain. Unlike other brain information such as the structural and sequential dimensions that have all been extensively studied with models and methods successfully developed, the 5th dimension, dynamics, has only very recently started receiving systematic analysis from the research community. The state-of-the-art models suffer from several fundamental limitations that have critically inhibited the accuracy and reliability of the dynamic parameters' computation. First, dynamic parameters are derived from each voxel of the brain spatially independently, and thus miss the fundamental spatial information since the brain is connected? Second, current models rely solely on single-patient data to estimate the dynamic parameters without exploiting the big medical data consisting of billions of patients with similar diseases.

    This project aims to develop a framework for data-driven brain dynamics characterization, modeling and evaluation that includes the new concept of a 5th dimension – brain dynamics – to complement the structural 4-D brain for a complete picture. The project studies how dynamic computing of the brain as a distinct problem from the image reconstruction and de-noising of convention models, and analyzes the impact of different models for the dynamics analysis. A data-driven, scalable framework will be developed to depict the functionality and dynamics of the brain. This framework enables full utilization of 4-D brain spatio-temporal data and big medical data, resulting in accurate estimations of the dynamics of the brain that are not reflected in the voxel-independent models and the single patient models. The model and framework will be evaluated on both simulated and real dual-dose computed tomography perfusion image data and then compared with the state-of-the-art methods for brain dynamics computation by leveraging collaborations with Florida International University Herbert Wertheim College of Medicine, NewYork-Presbyterian Hospital / Weill Cornell Medical College (WCMC) and Northwell School of Medicine at Hofstra University. The proposed research will significantly advance the state-of-the-art in quantifying and analyzing brain structure and dynamics, and the interplay between the two for brain disease diagnosis, including both the acute and chronic diseases. This unified approach brings together fields of Computer Science, Bioengineering, Cognitive Neuroscience and Neuroradiology to create a framework for precisely measuring and analyzing the 5th dimension – brain dynamics – integrated with the 4-D brain with three dimensions from spatial data and one dimension from temporal data. Results from the project will be incorporated into graduate-level multi-disciplinary courses in machine learning, computational neuroscience and medical image analysis. This project will open up several new research directions in the domain of brain analysis, and will educate and nurture young researchers, advance the involvement of underrepresented minorities in computer science research, and equip them with new insights, models and tools for developing future research in brain dynamics in a minority serving university.

  • April 2016
    Robin Sidhu Memorial Young Scientist Award
    image
    Dr. Fang was awarded the Robin Sidhu Memorial Young Scientist Award at the Annual Congress of Society of Brain Mapping and Theurapeutics. News reported on PR Newswire, Yahoo,FIU NEWS
  • March 2015
    National Science Foundation CISE CAREER Workshop Travel Award
    image
    Dr. Fang received a Travel Award to attend CISE NSF CAREER Proposal Writing Workshop in Arlington, VA.
  • 2014
    Hsien Wu and Daisy Yen Wu Memorial Award
    image
    In recognition of the excellent progress in the academic program and high potential for a successful academic career (5 awardees out of all graduate students at Cornell University).
  • 2014
    Student Travel Award at MICCAI
    image
    Student Travel Award at the International Conference on Medical Image Computing and Computer Assisted Intervention (MICCAI) 2014.
  • 2012
    IBM Cornell ECE Women's Conference Travel Grant
    image
    IBM Cornell ECE Women's Conference Travel Grant to attend the 15th International Conference on Medical Image Computing and Computer Assisted Intervention, 2012.
  • 2010
    Best Paper Award at IEEE ICIP
    image
    Best Paper Award at the 17th International Conference on Image Processing, 2010. (Top 1 out of 1190 accepted papers, first author publication)
  • 2009-2010
    Irwin and Joan Jacobs Fellowship
    image
    Cornell University, awarded to students who exemplify strength and potential in academics, service, and leadership, 2009-2010
  • 2010
    Best PhD Poster Award
    image
    Cornell Engineering Research Conference, 2010

Acknowledgements

  • Our work is supported by:

    image image image image

Current Members

Peng Liu

PhD Candidate

pliu1@ufl.edu
Biology-Inspired Artificial Intelligence
Medical Image Analysis
AI-Inspired Neuroscience

Yao Xiao

PhD Candidate

xiaoyao@ufl.edu
Medical Image Analysis
Computational Health Informatics

Jianqiao Tian

PhD Student

j.tian@ufl.edu
Medical Image Analysis
Early Neural Disease Diagnosis

Kyle See

PhD Student

NIH CTSI TL1 Predoctoral Fellowship
kylebsee@ufl.edu
Machine Learning in Somatotopy
Autoimmune Disease Analytics

Skylar Stolte

Master Student

skylastolte4444@ufl.edu
Cardiotoxicity Prediction
Longitudinal Glaucoma Study

Maximillian Diaz

Undergraduate Student

University Scholar Program
mdiaz40@ufl.edu
Early Neural Disease Diagnosis
Medical Image Analysis

Sumanth Aluri

Undergraduate Student

aluris@ufl.edu

Charlie Tran

Undergraduate Student

charlietran@ufl.edu

Rachel Peebles

Undergraduate Student

rachel.peebles@ufl.edu

Garrett Fullerton

Undergraduate Student

University Scholar Program
gfullerton@ufl.edu

Neeva Sethi

Undergraduate Student

neevasethi@ufl.edu

Gianna Sweeting

Undergraduate Student

sweetinggianna@ufl.edu

Ahmet Bilgili

Undergraduate Student

ahmet.bilgili@ufl.edu

Jason Chen

Undergraduate Student

yanghaoyuchen@ufl.edu

Muhamed Maher

Undergraduate Student

mhobi@ufl.edu

Edward Zhang

Undergraduate Student

edwardzhang@ufl.edu

Alumni

Daniel El Basha

Undergraduate Researcher, NSF REU Student, 2017-2019

PhD student at MD Anderson

Akshay Mathavan

Undergraduate Researcher, University Scholar Program, 2018-2019

Doctor of Medicine student, UF

Akash Mathavan

Undergraduate Researcher, University Scholar Program, 2018-2019

Doctor of Medicine student, UF

Yangjunyi Li

Masters Student, UF BME, 2017-2018

Novartis Institutes for BioMedical Research

Yun Liang

PhD Student (As Intern), UF BME, 2018-2019

PhD student, UF BME

Micheal Adeyosoye

MS-PhD, FIU Bridge to PhD Fellowship, 2016-2017

PhD Student, FIU

Jingan Qu

Masters Student, 2015-2017

Data Scientist, Applied Research Center FIU

Daniel Parra

Masters Student, 2015-2016

Software Engineer, ProActive Technologies, LLC

Haodi Jiang

Masters Student, 2014-2015

PhD student at NJIT

Sherman Ng

M.Eng. 2010-2011 @ Cornell ECE

Software Engineer, Microsoft

Yuanyuan Zhu

Visiting Undergraduate Student, 2016 Summer

Masters Student, computer Science, University of South California

Xing Pang

Visiting Graduate Student, 2015-2016

Nanjing University of Science and Technology

Edda Rivera

NSF DoD RET Teacher, Best NSF RET Poster Award at FIU SCIS RET Presentation, 2016 Summer

High School Teacher, John A. Ferguson Senior High School

Christian McDonald

NSF DoD RET Teacher, Best NSF RET Poster Award at FIU SCIS RET Presentation, 2016 Summer

High School Teacher, Miami Jackson Senior High School

Paul Naghshineh

NSF DoD REU Student, 2016 Summer

Gaumard Scientific

NSF Funded Projects

  • image

    IIS-1908299 III: Small: Collaborative Research: Modeling Multi-Level Connectivity of Brain Dynamics

    Project Page

    NSF Award Abstract

    The temporal dynamics of blood flows through the network of cerebral arteries and veins provides a window into the health of the human brain. Since the brain is vulnerable to disrupted blood supply, brain dynamics serves as a crucial indicator for many kinds of neurological diseases such as stroke, brain cancer, and Alzheimer's disease. Existing efforts at characterizing brain dynamics have predominantly centered on 'isolated' models in which data from single-voxel, single-modality, and single-subject are characterized. However, the brain is a vast network, naturally connected on structural and functional levels, and multimodal imaging provides complementary information on this natural connectivity. Thus, the current isolated models are deemed not capable of offering the platform necessary to enable many of the potential advancements in understanding, diagnosing, and treating neurological and cognitive diseases, leaving a critical gap between the current computational modeling capabilities and the needs in brain dynamics analysis. This project aims to bridge this gap by exploiting multi-scale structural (voxel, vasculature, tissue) connectivity and multi-modal (anatomical, angiography, perfusion) connectivity to develop an integrated connective computational paradigm for characterizing and understanding brain dynamics.

  • IIS-1564892 CRII: SCH: Characterizing, Modeling and Evaluating Brain Dynamics

    NSF Award Abstract

    The temporal dynamics of blood flows through the network of cerebral arteries and veins provides a window into the health of the human brain. Since the brain is vulnerable to disrupted blood supply, brain dynamics serves as a crucial indicator for many kinds of neurological diseases such as stroke, brain cancer, and Alzheimer's disease. Existing efforts at characterizing brain dynamics have predominantly centered on 'isolated' models in which data from single-voxel, single-modality, and single-subject are characterized. However, the brain is a vast network, naturally connected on structural and functional levels, and multimodal imaging provides complementary information on this natural connectivity. Thus, the current isolated models are deemed not capable of offering the platform necessary to enable many of the potential advancements in understanding, diagnosing, and treating neurological and cognitive diseases, leaving a critical gap between the current computational modeling capabilities and the needs in brain dynamics analysis. This project aims to bridge this gap by exploiting multi-scale structural (voxel, vasculature, tissue) connectivity and multi-modal (anatomical, angiography, perfusion) connectivity to develop an integrated connective computational paradigm for characterizing and understanding brain dynamics.

Filter by type:

Sort by year:

Monte Carlo Dosimetry For CT Brain Perfusion Studies Utilizing Volumetric Acquisitions

Justin L Brown, Daniel El Basha∗, Nathalie Correa, Yao Xiao, Izabella Barreto, Ruogu Fang, Chan Kim, Wesley E. Bolch
ConferenceJoint International Conference on Supercomputing in Nuclear Applications + Monte Carlo, May, 2020

ZMAT4 and DOCK9 Variants Associated with Heart Failure in Breast Cancer Patients in the UK Biobank data

Presidential Trainee Award, 2020 David J. Goldstein Trainee Award
Marwa Tantawy, Sonal Singh, Guang Yang, Matt Gitzendanner, Yiqing Chen, Yonghui Wu, Ruogu Fang, William Hogan, Yan Gong
ConferenceAmerican Society for Clinical Pharmacology and Therapeutics Annual Meeting in Houston, TX, March 18-21, 2020.

