Processing and Visualization of Biomedical Imagery

The remarkable achievements of life sciences over the last decade in monitoring, detection, and treatment of various diseases have lead to even higher expectations by the society in the future. Although new sensing modalities are continuously being developed, followed by an ever increasing stream of biomedical data, the analysis capabilities by humans have not changed. Effective tools for analyzing, representing and visualizing the captured data are of essence for the future of patient diagnosis and treatment.

Automatic scoring of bowel preparation from colonoscopic imagery (2008-...)
Team: C. Esteve, J. Konrad, P. Ishwar
Collaboration: S. Singh (Boston University School of Medicine)
Funding: Self-funded
A recent study reported in the Annals of Internal Medicine (video) indicates that colonoscopy screening (visual examination of colon by a probe equipped with imaging sensor) may not be as efficient as previously thought. The results indicate a lower effectiveness of colonoscopy in the right side of the colon. One conclusion from the study is that the right side of the colon is more difficult to examine (especially for flat lesions). However, in the accompanying editorial an argument is made that colon preparation before the exam is critical to exam’s accuracy (any foreign material can obscure polyps, especially flat lesions). Therefore, an objective assessment of the quality of bowel preparation can be a helpful tool for patient and physician (a well-prepared bowel with no polyps is a good indication of patient’s health) and for medical insurer (extension of time to the next exam). In this project, we are developing an image processing algorithm to automatically rate bowel preparation quality based on color in colonoscopic imagery. Our results to-date are very promising and indicate a very high correlation with the average of subjective scores from 12 gastroenterologists watching each colonoscopy video twice. Our current work involves improving robustness and reducing computatinal complexity of the algorithm.

3-D automultiscopic displays in the treatment of motor functions and balance (2004-2007)
Team: S. Ince, J. Konrad
Collaboration: L. Oddsson (Neuromuscular Research Center at Boston University)
Collaboration: S. Williams (Boston University Medical Center)
Funding: National Institutes of Health
This is a joint effort between the Neuromuscular Research Center, Boston University Medical Center and the Department of Electrical and Computer Engineering to develop new tools to study the development, structure and function of the human brain. One particular area of interest here is the treatment of motor functions and balance such as during rehabilitation after stroke, spinal cord injury, or cerebral palsy, or during prolonged depravation of gravity such as observed by astronauts in space. Our role in this project is to develop eyewear-free 3-D visualization system based on lenticular technology (currently Synthagram SG222 and SG202 by Stereographics Corp. are being used) and off-the-shelf digital point-and-shoot cameras. The idea is to capture 2-3 views of a scene of interest to the patient (his/her own house, garden etc,) and then reconstruct additional 6-7 views digitally on a computer for the total of 9 views that can be comfortably viewed on the 3-D screen and help regain balance control. To this effect advanced intermediate view reconstruction methods are being developed. For details of view reconstruction click here.