Congratulations to BME M.S. student, Shruti Siva Kumar, who won the GE Industrial Remix Challenge for her entry in Borescope.
The objective of the GE Industrial Remix Challenge is to identify innovative applications of an aviation fan blade technology, or a borescope technology, or a miniature MRI technology to achieve beneficial impact in other industrial and academic settings. The challenge focuses on three GE technologies: small MRI, aviation fan blade and borescope.
Shruti’s proposed application would change the diagnostic procedures for Periodontitis. Periodontitis is a severe form of gum infection (gingivitis) that affects the soft tissue and ultimately destroys bones supporting the teeth. A periodontal probe is an instrument in dentistry commonly used to measure pocket depths around the tooth to establish the state of health of the tissues that both surround and support the teeth. This procedure is both uncomfortable and does not give an accurate measurement since it relies solely on the diagnosis of the clinician.
Shruti’s proposed technique to increase the visualization power and depth measurement, is with a borescope, specifically GE’s Mentor Visual iQ Video Borescope with its probe customized to reach dental pockets. This probe would have a camera at the tip attached to the connector allowing scans of the area of interest or a set of regions. In addition to providing high-quality images and enabling video recording of the scan, the 3D phase measurement analysis software and the profile view can be used to calculate pocket depth, visualizing the destruction of soft tissue and bone attachment loss.
The benefits that would be generated would be:
- Better visualization of the infected area
- 3D view determining pocket depths thus reducing manual error
- Increase in patient comfort
- Better access to inaccessible areas such as back of the tooth-line found in conventional techniques
Shruti is pursuing a Master of Science degree in biomedical engineering at the University of Florida. She is a part-time student assistant at the UF Medical Image and Computational Analysis Lab and is currently, a team member representing UF Electrical and Computer Engineering at the Large-Scale Visual Recognition Challenge. Her prior projects include Raspberry Pi based Image processor for segmenting intracranial lesions in MRI images, EEG wavelet decomposition to demonstrate the therapeutic use of self-designed sleep inducer and Hybrid Signal Processing Approach to analyze physiological parameters in autistic children.