Low-Rise Gable Roof Buildings Pressure Prediction using Deep Neural Networks

Jianqiao Tian, Kurtis Gurley, Maximillian Diaz, Pedro L. Fernández Cabán, Forrest J. Masters, Ruogu Fang
Journal Journal of Wind Engineering & Industrial Aerodynamics, 2020.

Abstract

This paper presents a deep neural network (DNN) based approach for predicting mean and peak wind pressure coefficients on the surface of a scale model low-rise, gable roof residential building. Pressure data were collected on the model at multiple prescribed wind directions and terrain roughnesses. The resultant pressure coefficients quantified from a subset of these directions and terrains were used to train an DNN to predict coefficients for directions and terrains excluded from the training. The approach is able to leverage a variety of input conditions to predict pressure coefficients with high accuracy, while the prior work has limited flexibility with the number of input variables and yielded lower prediction accuracy. A two-step nested DNN procedure is introduced to improve the prediction of peak coefficients. The optimal correlation coefficients of return predictions were 0.9993 and 0.9964, for mean and peak coefficient prediction, respectively. The concept of super resolution based on global prediction was also discussed. With a sufficiently large database, the proposed DNN-based approach can augment existing experimental methods to improve the yield of knowledge while reducing the number of tests required to gain that knowledge.

IDRiD: Diabetic Retinopathy – Segmentation and Grading Challenge

Prasanna Porwal, Samiksha Pachade, Manesh Kokare, Girish Deshmukh, Jaemin Son, Woong Bae, Lihong Liu, Jianzong Wang, Xinhui Liu, Liangxin Gao, TianBo Wu, Jing Xiao, Fengyan Wang, Baocai Yin, Yunzhi Wang, Gopichandh Danala, Linsheng He, Yoon Ho Choi, Yeong Chan Lee, Sang-Hyuk Jung, Zhongyu Li, Xiaodan Sui, Junyan Wu, Xiaolong Li, Ting Zhou, Janos Toth, Agnes Baran, Avinash Kori, Sai Saketh Chennamsetty, Mohammed Safwan, Varghese Alex, Xingzheng Lyu,r, Li Cheng,D, Qinhao Chu, Pengcheng Li, Xin Ji, Sanyuan Zhang, Yaxin Shen, Ling Dai$, Oindrila Saha, Rachana Sathish, Tânia Melo, Teresa Araújo, Balazs Harangi, Bin Sheng, Ruogu Fang, Debdoot Sheet, Andras Hajdu, Yuanjie Zheng, Ana Maria Mendonça, Shaoting Zhang, Aurélio Campilho, Bin Zheng, Dinggang Shen, Luca Giancardo, Gwenolé Quellec, Fabrice Mériaudeau
Journal Medical Image Analysis, volume 59, 2020.

Abstract

Diabetic Retinopathy (DR) is the most common cause of avoidable vision loss, predominantly affecting the working-age population across the globe. Screening for DR, coupled with timely consultation and treatment, is a globally trusted policy to avoid vision loss. However, implementation of DR screening programs is challenging due to the scarcity of medical professionals able to screen a growing global diabetic population at risk for DR. Computer-aided disease diagnosis in retinal image analysis could provide a sustainable approach for such large-scale screening effort. The recent scientific advances in computing capacity and machine learning approaches provide an avenue for biomedical scientists to reach this goal. Aiming to advance the state-of-the-art in automatic DR diagnosis, a grand challenge on “Diabetic Retinopathy – Segmentation and Grading” was organized in conjunction with the IEEE International Symposium on Biomedical Imaging (ISBI - 2018). In this paper, we report the set-up and results of this challenge that is primarily based on Indian Diabetic Retinopathy Image Dataset (IDRiD). There were three principal sub-challenges: lesion segmentation, disease severity grading, and localization of retinal landmarks and segmentation. These multiple tasks in this challenge allow to test the generalizability of algorithms, and this is what makes it different from existing ones. It received a positive response from the scientific community with 148 submissions from 495 registrations effectively entered in this challenge. This paper outlines the challenge, its organization, the dataset used, evaluation methods and results of top-performing participating solutions. The top-performing approaches utilized a blend of clinical information, data augmentation, and an ensemble of models. These findings have the potential to enable new developments in retinal image analysis and image-based DR screening in particular.

REFUGE Challenge: A Unified Framework for Evaluating Automated Methods for Glaucoma Assessment from Fundus Photographs

Jose Ignacio Orlando, Huazhu Fu, Joa ̃o Barbossa Breda, Karel van Keer, Deepti R. Bathula, Andre ́s Diaz-Pinto, Ruogu Fang, Pheng-Ann Heng, Jeyoung Kim, JoonHo Lee, Joonseok Lee, Xiaoxiao Li, Peng Liu, Shuai Lu, Balamurali Murugesan, Valery Naranjo, Sai Samarth R. Phaye, Sharath M. Shankaranarayana, Apoorva Sikka, Jaemin Son, Anton van den Hengel, Shujun Wang, Junyan Wu, Zifeng Wu, Guanghui Xu, Yongli Xu, Pengshuai Yin, Fei Li, Xiulan Zhang, Yanwu Xu, Hrvoje Bogunovic ́
Journal Medical Image Analysis, volume 59, 2020.

Abstract

Glaucoma is one of the leading causes of irreversible but preventable blindness in working age populations. Color fundus photography (CFP) is the most cost-effective imaging modality to screen for retinal disorders. However, its application to glaucoma has been limited to the computation of a few related biomarkers such as the vertical cup-to-disc ratio. Deep learning approaches, although widely applied for medical image analysis, have not been extensively used for glaucoma assessment due to the limited size of the available data sets. Furthermore, the lack of a standardize benchmark strategy makes difficult to compare existing methods in a uniform way. In order to overcome these issues we set up the Retinal Fundus Glaucoma Challenge, REFUGE (https://refuge.grand-challenge.org), held in conjunction with MICCAI 2018. The challenge consisted of two primary tasks, namely optic disc/cup segmentation and glaucoma classification. As part of REFUGE, we have publicly released a data set of 1200 fundus images with ground truth segmentations and clinical glaucoma labels, currently the largest existing one. We have also built an evaluation framework to ease and ensure fairness in the comparison of different models, encouraging the development of novel techniques in the field. 12 teams qualified and participated in the online challenge. This paper summarizes their methods and analyzes their corresponding results. In particular, we observed that two of the top-ranked teams outperformed two human experts in the glaucoma classification task. Furthermore, the segmentation results were in general consistent with the ground truth annotations, with complementary outcomes that can be further exploited by ensembling the results.

Deep Spatial-Temporal Convolutional Neural Networks for Medical Image Restoration Deep Learning and Convolutional Neural Networks for Medical Image Computing

Yao Xiao, Skylar Stolte, Peng Liu, Yun Liang, Pina Sanelli, Ajay Gupta, Jana Ivanidze, and Ruogu Fang
Book Chapter Deep Learning and Convolutional Neural Networks for Medical Image Computing, Springer Publisher, 2019.

Big Data in Computational Health Informatics

Ruogu Fang, Samira Pouyanfar, Yimin Yang, Yao Xiao, Jianqiao Tian, Shu-Ching Chen, and S.S. Iyengar
Book Chapter Big Data in Multimodal Medical Imaging, CRC Publisher, 2019.

Development and Validation of the Automated Imaging Differentiation in Parkinsonism (AID-P): A Multi-Site Machine Learning Study

Derek B. Archer, ..., Ruogu Fang, ..., David E. Vaillancourt
JournalThe Lancet Digital Healt, 2019.

Identifying Relations of Medications with Adverse Drug Events Using Recurrent Convolutional Neural Networks and Gradient Boosting

Xi Yang, Jiang Bian, Ruogu Fang, Ragnhildur I. Bjarnadottir, William R. Hogan, and Yonghui Wu
JournalJournal of the American Medical Informatics Association, 2019.

Deep Evolutionary Networks with Expedited Genetic Algorithms for Medical Image Denoising

Peng Liu, Mohammad D El Basha, Yangjunyi Li, Yao Xiao, Pina C.Sanelli, and Ruogu Fang
Journal Medical Image Analysis, vol. 54, pp. 306-315, 2019.

Abstract

Deep convolutional neural networks offer state-of-the-art performance for medical image analysis. However, their architectures are manually designed for particular problems. On the one hand, a manual designing process requires many trials to tune a large number of hyperparameters and is thus quite a time-consuming task. On the other hand, the fittest hyperparameters that can adapt to source data properties (e.g., sparsity, noisy features) are not able to be quickly identified for target data properties. For instance, the realistic noise in medical images is usually mixed and complicated, and sometimes unknown, leading to challenges in applying existing methods directly and creating effective denoising neural networks easily. In this paper, we present a Genetic Algorithm (GA)-based network evolution approach to search for the fittest genes to optimize network structures automatically. We expedite the evolutionary process through an experience-based greedy exploration strategy and transfer learning. Our evolutionary algorithm procedure has flexibility, which allows taking advantage of current state-of-the-art modules (e.g., residual blocks) to search for promising neural networks. We evaluate our framework on a classic medical image analysis task: denoising. The experimental results on computed tomography perfusion (CTP) image denoising demonstrate the capability of the method to select the fittest genes for building high-performance networks, named EvoNets. Our results outperform state-of-the-art methods consistently at various noise levels.

STIR-Net: Spatial-Temporal Image Restoration Net for CT Perfusion Radiation Reduction

Yao Xiao, Peng Liu, Yun Liang, Skylar Stolte, Pina Sanelli, Ajay Gupta, Jana Ivanidze, and Ruogu Fang
JournalFrontiers in Nuerology, 2019.

