Computer aided diagnosis of diabetic peripheral neuropathy

Viktor Chekh; Peter Soliz; Elizabeth McGrew; Simon Barriga; Mark Burge; Shuang Luan

doi:10.1117/12.2043286

24 March 2014 Computer aided diagnosis of diabetic peripheral neuropathy

Viktor Chekh, Peter Soliz, Elizabeth McGrew, Simon Barriga, Mark Burge, Shuang Luan

Proceedings Volume 9035, Medical Imaging 2014: Computer-Aided Diagnosis; 90353F (2014) https://doi.org/10.1117/12.2043286
Event: SPIE Medical Imaging, 2014, San Diego, California, United States

Abstract

Diabetic peripheral neuropathy (DPN) refers to the nerve damage that can occur in diabetes patients. It most often affects the extremities, such as the feet, and can lead to peripheral vascular disease, deformity, infection, ulceration, and even amputation. The key to managing diabetic foot is prevention and early detection. Unfortunately, current existing diagnostic techniques are mostly based on patient sensations and exhibit significant inter- and intra-observer differences. We have developed a computer aided diagnostic (CAD) system for diabetic peripheral neuropathy. The thermal response of the feet of diabetic patients following cold stimulus is captured using an infrared camera. The plantar foot in the images from a thermal video are segmented and registered for tracking points or specific regions. The temperature recovery of each point on the plantar foot is extracted using our bio-thermal model and analyzed. The regions that exhibit abnormal ability to recover are automatically identified to aid the physicians to recognize problematic areas. The key to our CAD system is the segmentation of infrared video. The main challenges for segmenting infrared video compared to normal digital video are (1) as the foot warms up, it also warms up the surrounding, creating an ever changing contrast; and (2) there may be significant motion during imaging. To overcome this, a hybrid segmentation algorithm was developed based on a number of techniques such as continuous max-flow, model based segmentation, shape preservation, convex hull, and temperature normalization. Verifications of the automatic segmentation and registration using manual segmentation and markers show good agreement.

Citation Download Citation

Viktor Chekh, Peter Soliz, Elizabeth McGrew, Simon Barriga, Mark Burge, and Shuang Luan "Computer aided diagnosis of diabetic peripheral neuropathy", Proc. SPIE 9035, Medical Imaging 2014: Computer-Aided Diagnosis, 90353F (24 March 2014); https://doi.org/10.1117/12.2043286

ACCESS THE FULL ARTICLE

INSTITUTIONAL
Select your institution to access the SPIE Digital Library.

SELECT YOUR INSTITUTION

PERSONAL
Sign in with your SPIE account to access your personal subscriptions or to use specific features such as save to my library, sign up for alerts, save searches, etc.

PERSONAL SIGN IN

No SPIE Account? Create one

PURCHASE THIS CONTENT

SUBSCRIBE TO DIGITAL LIBRARY

50 downloads per 1-year subscription

Members: $195

Non-members: $335 ADD TO CART

25 downloads per 1 - year subscription

Members: $145

Non-members: $250 ADD TO CART

PURCHASE SINGLE ARTICLE

Includes PDF, HTML & Video, when available