Congratulations to UF BME Ph.D. student, Yao Xiao, who was awarded two prestigious travel awards!
IEEE/ACM Travel Award
The Institute of Electrical and Electronics Engineers (IEEE)/ Association for Computing Machinery (ACM) Connected Health Applications, Systems and Engineering Technologies (CHASE) honored Xiao with a travel award for her paper entitled, “RFMiner: Risk Factors Discovery and Mining for Preventive Cardiovascular Health.”
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. This paper proposes a cascaded classifier for heart attack prediction, which can boost the classification performance by cascading the individual classifiers with high precision or recall. The heart attack risk factors are identified and ranked by integrating various interestingness measures. Several novel risk factors are discovered such as employment status, seat belt usage, teeth removal and veteran status.
IEEE/ACM CHASE is a leading international conference in the field of connected health and is supported by the National Science Foundation. It aims at bringing together researchers worldwide working in the smart and connected health area to exchange innovative ideas and develop collaborations. Connected health can be defined as the use of Internet, sensing, communications and intelligent techniques in support of health-related Applications, Systems and Engineering. The conference was held in Philadelphia, PA on July 17-19, 2017.
MICCAI Travel Award
The Medical Image and Computing and Computer Assisted Intervention Society (MICCAI) honored Xiao with a travel award for her paper entitled, “STAR: Spatio-Temporal Architecture for super-Resolution in Low-Dose CT Perfusion.”
The aim of Xiao’s paper is to maintain the image quality within 1/3 of the original scanning time for reconstructed computed tomography perfusion (CTP) slices. CTP has been criticized for limited brain coverage which results in inadequate coverage of the lesion. STAR is a convolutional neural network base end-to-end structure for CT perfusion image super-resolution. By input with low-resolution patches from four spatio-temporal cross-sections can output with high-resolution reconstructed CTP slices. The goal of this research is to minimize the CTP scanning time, therefore, reduce the radiation exposure to patients.
The Medical Image Computing and Computer Assisted Intervention Society (the MICCAI Society) is the leading international conference in medical image analysis and computer-assisted intervention. The MICCAI Society is dedicated to the promotion, preservation and facilitation of research, education and practice in the field of medical image computing and computer-assisted medical interventions including biomedical imaging and robotics, through the organization and operation of regular high quality international conferences and publications which promote and foster the exchange and dissemination of advanced knowledge, expertise and experience in the field produced by leading institutions and outstanding scientists, physicians and educators around the world. This year’s conference is in Quebec City, Canada, September 10-14, 2017.
Xiao’s research interests are in the fields of biomedical image analysis and computational health informatics. She uses machine learning and computer vision to provide more reliable, feasible and affordable solutions for brain disease diagnosis and treatment decisions. Xiao’s Ph.D. advisor is Dr. Ruogu Fang.