Abstract

Computed Tomography Perfusion (CTP) imaging is a cost-effective and fast approach to provide diagnostic images for acute stroke treatment. Its cine scanning mode allows the visualization of anatomic brain structures and blood flow; however, it requires contrast agent injection and continuous CT scanning over an extended time. In fact, the accumulative radiation dose to patients will increase health risks such as skin irritation, hair loss, cataract formation, and even cancer. Solutions for reducing radiation exposure include reducing the tube current and/or shortening the X-ray radiation exposure time. However, images scanned at lower tube currents are usually accompanied by higher levels of noise and artifacts. On the other hand, shorter X-ray radiation exposure time with longer scanning intervals will lead to image information that is insufficient to capture the blood flow dynamics between frames. Thus, it is critical for us to seek a solution that can preserve the image quality when the tube current and the temporal frequency are both low. We propose STIR-Net in this paper, an end-to-end spatial-temporal convolutional neural network structure, which exploits multi-directional automatic feature extraction and image reconstruction schema to recover high-quality CT slices effectively. With the inputs of low-dose and low-resolution patches at different cross-sections of the spatio-temporal data, STIR-Net blends the features from both spatial and temporal domains to reconstruct high-quality CT volumes. In this study, we finalize extensive experiments to appraise the image restoration performance at different levels of tube current and spatial and temporal resolution scales.The results demonstrate the capability of our STIR-Net to restore high-quality scans at as low as 11% of absorbed radiation dose of the current imaging protocol, yielding an average of 10% improvement for perfusion maps compared to the patch-based log likelihood method.

Automatic Choroid Layer Segmentation from Optical Coherence Tomography Images Using Deep Learning

Saleha Masood, Ruogu Fang, Huating Li, Bin Sheng, Ping Li, Akash Mathavan, Xiangning Wang, Po Yang, Qiang Wu, Jing Qin, and Weiping Jia
JournalNature Scientific Reports, 9(1):3058, 2019.

Abstract

The choroid layer is a vascular layer in human retina and its main function is to provide oxygen and support to the retina. Various studies have shown that the thickness of the choroid layer is correlated with the diagnosis of several ophthalmic diseases. For example, diabetic macular edema (DME) is a leading cause of vision loss in patients with diabetes. Despite contemporary advances, automatic segmentation of the choroid layer remains a challenging task due to low contrast, inhomogeneous intensity, inconsistent texture and ambiguous boundaries between the choroid and sclera in Optical Coherence Tomography (OCT) images. The majority of currently implemented methods manually or semi-automatically segment out the region of interest. While many fully automatic methods exist in the context of choroid layer segmentation, more effective and accurate automatic methods are required in order to employ these methods in the clinical sector. This paper proposed and implemented an automatic method for choroid layer segmentation in OCT images using deep learning and a series of morphological operations. The aim of this research was to segment out Bruch’s Membrane (BM) and choroid layer to calculate the thickness map. BM was segmented using a series of morphological operations, whereas the choroid layer was segmented using a deep learning approach as more image statistics were required to segment accurately. Several evaluation metrics were used to test and compare the proposed method against other existing methodologies. Experimental results showed that the proposed method greatly reduced the error rate when compared with the other state-of-the-art methods.

Multimodal CT Image Super-Resolution via Transfer-GAN.

Yao Xiao and Ruogu Fang
ConferenceBiomedical Engineering Society Annual Meeting, October, 2019, Philadelphia, PA

Deep Learning-based Alzheimers Disease Classification of FDG-PET and AV45 PET Images.

Jianqiao Tian, Max Diaz, and Ruogu Fang
ConferenceBiomedical Engineering Society Annual Meeting, October, 2019, Philadelphia, PA

Artificial Intelligence For Automated Diagnosis of Glaucoma In Stereoscopic Images

Skylar Stolte and Ruogu Fang
ConferenceBiomedical Engineering Society Annual Meeting, October, 2019, Philadelphia, PA

Classification Of Neural Stimulations In The Brain With Super Voxels

Kyle See and Ruogu Fang
ConferenceBiomedical Engineering Society Annual Meeting, October, 2019, Philadelphia, PA

Retinal Disease Diagnosis Using Mobile Devices

Skylar Stolte, Kyle See, Daniel El Basha, and Ruogu Fang
ConferenceBiomedical Engineering Society Annual Meeting, October, 2019, Philadelphia, PA

Multimodal CT Image Super-Resolution via Transfer Generative Adversarial Network

Yao Xiao∗, Manual Arreola, Izabella Barrreto, W. Christopher Fox, Keith Peters, and Ruogu Fang
ConferenceAnnual Meeting of Radiology Society of North American, December 2019

CFEA: Collaborative Feature Ensembling Adaptation for Domain Adaptation in Unsupervised Optic Disc and Cup Segmentation

Peng Liu, Bin Kong, Zhongyu Li, Shaoting Zhang, and Ruogu Fang
ConferenceMedical Image Analysis and Computer Assisted Intervention, October, 2019.

Abdominal Adipose Tissue Segmentation in MRI with Double Loss Function Collaborative Learning

Siyuan Pan, Yuxin Xue, Bin Sheng, Xuhong Hou, Huating Li, Ruogu Fang, Weiping Jia, and Jing Qin
ConferenceMedical Image Analysis and Computer Assisted Intervention, October, 2019.

Mining Big Neuron Morphological Data

Maryamossadat Aghili and Ruogu Fang
JournalComputational Intelligence and Neuroscience, 2018.

Abstract

The advent of automatic tracing and reconstruction technology has led to a surge in the number of neurons 3D reconstruction data and consequently the neuromorphology research. However, the lack of machine-driven annotation schema to automatically detect the types of the neurons based on their morphology still hinders the development of this branch of science. Neuromorphology is important because of the interplay between the shape and functionality of neurons and the far-reaching impact on the diagnostics and therapeutics in neurological disorders. This survey paper provides a comprehensive research in the field of automatic neurons classification and presents the existing challenges, methods, tools, and future directions for automatic neuromorphology analytics. We summarize the major automatic techniques applicable in the field and propose a systematic data processing pipeline for automatic neuron classification, covering data capturing, preprocessing, analyzing, classification, and retrieval. Various techniques and algorithms in machine learning are illustrated and compared to the same dataset to facilitate ongoing research in the field.

Retinal Vessel Segmentation Using Minimum Spanning Superpixel Tree Detector

Bin Sheng, Ping Li, Shuangjia Mo, Huating Li, Xuhong Hou, Qiang Wu, Jing Qin, Ruogu Fang, and David Dagan Feng
JournalIEEE Transaction on Cybernetics, 99, pp.1-13, 2018 .

Abstract

The retinal vessel is one of the determining factors in an ophthalmic examination. Automatic extraction of retinal vessels from low-quality retinal images still remains a challenging problem. In this paper, we propose a robust and effective approach that qualitatively improves the detection of low-contrast and narrow vessels. Rather than using the pixel grid, we use a superpixel as the elementary unit of our vessel segmentation scheme. We regularize this scheme by combining the geometrical structure, texture, color, and space information in the superpixel graph. And the segmentation results are then refined by employing the efficient minimum spanning superpixel tree to detect and capture both global and local structure of the retinal images. Such an effective and structure-aware tree detector significantly improves the detection around the pathologic area. Experimental results have shown that the proposed technique achieves advantageous connectivity-area-length (CAL) scores of 80.92% and 69.06% on two public datasets, namely, DRIVE and STARE, thereby outperforming state-of-the-art segmentation methods. In addition, the tests on the challenging retinal image database have further demonstrated the effectiveness of our method. Our approach achieves satisfactory segmentation performance in comparison with state-of-the-art methods. Our technique provides an automated method for effectively extracting the vessel from fundus images

Neural Network Evolution Using Expedited Genetic Algorithm for Medical Image Denoising

Peng Liu, Yangjunyi Li, Mohammad D El Basha, and Ruogu Fang
Conference Medical Image Analysis and Computer Assisted Intervention, September, 2018, Granada, Spain.

Abstract

Convolutional neural networks offer state-of-the-art performance for medical image denoising. However, their architectures are manually designed for different noise types. The realistic noise in medical images is usually mixed and complicated, and sometimes unknown, leading to challenges in creating effective denoising neural networks. In this paper, we present a Genetic Algorithm (GA)-based network evolution approach to search for the fittest genes to optimize network structures. We expedite the evolutionary process through an experience-based greedy exploration strategy and transfer learning. The experimental results on computed tomography perfusion (CTP) images denoising demonstrate the capability of the method to select the fittest genes for building high-performance networks, named EvoNets, and our results compare favorably with state-of-the-art methods

Multi-task Fundus Image Quality Assessment via Transfer Learning and Landmarks Detection

Yaxin Shen, Ruogu Fang, Bin Sheng, Ling Dai, Huating Li, Jing Qin, Qiang Wu, and Weiping Jia
Conference Machine Learning in Medical Imaging, September, 2018, Granada, Spain.

Abstract

The quality of fundus images is critical for diabetic retinopathy diagnosis. The evaluation of fundus image quality can be affected by several factors, including image artifact, clarity, and field definition. In this paper, we propose a multi-task deep learning framework for automated assessment of fundus image quality. The network can classify whether an image is gradable, together with interpretable information about quality factors. The proposed method uses images in both rectangular and polar coordinates, and fine-tunes the network from trained model grading of diabetic retinopathy. The detection of optic disk and fovea assists learning the field definition task through coarse-to-fine feature encoding. The experimental results demonstrate that our framework outperform single-task convolutional neural networks and reject ungradable images in automated diabetic retinopathy diagnostic systems.

Low-Dose CT Perfusion Image Restoration and Radiation Reduction.

Yao Xiao, Peng Liu, and Ruogu Fang
ConferenceBiomedical Engineering Society Annual Meeting, Atlanta, GA, October, 2018.

Efficient Multi Modality Medical Image Joint Recosntruction via Vectorized Gradient

Yao Xiao, Yun Liang, Yunmei Chen, Xiaojing Ye, and Ruogu Fang
ConferenceBiomedical Engineering Society Annual Meeting, Atlanta, GA, October, 2018.

Multi-Modality Brain Image Co-Registration

Skylar Stolte, Yao Xiao,and Ruogu Fang
ConferenceBiomedical Engineering Society Annual Meeting, Atlanta, GA, October, 2018.

Decision Tree-based Classification for Differentiating System Lupus Erythematosus and Mixed Connective Tissue Disease

Kyle B. See and Ruogu Fang
ConferenceBiomedical Engineering Society Annual Meeting, Atlanta, GA, October, 2018.

STDN: Spatial-Temporal Denoising Net for Radiation Optimization in CT Perfusion

Yao Xiao, Liupeng, Yun Liang, and Ruogu Fang
ConferenceACM Richard Tapia Celebration of Diversity in Computing, September, Orlando, FL. 2018.

Multi-Modality PET-MRI Image Joint Reconstruction

Yao Xiao, Yun Liang, Yunmei Chen, Xiaojing Ye, and Ruogu Fang
ConferenceASNR 56th Annual Meeting & The Foundation of the ASNR Symposium, Vancouver, Canada, June, 2018.

Image Super-Resolution and Radiation Reduction via Deep Learning

Yao Xiao, Pina C. Sanelli, and Ruogu Fang
ConferenceASNR 56th Annual Meeting & The Foundation of the ASNR Symposium, Vancouver, Canada, June, 2018.

Regulated-convolutional Networks for Low-dose Cerebral CT Perfusion Restoration

Peng Liu and Ruogu Fang
ConferenceASNR 56th Annual Meeting & The Foundation of the ASNR Symposium, Vancouver, Canada, June, 2018.

SDCNET: Smoothed Dense-Convolution Network For Restoring Low-Dose Cerebral CT Perfusion

Peng Liu and Ruogu Fang
ConferenceIEEE International Symposium on Biomedical Imaging, April, 2018, Washington D.C.

Neural Network Evolution Using Expedited Genetic Algorithm for Medical Image Denoising

Peng Liu and Ruogu Fang
PatentsRef. No: UF-17344, Filed on 9/10/2018, Provisional Patent. US 62/728,995

Automatic Choroid Layer Segmentation Using Normalized Graph Cut

Saleha Masood ; Bin Sheng ; Ping Li ; Ruimin Shen ; Ruogu Fang; Qiang Wu
Journal IET Image Processing. pp. 22, DOI: 10.1049/iet-ipr.2017.0273, Online ISSN 1751-9667, 2017.

Abstract

Optical coherence tomography (OCT) is an immersive technique for depth analysis of retinal layers. Automatic choroid layer segmentation is a challenging task because of the low contrast inputs. Existing methodologies carried choroid layer segmentation manually or semi-automatically. In this paper, we proposed automated choroid layer segmentation based on normalized cut algorithm, which aims at extracting the global impression of images and treats the segmentation as a graph partitioning problem. Due to the complexity of the layering structure of retinal layers and choroid layer, we employed a series of preprocessing to make the cut more deterministic and accurate. The proposed method divided the image into several patches and ran the normalized cut on every image patch separately. The aim was to avoid insignificant vertical cuts and focus on horizontal cutting. After processing every patch, we acquired a global cut on the original image by combining all the patches. Later we measured the choroidal thickness which is highly helpful in the diagnosis of several retinal diseases. The results were computed on a total of 525 images of 21 real patients. Experimental results showed that the mean relative error rate of the proposed method was around 0.4 as the compared the manual segmentation performed by the experts.

STAR: Spatio-Temporal Architecture for super-Resolution in Low-Dose CT Perfusion.

Yao Xiao, Ajay Gupta, Pina C. Sanelli, Ruogu Fang
Conference Machine Learning in Medical Imaging (MIML), Medical Image Computing and Computer Assisted Intervention (MICCAI), Lecture Notes in Computer Science book series (LNCS, volume 10541), pp 97-105, Quebec, Canada, Sep. 2017.

Abstract

Computed tomography perfusion (CTP) is one of the most widely used imaging modality for cerebrovascular disease diagnosis and treatment, especially in emergency situations. While cerebral CTP is ca- pable of quantifying the blood flow dynamics by continuous scanning at a focused region of the brain, the associated excessive radiation increases the patients' risk levels of developing cancer. To reduce the necessary radiation dose in CTP, decreasing the temporal sampling frequency is one promising direction. In this paper, we propose STAR, an end-to- end Spatio-Temporal Architecture for super-Resolution to significantly reduce the necessary scanning time and therefore radiation exposure. The inputs into STAR are multi-directional 2D low-resolution spatio- temporal patches at different cross sections over space and time. Via training multiple direction networks followed by a conjoint reconstruc- tion network, our approach can produce high-resolution spatio-temporal volumes. The experiment results demonstrate the capability of STAR to maintain the image quality and accuracy of cerebral hemodynamic parameters at only one-third of the original scanning time.

Clinical Report Guided Retinal Microaneurysm Detection Using Deep Learning.

Ling Dai, Qiang Wu, Bin Sheng, Weiping Jia, Xuhong Hou, Ruogu Fang
Conference Biomedical Engineering Society Annual Meeting (BMES), 2017 Annual Meeting, October 11-14, 2017, Phoenix, Arizona.

Cardiovascular Disease Prediction and Risk Factor Mining with RFMiner.

Yao Xiao, Ruogu Fang
Conference Biomedical Engineering Society Annual Meeting (BMES), 2017 Annual Meeting, October 11-14, 2017, Phoenix, Arizona.

Accelerated Brain Perfusion Imaging via Spatio-Temporal Super-Resolution.

Yao Xiao, Ruogu Fang
Conference Biomedical Engineering Society Annual Meeting (BMES), 2017 Annual Meeting, October 11-14, 2017, Phoenix, Arizona.

A Simple and Realistic Simulation Method for Low-Dose CT.

Peng Liu, Ruogu Fang
Conference Biomedical Engineering Society Annual Meeting (BMES), 2017 Annual Meeting, October 11-14, 2017, Phoenix, Arizona.

RFMiner: Risk Factors Discovery and Mining for Preventive Cardiovascular Health.

Yao Xiao, Ruogu Fang
Conference The Second IEEE/ACM Conference on Connected Health: Applications, Systems and Engineering Technologies (CHASE), Philadelphia, PA. July 2017.

Abstract

Cardiovascular disease is one of the leading causes of death in the United States. It is critical to identify the risk factors associated with cardiovascular diseases and to alert individuals before they experience a heart attack. In this paper we propose RFMiner, a risk factor discovery and mining framework for identifying significant risk factors using integrated measures. We provide the blueprints for accurately predicting the possibility of heart attacks in the near future while identifying notable risk factors - especially the factors which are not well recognized.

Retinal Microaneurysm Detection Using Clinical Report Guided Multi-Sieving Convolutional Neural Network

Ling Dai, Bin Sheng, Qiang Wu, Huating Li, Xuhong Hou, Weiping Jia, and Ruogu Fang
Conference Medical Image Analysis and Computer Assisted Intervention, September, 2017, Quebec, Canada.

Indexing and Mining Large-Scale Neuron Databases using Maximum Inner Product Search.

Zhongyu Li, Ruogu Fang, Fumin Shen, Amin Katouzian, Shaoting Zhang.
Journal Pattern Recognition, vol. 63, pp. 680-688, 2017.

Abstract

Morphological retrieval is an effective approach to explore large-scale neuronal databases, as the morphology is correlated with neuronal types, regions, functions, etc. In this paper, we focus on the neuron identification and analysis via morphological retrieval. In our proposed framework, multiple features are extracted to represent 3D neuron data. Because each feature reflects different levels of similarity between neurons, we group features into different hierarchies to compute the similarity matrix. Then, compact binary codes are generated from hierarchical features for efficient similarity search. Since neuronal cells usually have tree-topology structure, it is hard to distinguish different types of neurons simply via traditional binary coding or hashing methods based on Euclidean distance metric and/or linear hyperplanes. Therefore, we employ an asymmetric binary coding strategy based on the maximum inner product search (MIPS), which not only makes it easier to learn the binary coding functions, but also preserves the non-linear characteristics of the neuron morphological data. We evaluate the proposed method on more than 17,000 neurons, by validating the retrieved neurons with associated cell types and brain regions. Experimental results show the superiority of our approach in neuron morphological retrieval compared with other state-of-the-art methods. Moreover, we demonstrate its potential use cases in the identification and analysis of neuron characteristics from large neuron databases.

Abdominal Adipose Tissues Extraction Using Multi-Scale Deep Neural Network.

Fei Jiang, Huating Li, Xuhong Hou, Bin Sheng∗, Ruimin Shen, Xiao-Yang Liu, Weiping Jia, Ping Li, Ruogu Fang∗ (* corresponding authors)
JournalNeuroComputing, vol. 229, pp. 23-33, 2017.

Abstract

Segmentation of abdominal adipose tissues (AAT) into subcutaneous adipose tissues (SAT) and visceral adipose tissues (VAT) is of crucial interest for managing the obesity. Previous methods with raw or hand-crafted features rarely work well on large-scale subject cohorts, because of the inhomogeneous image intensities, artifacts and the diverse distributions of VAT. In this paper, we propose a novel two-stage coarse-to-fine algorithm for AAT seg- mentation. In the first stage, we formulate the AAT segmentation task as a pixel-wise classification problem. First, three types of features, intensity, spatial and contextual fea- tures, are adopted. Second, a new type of deep neural network, named multi-scale deep neural network (MSDNN), is provided to extract high-level features. In the second stage, to improve the segmentation accuracy, we refine coarse segmentation results by determining the internal boundary of SAT based on coarse segmentation results and continuous of SAT internal boundary. Finally, we demonstrate the efficacy of our algorithm for both 2D and 3D cases on a wide population range. Compared with other algorithms, our method is not only more suitable for large-scale dataset, but also achieves better segmentation results. Fur- thermore, our system takes about 2 seconds to segment an abdominal image, which implies potential clinical applications.

TENDER: TEnsor Non-local Deconvolution Enabled Radiation Reduction in CT Perfusion.

Ruogu Fang*, Ajay Gupta, Junzhou Huang, Pina Sanelli.
Journal NeuroComputing, vol. 229, pp. 13-22, 2016.

Abstract

Stroke is the leading cause of long-term disability and the second leading cause of mortality in the world, and exerts an enormous burden on the public health. CT remains one of the most widely used imaging modality for stroke diagnosis. However when coupled with CT perfusion, the excessive radiation exposure in repetitive imaging to assess treatment response and prognosis has raised significant public concerns regarding its potential hazards to both short- and longterm health outcomes. Tensor total variation has been proposed to reduce the necessary radiation dose in CT perfusion without comprising the image quality by fusing the information of the local anatomical structure with the temporal blood flow model. However the local search in the framework fails to leverage the non-local information in the spatio-temporal data. In this paper, we propose TENDER, an efficient framework of non-local tensor deconvolution to maintain the accuracy of the hemodynamic parameters and the diagnostic reliability in low radiation dose CT perfusion. The tensor total variation is extended using non-local spatio-temporal cubics for regularization to integrate contextual and non-local information. We also propose an efficient framework consisting of fast nearest neighbor search, accelerated optimization and parallel computing to improve the efficiency and scalability of the non-local spatio-temporal algorithm. Evaluations on clinical data of subjects with cerebrovascular disease and normal subjects demonstrate the advantage of non-local tensor deconvolution for reducing radiation dose in CT perfusion.

Computational Health Informatics in the Big Data Age: A Survey

Ruogu Fang*, Samira Pouyanfar*, Yimin Yang, Shu-Ching Chen, S. S. Iyengar (* indicates equal contributions)
Journal Journal CSUR, ACM Computing Survey, Volume 49 Issue 1, Article No. 12, June 2016

Abstract

The explosive growth and widespread accessibility of digital health data have led to a surge of research activity in the healthcare and data sciences fields. The conventional approaches for health data management have achieved limited success as they are incapable of handling the huge amount of complex data with high volume, high velocity, and high variety. This article presents a comprehensive overview of the existing challenges, techniques, and future directions for computational health informatics in the big data age, with a structured analysis of the historical and state-of-the-art methods. We have summarized the challenges into four Vs (i.e., volume, velocity, variety, and veracity) and proposed a systematic data-processing pipeline for generic big data in health informatics, covering data capturing, storing, sharing, analyzing, searching, and decision support. Specifically, numerous techniques and algorithms in machine learning are categorized and compared. On the basis of this material, we identify and discuss the essential prospects lying ahead for computational health informatics in this big data age.

Hemodynamic Imaging of Lower Extremity Ulcers.

Rebecca Kwasinski, Cristianne Fernandez, Kevin Leiva, Edwin Robledo, Yuanyuan Zhu, Penelope Kallis, Francesco-Perez Clavijo, Ruogu Fang, Robert Kirsner, Anuradha Godavarty.
Conference Innovations in Wound Healing, Dec. 2016.

Abstract

Clinicians employ visual inspection of the wound and reduction in its size over time to monitor its healing process. Although these are standard clinical assessments, there is a need to develop a physiological approach that can map sub-surface tissue oxygenation at and around the wound region. Recently, a non-contact, portable, hand-held near infrared optical scanner (NIROS) has been developed to functionally image wound sites and differentiate healing from non-healing in lower extremity ulcers. Past studies using NIROS focused on differentiating healing from non-healing wounds based on NIR optical contrast between the wound and healthy surrounding tissue. However, these studies did not showcase the physiological changes in tissue oxygenation. Herein, NIROS has been modified to perform multi wavelength imaging in order to obtain the oxy and deoxy- hemoglobin maps of the wound and its surroundings. Clinical studies are currently performed at two clinical sites in Miami on lower extremity ulcers (2, diabetic foot ulcers (DFUs) and 4 venous leg ulcers (VLUs to date). Preliminary results have shown changes in oxy- and deoxy-hemoglobin maps of the wound and background across weeks of the treatment process. Image segmentation studies quantified regions of varied tissue oxygenation around and beneath the wound to potentially determine sub-surface healing regions. Ongoing efforts involve systematic 8-week imaging studies to obtain physiological indicators of healing from hemodynamic studies of DFUs and VLUs.

CT perfusion image super-resolution using a deep convolutional network.

Paul Naghshineh, Peng Liu, Ruogu Fang∗ (* corresponding authors)
ConferenceBMES, Biomedical Engineering Society Annual Meeting, October 5-8, 2016 in Minneapolis, Minnesota.

Towards High-Throughput Abnormal Brain Screening in MRI Images

Maryamossadat Aghili and Ruogu Fang
Conference Women in Machine Learning Workshop, Neural Information Processing Systems (NIPS), December 2016, Barcelona, Spain.

Physiological Assessment of Wound Healing using a Near-Infrared Optical Scanner.

Anuradha Godavarty, Rebecca Kwasinki, Cristianne Fernandez, Yuanyuan Zhu, Edwin Robledo, F. Perez-Clavijo, Ruogu Fang
Conference Biomedical Engineering Society Annual Meeting (BMES), October 5-8, 2016 in Minneapolis, Minnesota.

Maximum Inner Product Search for Morphological Retrieval of Large-Scale Neuron Data

Zhongyu Li, Fumin Shen, Ruogu Fang, Sailesh Conjeti, Amin Katouzian, Shaoting Zhang.
ConferenceISBI, IEEE International Symposium on Biomedical Imaging, Prague, Czech Republic, April, 2016

Abstract

Morphological retrieval is an effective approach to explore neurons' databases, as the morphology is correlated with neuronal types, regions, functions, etc. In this paper, we focus on the neuron identification and analysis via morphological retrieval. In our proposed framework, both global and local features are extracted to represent 3D neuron data. Then, compacted binary codes are generated from original features for efficient similarity search. As neuron cells usually have tree-topology structure, it is hard to distinguish different types of neuron simply via traditional binary coding or hashing methods based on Euclidean distance metric and/or linear hyperplanes. Thus, we propose a novel binary coding method based on the maximum inner product search (MIPS), which is not only more easier to learn the binary coding function, but also preserves the non-linear characteristics of neuron morphology data. We evaluate the proposed method on more than 17,000 neurons, by validating the retrieved neurons with associated cell types and brain regions. Experimental results show the superiority of our approach in neuron morphological retrieval compared with other state-of-the-art methods. Moreover, we demonstrate its potential use case in the identification and analysis of neuron characteristics.

Direct Estimation of Permeability Maps for Low-Dose CT Perfusion

Ruogu Fang, Ajay Gupta, Pina C. Sanelli
Conference ISBI, IEEE International Symposium on Biomedical Imaging, Prague, Czech Republic, April, 2016

Abstract

With the goal of achieving low radiation exposure from medical imaging, computed tomography perfusion (CTP) introduces challenging problems for both image reconstruction and perfusion parameter estimation in the qualitative and quantitative analyses. Conventional approaches address the reconstruction and the estimation processes separately. Since the hemodynamic parameter maps have much lower dimensionality than the original sinogram data, estimating hemodynamic parameters directly from sinogram will further reduce radiation exposure and save computational resources to reconstruct the intermediate time-series images. In this work, we propose the first direct estimation framework for CTP that integrates the time-series image reconstruction, contrast conversion, hematocrit correction and hemodynamic parameter estimation in one optimization function, which is solved using an efficient algorithm. Evaluations on the digital brain perfusion phantom and a clinical acute stroke subject demonstrate that the proposed direct estimation framework boosts the estimation accuracy remarkably in CTP scanning with lower radiation exposure.

Automatic Segmentation of Lower Extremity Ulcers in Near-Infrared Optical Imaging

Ruogu Fang, Xing Pang, Arash Dadkhah, Jiali Lei, Elizabeth Solis, Suset Rodriguesz, Francisco Perez-Clavijo, Stephen Wigley, Charles Buscemi, Anuradha Godvarty.
Conference ISBI, IEEE International Symposium on Biomedical Imaging, Prague, Czech Republic, April, 2016

Near-Infrared Optical Imaging and Wound Segmentation in Lower Extremity Ulcers

Xing Pang, Arash Dadkhah, Jaili Lei, Elizabeth Solis, Suset Rodriguez, Francisco Perez-Clavijo, Stephen Wigley, Ruogu Fang, Anuradha Godvarty.
ConferenceOSA, Optical Society of America Annual Meeting, 2016.

Abstract

Near-Infrared (NIR) optical imaging can reveal tissue oxygenation of the wound, complementing the visual inspection of the surface granulation. Herein, graph cuts algorithm is applied to segment NIR images of the wound from its peripheries.

Wound Size Measurement of Lower Extremity Ulcers Using Segmentation Algorithms

Arash Dadkhah, Xing Pang, Elizabeth Solis, Ruogu Fang, Anuradha Godvarty.
Conference SPIE Proceedings in Photonics West, San Francisco, February 2016.

Abstract

Lower extremity ulcers are one of the most common complications that not only affect many people around the world but also have huge impact on economy since a large amount of resources are spent for treatment and prevention of the diseases. Clinical studies have shown that reduction in the wound size of 40% within 4 weeks is an acceptable progress in the healing process. Quantification of the wound size plays a crucial role in assessing the extent of healing and determining the treatment process. To date, wound healing is visually inspected and the wound size is measured from surface images. The extent of wound healing internally may vary from the surface. A near-infrared (NIR) optical imaging approach has been developed for non-contact imaging of wounds internally and differentiating healing from non-healing wounds. Herein, quantitative wound size measurements from NIR and white light images are estimated using a graph cuts and region growing image segmentation algorithms. The extent of the wound healing from NIR imaging of lower extremity ulcers in diabetic subjects are quantified and compared across NIR and white light images. NIR imaging and wound size measurements can play a significant role in potentially predicting the extent of internal healing, thus allowing better treatment plans when implemented for periodic imaging in future.

Efficient 4D Non-Local Tensor Total-Variation for Low-Dose CT Perfusion Deconvolution

Ruogu Fang, Ming Ni, Junzhou Huang, Qianmu Li, Tao Li
JournalMedical Computer Vision: Algorithms for Big DataChapter, no.16, Lecture Notes in Computer Science, 2015.

Abstract

Tensor total variation deconvolution has been recently proposed as a robust framework to accurately estimate the hemodynamic parameters in low-dose CT perfusion by fusing the local anatomicalstructure correlation and temporal blood flow continuation. However the locality property in the current framework constrains the search for anatomical structure similarities to the local neighborhood, missing the global and long-range correlations in the whole anatomical structure. This limitation has led to noticeable absence or artifact of delicate structures, including the critical indicators for the clinical diagnosis of cerebrovascular diseases. In this paper, we propose an extension of the TTV framework by introducing 4D non-local tensor total variation into the deconvolution to bridge the gap between non-adjacent regions of the same tissue classes. The non-local regularization using tensor total variation term is imposed on the spatio-temporal flow-scaled residue functions. An efficient algorithm and implementation of the non-local tensor total variation (NL-TTV) reduces the time complexity with fast similarity computation, accelerated optimization and parallel operations. Extensive evaluations on the clinical data with cerebrovascular diseases and normal subjects demonstrate the importance of non-local linkage and long-range connections for low-dose CT perfusion deconvolution.

Robust Low-dose CT Perfusion Deconvolution via Tensor Total-Variation Regularization

Ruogu Fang, Shaoting Zhang, Tsuhan Chen, Pina C. Sanelli.
JournalTMI, IEEE Transaction on Medical Imaging, vol.34, no.7, pp.1533-1548, July 2015.

Abstract

Acute brain diseases such as acute strokes and transit ischemic attacks are the leading causes of mortality and morbidity worldwide, responsible for 9% of total death every year. ‘Time is brain' is a widely accepted concept in acute cerebrovascular disease treatment. Efficient and accurate computational framework for hemodynamic parameters estimation can save critical time for thrombolytic therapy. Meanwhile the high level of accumulated radiation dosage due to continuous image acquisition in CT perfusion (CTP) raised concerns on patient safety and public health. However, low-radiation leads to increased noise and artifacts which require more sophisticated and time-consuming algorithms for robust estimation. In this paper, we focus on developing a robust and efficient framework to accurately estimate the perfusion parameters at low radiation dosage. Specifically, we present a tensor total-variation (TTV) technique which fuses the spatial correlation of the vascular structure and the temporal continuation of the blood signal flow. An efficient algorithm is proposed to find the solution with fast convergence and reduced computational complexity. Extensive evaluations are carried out in terms of sensitivity to noise levels, estimation accuracy, contrast preservation, and performed on digital perfusion phantom estimation, as well as in-vivo clinical subjects. Our framework reduces the necessary radiation dose to only 8% of the original level and outperforms the state-of-art algorithms with peak signal-to-noise ratio improved by 32%. It reduces the oscillation in the residue functions, corrects overestimation of cerebral blood flow (CBF) and under-estimation of mean transit time (MTT), and maintains the distinction between the deficit and normal regions.

Guest Editorial: Sparsity Techniques in Medical Imaging.

Ruogu Fang, Tsuhan Chen, Dimitris Metaxas, Pina Sanelli, Shaoting Zhang.
JournalCMIG, Elsevier Journal of Computerized Medical Imaging and Graphics, vol. 46, no. 1, 2015.

Abstract

With the advent of the age for big data and complex structure, sparsity has been an important modeling tool in compressed sensing, machine learning, image processing, neuroscience and statistics. In the medical imaging field, sparsity methods have been successfully used in image reconstruction, image enhancement, image segmentation, anomaly detection, disease classification, and image database retrieval. Developing more powerful sparsity models for a large range of medical imaging and medical image analysis problems as well as efficient optimization and learning algorithm will keep being a main research topic in this field. The goal of this special issue is to publish original and high quality papers on innovation research and development in medical imaging and medical image analysis using sparsity techniques. This special issue will help advance the scientific research within the field of sparsity methods for medical imaging.

Tissue-Specific Sparse Deconvolution for Brain CT Perfusion.

Ruogu Fang,Haodi Jiang, Junzhou Huang.
Journal CMIG, Elsevier Journal of Computerized Medical Imaging and Graphics, vol.46, no.1, pp. 64-72, 2015.

Abstract

Enhancing perfusion maps in low-dose computed tomography perfusion (CTP) for cerebrovascular disease diagnosis is a challenging task, especially for lowcontrast tissue categories where infarct core and ischemic penumbra usually occur. Sparse perfusion deconvolution has been recently proposed to effectively improve the image quality and diagnostic accuracy of low-dose perfusion CT by extracting the complementary information from the high-dose perfusion maps to restore the low-dose using a joint spatio-temporal model. However the lowcontrast tissue classes where infarct core and ischemic penumbra are likely to occur in cerebral perfusion CT tend to be over-smoothed, leading to loss of essential biomarkers. In this paper, we propose a tissue-specific sparse deconvolution approach to preserve the subtle perfusion information in the low-contrast tissue classes. We first build tissue-specific dictionaries from segmentations of high-dose perfusion maps using online dictionary learning, and then perform deconvolution-based hemodynamic parameters estimation for block-wise tissue segments on the low-dose CTP data. Extensive validation on clinical datasets of patients with cerebrovascular disease demonstrates the superior performance of our proposed method compared to state-of-art, and potentially improve diagnostic accuracy by increasing the differentiation between normal and ischemic tissues in the brain

Efficient 4D Non-Local Tensor Total-Variation for Low-Dose CT Perfusion Deconvolution

Ruogu Fang, Ming Ni, Junzhou Huang, Qianmu Li, and Tao Li
Conference The 18th Annual International Conference on Medical Image Computing and Computer Assisted Intervention, Workshop on Medical Computer Vision, Munich, Germany, October 2015.

Wound Segmentation in Near-Infrared Optical Imaging

Ruogu Fang, Xing Pang, Arash Dadkhah, Jiali Lei, Elizabeth SOlis, Suset ROdriguez, Francisco Perez-Calvijo, Stephen Wigley, Charles Buscemi, Anuradha Godvarty.
Conference Innovation in Wound Healing, Hawks Cay, FL. Dec. 2015.

Fast Preconditioning for Accelerated Multi-Contrast MRI Reconstruction

Ruoyu Li, Yeqing Li, Ruogu Fang,Shaoting Zhang, Hao Pan, Junzhou Huang
Conference MICCAI'15, In Proc. of the 18th Annual International Conference on Medical Image Computing and Computer Assisted Intervention, Munich, Germany, October 2015.

Robust Low-Dose CT Perfusion Deconvolution via Non-Local Tensor Total Variation

Ruogu Fang, Ming Ni, Junzhou Huang, Qianmu Li, Tao Li
Conference BMES, Biomedical Engineering Society Annual Meeting, Tampa, FL, October 2015.

Introduction

Stroke and cerebrovascular diseases are the leading cause of serious, long-term disability in the United States. Computed tomography perfusion (CTP) is one of the most widely accepted imaging modality for stroke care. However, the high radiation exposure of CTP has lead to increased cancer risk. Tensor total variation (TTV)[1] has been proposed to stabilize the quantification of perfusion parameters by integrating the anatomical structure correlation. Yet the locality limitation of the neighborhood region has led to noticeable absence or inflation of the delicate structures which are critical indicators for the clinical diagnosis. In this work, we propose a non-local tensor total variation (NL-TTV) deconvolution method to by incorporating the long-range dependency and the global connections in the spatio-temporal domain

A Spatio-Temporal Low-rank Total Variation Approach for Denoising Arterial Spin Labeling MRI Data

Ruogu Fang,Junzhou Huang, Wen-Ming Luh.
Conference ISBI'15, The IEEE International Symposium on Biomedical Imaging (ISBI), NYC, USA, April, 2015.

Abstract

Arterial spin labeling MRI (ASL-MRI) can provide quantitative signals correlated to the cerebral blood flow and neural activity. However, the low signal-to-noise ratio in ASL requires repeated acquisitions to improve the signal reliability, leading to prolonged scanning time. At fewer repetitions, noise and corruptions arise due to motion and physiological artifacts, introducing errors into the cerebral blood flow estimation. We propose to recover the ASL-MRI data from the noisy and corrupted observations at shorter scanning time with a spatio-temporal low-rank total variation method. The low-rank approximation uses the similarity of the repetitive scans, and the total variation regularization considers the local spatial consistency. We compare with the state-of-art robust M-estimator for ASL cerebral blood flow map estimation. Validation on simulated and real data demonstrate the robustness of the proposed method at fewer scanning repetitions and with random corruption

Leveraging Coupled Multi-Index for Scalable Retrieval of Mammographic Masses.

Menglin Jiang, Shaoting Zhang, Ruogu Fang, Dimitris Metaxas.
Conference ISBI'15, The IEEE International Symposium on Biomedical Imaging (ISBI), NYC, USA, April, 2015. Oral presentation 130 / 714 = 18%

4-D Spatio-Temporal MR Perfusion Deconvolution via Tensor Total Variation.

Ruogu Fang
Conference ISMRM'15, International Society for Magnetic Resonance in Medicine (ISMRM) Annual Meeting, Toronto, Canada, May-June 2015. Oral presentation

Introduction

4-D dynamic susceptibility contrast (DSC) magnetic resonance imaging (MRI) is a well-established perfusion technique for non-invasive characterization of tissue dynamics, with promising applications in assessing a wide range of diseases, as well as monitoring response of therapeutic interventions). DSC-MRI provides critical real-time information by tracking the first-pass of an injected contrast-agent (e.g. gadolinium) with T2*-weighted MRI. The spatio-temproal data, consisting of contrast concentration signals for each voxel of a volume, are deconvolved from the arterial input function (AIF) and then post-processed to generate perfusion parameter maps, typically including the cerebral blood flow (CBF), cerebral blood volume (CBV), mean transit time (MTT) and time to peak (TTP). The most popular deconvolution method is truncated singular value decomposition (TSVD)1,2 and its variants3 , which fail to exploit the spatio-temporal nature of the 4D data with both the anatomical structure and the temporal continuation. This work adapts and demonstrates the feasibility of a 4-D tensor total variation (TTV) deconvolution approach, which has been proposed for CT perfusion4 , to brain MR perfusion, with evaluation on synthetic data and clinical DSC-MRI data for glioblastomas, the most common type of brain cancer. The method is guaranteed to convergence to global optimal because of the convex cost function and presents a more elegant framework of total variation for the deconvolution, compared to recent efforts5,6 which either do not have a global optimal solution for the non-convex case or need to handcraft spatial and temporal regularization terms.

Improving Low-Dose Blood-Brain Barrier Permeability Quantification Using Sparse High-Dose Induced Prior for Patlak Model.

Ruogu Fang, Kolbeinn Karlsson, Tsuhan Chen, Pina C. Sanelli.
JournalMedIA'14, Medical Image Analysis, Volume 18, Issue 6, Pages 866-880, 2014.

Abstract

Blood-brain barrier permeability (BBBP) measurements extracted from the perfusion computed tomography (PCT) using the Patlak model can be a valuable indicator to predict hemorrhagic transformation in patients with acute stroke. Unfortunately, the standard Patlak model based PCT requires excessive radiation exposure, which raised attention on radiation safety. Minimizing radiation dose is of high value in clinical practice but can degrade the image quality due to the introduced severe noise. The purpose of this work is to construct high quality BBBP maps from low-dose PCT data by using the brain structural similarity between different individuals and the relations between the high- and low-dose maps. The proposed sparse high-dose induced (shd-Patlak) model performs by building a high-dose induced prior for the Patlak model with a set of location adaptive dictionaries, followed by an optimized estimation of BBBP map with the prior regularized Patlak model. Evaluation with the simulated low-dose clinical brain PCT datasets clearly demonstrate that the shd-Patlak model can achieve more significant gains than the standard Patlak model with improved visual quality, higher fidelity to the gold standard and more accurate details for clinical analysis.

Tensor Total-Variation Regularized Deconvolution for Efficient Low-Dose CT Perfusion.

Ruogu Fang,Pina Sanelli, Shaoting Zhang, Tsuhan Chen.
ConferenceMICCAI'14, The 17th Annual International Conference on Medical Image Computing and Computer Assisted Intervention, Boston, USA, September, 2014.

Abstract

Acute brain diseases such as acute stroke and transit ischemic attacks are the leading causes of mortality and morbidity worldwide, responsible for 9% of total death every year. ‘Time is brain' is a widely accepted concept in acute cerebrovascular disease treatment. Efficient and accurate computational framework for hemodynamic parameters estimation can save critical time for thrombolytic therapy. Meanwhile the high level of accumulated radiation dosage due to continuous image acquisition in CT perfusion (CTP) raised concerns on patient safety and public health. However, low-radiation will lead to increased noise and artifacts which require more sophisticated and time-consuming algorithms for robust estimation. We propose a novel efficient framework using tensor totalvariation (TTV) regularization to achieve both high efficiency and accuracy in deconvolution for low-dose CTP. The method reduces the necessary radiation dose to only 8% of the original level and outperforms the state-of-art algorithms with estimation error reduced by 40%. It also corrects over-estimation of cerebral blood flow (CBF) and under-estimation of mean transit time (MTT), at both normal and reduced sampling rate. An efficient

Anisotropic Tensor Total Variation Regularization For Low Dose Low CT Perfusion Deconvolution.

Ruogu Fang, Tsuhan Chen, Pina C. Sanelli.
ConferenceMICCAI'14, The 17th Annual International Conference on Medical Image Computing and Computer Assisted Intervention, Workshop on Sparsity Techniques in Medical Imaging, Boston, USA, September, 2014.

Abstract

Tensor total variation (TTV) regularized deconvolution has been proposed for robust low radiation dose CT perfusion. In this paper, we extended TTV algorithm with anisotropic regularization weighting for the temporal and spatial dimension. We evaluated TTV algorithm on synthetic dataset for bolus delay, uniform region variability and contrast preservation, and on clinical dataset for reduced sampling rate with visual and quantitative comparison. The extensive experiments demonstrated promising results of TTV compared to baseline and state-of-art algorithms in low-dose and low sampling rate CTP deconvolution with insensitivity to bolus delay. This work further demonstrates the effectiveness and potential of TTV algorithm's clinical usage for cerebrovascular diseases with significantly reduced radiation exposure and improved patient safety.

Towards Robust Deconvolution in Medical Imaging: Informatics, Diagnosis and Treatment.

Ruogu Fang
PhD ThesisSchool of Electrical and Computer Engineering, Cornell University, August 2014.

Introduction

Deconvolution in medical imaging is an inverse process to estimate the hemodynamic parameters, such as the blood flow, blood volume and mean transit time, from the measurements in the medical images, as illustrated in Figure 1.1. A traditional machinery employed for estimating these hemodynamic parameters is to compute the impulse response function of each voxel independently using matrix factorization or curve fitting. For instance, singular value decomposition (SVD) is widely used in current commercial softwares to inverse the convolution process.

Towards Robust Deconvolution of Low-Dose Perfusion CT: Sparse Perfusion Deconvolution Using Online Dictionary Learning.

Ruogu Fang, Tsuhan Chen, Pina C. Sanelli.
JournalMedIA'13, Medical Image Analysis, Volume 17, Issue 4, Pages 417-428, 2013. (5 Year Impact Factor: 4.512)

Abstract

Computed tomography perfusion (CTP) is an important functional imaging modality in the evaluation of cerebrovascular diseases, particularly in acute stroke and vasospasm. However, the post-processed parametric maps of blood flow tend to be noisy, especially in low-dose CTP, due to the noisy contrast enhancement profile and the oscillatory nature of the results generated by the current computational methods. In this paper, we propose a robust sparse perfusion deconvolution method (SPD) to estimate cerebral blood flow in CTP performed at low radiation dose. We first build a dictionary from high-dose perfusion maps using online dictionary learning and then perform deconvolution-based hemodynamic parameters estimation on the low-dose CTP data. Our method is validated on clinical data of patients with normal and pathological CBF maps. The results show that we achieve superior performance than existing methods, and potentially improve the differentiation between normal and ischemic tissue in the brain.

Tissue-Specific Sparse Deconvolution for Low-Dose CT Perfusion.

Ruogu Fang, Tsuhan Chen, Pina C. Sanelli.
ConferenceMICCAI'13, The 16th Annual International Conference on Medical Image Computing and Computer Assisted Intervention, Japn, September, 2013.

Abstract

Sparse perfusion deconvolution has been recently proposed to effectively improve the image quality and diagnostic accuracy of low-dose perfusion CT by extracting the complementary information from the high-dose perfusion maps to restore the low-dose using a joint spatio-temporal model. However the low-contrast tissue classes where infarct core and ischemic penumbra usually occur in cerebral perfusion CT tend to be over-smoothed, leading to loss of essential biomarkers. In this paper, we extend this line of work by introducing tissuespecific sparse deconvolution to preserve the subtle perfusion information in the low-contrast tissue classes by learning tissue-specific dictionaries for each tissue class, and restore the low-dose perfusion maps by joining the tissue segments reconstructed from the corresponding dictionaries. Extensive validation on clinical datasets of patients with cerebrovascular disease demonstrates the superior performance of our proposed method with the advantage of better differentiation between abnormal and normal tissue in these patients.

Sparsity-Based Deconvolution of Low-Dose Perfusion CT Using Learned Dictionaries.

Ruogu Fang, Tsuhan Chen, Pina C. Sanelli.
ConferenceMICCAI'12, The 15th Annual International Conference on Medical Image Computing and Computer Assisted Intervention, Nice, France, October, 2012. Lecture Notes in Computer Science Volume 7510, 2012, pp 272-280.

Sparsity-Based Deconvolution Of Low-Dose Brain Perfusion CT In Subarachnoid Hemorrhage Patients.

Ruogu Fang, Tsuhan Chen, Pina C. Sanelli.
ConferenceISBI'12, The 9th International Symposium on Biomedical Imaging, pp. 872-875, Barcelona, Spain, May 2012. Oral presentation.

Abstract

Functional imaging serves as an important supplement to anatomical imaging modalities such as MR and CT in modern health care. In perfusion CT (CTP), hemodynamic parameters are derived from the tracking of the first-pass of the contrast bolus entering a tissue region of interest. In practice, however, the post-processed parametric maps tend to be noisy, especially in low-dose CTP, in part due to the noisy contrast enhancement profile and oscillatory nature of results generated by current computational methods. In this paper, we propose a sparsity-based perfusion parameter deconvolution approach that consists of a non-linear processing based on sparsity prior in terms of residue function dictionaries. Our simulated results from numericaldata and experiments in aneurysmal subarachnoid hemorrhage patients with clinical vasospasm show that the algorithm improves the quality and reduces the noise of the perfusion parametric maps in low-dose CTP, compared to state-of-the-art methods

Radiation dose reduction in computed tomography perfusion using spatial-temporal Bayesian methods.

Ruogu Fang, Ashish Raj, Tsuhan Chen, Pina C. Sanelli
ConferenceSPIE'12, In Proceedings of SPIE Medical Imaging, Volume 8313, Paper #831345, April, 2012.

Abstract

In current computed tomography (CT) examinations, the associated X-ray radiation dose is of significant concern to patients and operators, especially CT perfusion (CTP) imaging that has higher radiation dose due to its cine scanning technique. A simple and cost-effective means to perform the examinations is to lower the milliampere-seconds (mAs) parameter as low as reasonably achievable in data acquisition. However, lowering the mAs parameter will unavoidably increase data noise and degrade CT perfusion maps greatly if no adequate noise control is applied during image reconstruction. To capture the essential dynamics of CT perfusion, a simple spatial-temporal Bayesian method that uses a piecewise parametric model of the residual function is used, and then the model parameters are estimated from a Bayesian formulation of prior smoothness constraints on perfusion parameters. From the fitted residual function, reliable CTP parameter maps are obtained from low dose CT data. The merit of this scheme exists in the combination of analytical piecewise residual function with Bayesian framework using a simpler prior spatial constrain for CT perfusion application. On a dataset of 22 patients, this dynamic spatial-temporal Bayesian model yielded an increase in signal-tonoise-ratio (SNR) of 78% and a decrease in mean-square-error (MSE) of 40% at low dose radiation of 43mA.

System and Method For Interactive Segmentation On Mobile Devices in a Cloud Computing Environment

Ruogu Fang,Leo Grady, Gianluca Paladini.
PatentsSiemens Corporation. Patent No: US20130272587 A1, WO2012027259 A2, WO2012027259 A3, approved on 4/19/2012.

Abstract

A mobile device (160) for medical image analysis is disclosed. The mobile device (160) includes a display (162), a communication module (218), a memory (204) configured to store processor-executable instructions (224) and a processor (202) in communication with the display (162), the communication module (218) and the memory (204). The processor (202) being configured to execute the processor-executable instructions (224) to implement a compression routine to generate a compressed representation of a medical image stored in the memory (204), transmit the compressed representation to a remote device (110) via the communication module (218), receive segmented results from the remote device (110), wherein the segmented results are derived from a reconstruction of the compressed representation generated at the remote device (110), and present, via the display (162), a segmented medical image based on the received segmented results.

Segmentation of Liver Tumor Using Efficient Global Optimal Tree Metrics Graph Cuts.

Ruogu Fang, Ramin Zabih, Ashish Raj, Tsuhan Chen.
ConferenceMICCAI'11, Abdominal Imaging, International Conference on Medical Image Computing and Computer Assisted Intervention, pp. 51-59, September, 2011.

Abstract

We propose a novel approach that applies global optimal tree-metrics graph cuts algorithm on multi-phase contrast enhanced contrast enhanced MRI for liver tumor segmentation. To address the difficulties caused by low contrasted boundaries and high variability in liver tumor segmentation, we first extract a set of features in multi-phase contrast enhanced MRI data and use color-space mapping to reveal spatial-temporal information invisible in MRI intensity images. Then we apply efficient tree-metrics graph cut algorithm on multi-phase contrast enhanced MRI data to obtain global optimal labeling in an unsupervised framework. Finally we use tree-pruning method to reduce the number of available labels for liver tumor segmentation. Experiments on realworld clinical data show encouraging results. This approach can be applied to various medical imaging modalities and organs.

Tree-Metrics Graph Cuts For Brain MRI Segmentation With Tree Cutting.

Ruogu Fang, Joyce Yu-hsin Chen, Ramin Zabih, Tsuhan Chen.
ConferenceWNYIPW'10, IEEE Western New York Image Processing Workshop, pp. 10-13, Rochesester, NY. USA. November, 2010. oral presentation

Abstract

We tackle the problem of brain MRI image segmentation using the tree-metric graph cuts (TM) algorithm, a novel image segmentation algorithm, and introduce a “tree-cutting” method to interpret the labeling returned by the TM algorithm as tissue classification for the input brain MRI image. The approach has three steps: 1) pre-processing, which generates a tree of labels as input to the TM algorithm; 2) a sweep of the TM algorithm, which returns a globally optimal labeling with respect to the tree of labels; 3) post-processing, which involves running the “tree-cutting” method to generate a mapping from labels to tissue classes (GM, WM, CSF), producing a meaningful brain MRI segmentation. The TM algorithm produces a globally optimal labeling on tree metrics in one sweep, unlike conventional methods such as EMS and EM-style geo-cuts, which iterate the expectation maximization algorithm to find hidden patterns and produce only locally optimal labelings. When used with the “tree-cutting” method, the TM algorithm produces brain MRI segmentations that are as good as the Unified Segmentation algorithm used by SPM8, using a much weaker prior. Comparison with the current approaches shows that our method is faster and that our overall segmentation accuracy is better.

Kinship Classification by Modeling Facial Feature Heredity.

Ruogu Fang, Joyce Yu-hsin Chen, Ramin Zabih, Tsuhan Chen.
ConferenceWNYIPW'10, IEEE Western New York Image Processing Workshop, pp. 10-13, Rochesester, NY. USA. November, 2010. oral presentation

Abstract

We tackle the problem of brain MRI image segmentation using the tree-metric graph cuts (TM) algorithm, a novel image segmentation algorithm, and introduce a “tree-cutting” method to interpret the labeling returned by the TM algorithm as tissue classification for the input brain MRI image. The approach has three steps: 1) pre-processing, which generates a tree of labels as input to the TM algorithm; 2) a sweep of the TM algorithm, which returns a globally optimal labeling with respect to the tree of labels; 3) post-processing, which involves running the “tree-cutting” method to generate a mapping from labels to tissue classes (GM, WM, CSF), producing a meaningful brain MRI segmentation. The TM algorithm produces a globally optimal labeling on tree metrics in one sweep, unlike conventional methods such as EMS and EM-style geo-cuts, which iterate the expectation maximization algorithm to find hidden patterns and produce only locally optimal labelings. When used with the “tree-cutting” method, the TM algorithm produces brain MRI segmentations that are as good as the Unified Segmentation algorithm used by SPM8, using a much weaker prior. Comparison with the current approaches shows that our method is faster and that our overall segmentation accuracy is better.

Towards Computational Models of Kinship Verification.

Ruogu Fang, Kevin D. Tang, Noah Snavely, Tsuhan Chen.
ConferenceICIP'10, The 17th IEEE International Conference on Image Processing , Hong Kong, October, 2010. Oral presentation ICIP 2010 Best Paper Award

Abstract

We tackle the challenge of kinship verification using novel feature extraction and selection methods, automatically classifying pairs of face images as “related” or “unrelated” (in terms of kinship). First, we conducted a controlled online search to collect frontal face images of 150 pairs of public figures and celebrities, along with images of their parents or children. Next, we propose and evaluate a set of low-level image features that for use in this classification problem. After selecting the most discriminative inherited facial features, we demonstrate a classification accuracy of 70.67% on a test set of image pairs using K-Nearest-Neighbors. Finally, we present an evaluation of human performance on this problem.

Adaptive Scale Robust Feature Density Approximation For Visual Object Representation And Tracking

Chongyang Liu, Ruogu Fang, and Nelson H.C.Yung
Conference IEEE International Conference on Computer Vision Theory and Applications, Lisboa, Portugal, 2009.

Current Teaching

  • 2019 Fall

    BME3053C Computer Applications for BME

    The objectives this course are: 1) Develop a proficiency in the use of computer programming (specifically, MATLAB) to analyze biomedical measurements. 2) Develop an understanding of biomedical engineering problems that require quantitative analysis and visualization.

Teaching History

    • 2018 Fall

      BME3053C Computer Applications for BME

      The objectives this course are: 1) Develop a proficiency in the use of computer programming (specifically, MATLAB) to analyze biomedical measurements. 2) Develop an understanding of biomedical engineering problems that require quantitative analysis and visualization.

    • 2017 Fall

      BME3053C Computer Applications for BME

      The objectives this course are: 1) Develop a proficiency in the use of computer programming (specifically, MATLAB) to analyze biomedical measurements. 2) Develop an understanding of biomedical engineering problems that require quantitative analysis and visualization.

    2017 Spring

    CAP 5771 Principles of Data Mining

    Data Mining is the nontrivial extraction of implicit, previously unknown, and potentially useful information from data. It has gradually matured as a discipline merging ideas from statistics, machine learning, database and etc. This is an introductory graduate course for master and PhD computer science students on the topic of Data Mining. Topics include data mining applications, knowing your data, data exploration, and various data mining techniques (such as classification, association, clustering, anomaly detection) and advanced topics in data mining.

  • 2017 Spring

    CAP 4770 Introduction to Data Mining

    Data Mining is the nontrivial extraction of implicit, previously unknown, and potentially useful information from data. It has gradually matured as a discipline merging ideas from statistics, machine learning, database and etc. This is an introductory course for junior/senior computer science undergraduate students on the topic of Data Mining. Topics include data mining applications, data preparation, data reduction and various data mining techniques (such as association, clustering, classification, anomaly detection).

  • 2016 Fall

    CAP 4770 Introduction to Data Mining

    Data Mining is the nontrivial extraction of implicit, previously unknown, and potentially useful information from data. It has gradually matured as a discipline merging ideas from statistics, machine learning, database and etc. This is an introductory course for junior/senior computer science undergraduate students on the topic of Data Mining. Topics include data mining applications, data preparation, data reduction and various data mining techniques (such as association, clustering, classification, anomaly detection).

  • 2016 Spring

    CAP 5610 Machine Learning

    Machine learning is concerned with the question of how to make computers learn from experience. The ability to learn is not only central to most aspects of intelligent behavior, but machine learning techniques have become key components of many software systems. For examples, machine learning techniques are used to create spam filters, to analyze customer purchase data, to understand natural language, or to detect fraudulent credit card transactions.

  • 2015 Fall

    CAP 4770 Introduction to Data Mining

    Data Mining is the nontrivial extraction of implicit, previously unknown, and potentially useful information from data. It has gradually matured as a discipline merging ideas from statistics, machine learning, database and etc. This is an introductory course for junior/senior computer science undergraduate students on the topic of Data Mining. Topics include data mining applications, data preparation, data reduction and various data mining techniques (such as association, clustering, classification, anomaly detection).

  • 2015 Spring

    CAP 5610 Machine Learning

    Machine learning is concerned with the question of how to make computers learn from experience. The ability to learn is not only central to most aspects of intelligent behavior, but machine learning techniques have become key components of many software systems. For examples, machine learning techniques are used to create spam filters, to analyze customer purchase data, to understand natural language, or to detect fraudulent credit card transactions.

Filter by type:

Domain Shift

CodeAdversarial Discriminative Adaptation and Ensembling Collaborative Learning for Domain Shift in Unsupervised Optic Disc and Cup Segmentation

Citation

  • Peng Liu, Bin Kong, Zhongyu Li, Shaoting Zhang, and Ruogu Fang, 2019. CFEA: Collaborative Feature Ensembling Adaptation for Domain Adaptation in Unsupervised Optic Disc and Cup Segmentation. Medical Image Analysis and Computer Assisted Intervention.

CT Perfusion Toolbox

CodeToolbox for CT perfusion image processing and computation, including image loading, preprocessing, reconstruction, quantification, and example code.

Citation

  • Fang, R., Chen, T. and Sanelli, P.C., 2013. Towards robust deconvolution of low-dose perfusion CT: Sparse perfusion deconvolution using online dictionary learning. Medical image analysis, 17(4), pp.417-428.
  • Fang, R., Zhang, S., Chen, T. and Sanelli, P.C., 2015. Robust low-dose CT perfusion deconvolution via tensor total-variation regularization. IEEE transactions on medical imaging, 34(7), pp.1533-1548.

Tensor Total Variation

CodeToolbox for Tensor Total Variation quantfication of CT perfusion parameters in low-dose CT perfusion.

Citation

  • Fang, R., Zhang, S., Chen, T. and Sanelli, P.C., 2015. Robust low-dose CT perfusion deconvolution via tensor total-variation regularization. IEEE transactions on medical imaging, 34(7), pp.1533-1548.
  • Fang, R., Sanelli, P.C., Zhang, S. and Chen, T., 2014, September. Tensor total-variation regularized deconvolution for efficient low-dose CT perfusion. In International Conference on Medical Image Computing and Computer-Assisted Intervention (pp. 154-161). Springer, Cham.

Sparse High-Dose Induced Patlak Model for Permeability

CodeSparse high-dose induced Patlak model for Permeability quantification in low-dose CT perfusion.

Citation

  • Fang, R., Karlsson, K., Chen, T. and Sanelli, P.C., 2014. Improving low-dose blood–brain barrier permeability quantification using sparse high-dose induced prior for Patlak model. Medical image analysis, 18(6), pp.866-880.

Sparse Perfusion Deconvolution Toolbox

CodeSparse perfusion deconvolution toolbox using dictionary learning and sparse coding for low-dose CT perfusion parameters quantification.

Citation

  • Fang, R., Chen, T. and Sanelli, P.C., 2012, October. Sparsity-based deconvolution of low-dose perfusion CT using learned dictionaries. In International Conference on Medical Image Computing and Computer-Assisted Intervention (pp. 272-280). Springer Berlin Heidelberg.
  • Fang, R., Chen, T. and Sanelli, P.C., 2013. Towards robust deconvolution of low-dose perfusion CT: Sparse perfusion deconvolution using online dictionary learning. Medical image analysis, 17(4), pp.417-428.

Kinship Classification Dataset

DataFamily101 Dataset: first large-scale dataset of families across several generations. It contains 101 different family with distinct family names, including 206 nuclear families, 607 individuals, with 14,816 images.

Citation

  • Ruogu Fang, Andrew C. Gallagher, Tsuhan Chen, Alexander Loui. Kinship Classification by Modeling Facial Feature Heredity. IEEE International Conference on Image Processing, Australia, 2013 (ICIP '13)

Kinship Verification Dataset

DataCornell Kinship Verification Dataset (143 pairs of parents and children)

Citation

  • Ruogu Fang, Kevin D. Tang, Noah Snavely, Tsuhan Chen. Towards Computational Models of Kinship Verification. IEEE International Conference on Image Processing, Hong Kong, September 2010 (ICIP '10)

How to apply

Please send me your CV and transcript, and a brief research statement of why you want to join SMILE lab as an undergraduate researcher, what related research projects you have been involved, and why you think you will be a good undergraduate researcher in our lab.

We look forward to your smile at SMILE Lab to make your day!

At My Office

J287 Biomedical Science Building
University of Florida
1275 Center Dr.
Gainesville, FL, 32611.