Share Email Print
cover

Proceedings Paper

Computer aided diagnosis of diabetic peripheral neuropathy
Author(s): Viktor Chekh; Peter Soliz; Elizabeth McGrew; Simon Barriga; Mark Burge; Shuang Luan
Format Member Price Non-Member Price
PDF $14.40 $18.00
cover GOOD NEWS! Your organization subscribes to the SPIE Digital Library. You may be able to download this paper for free. Check Access

Paper 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.

Paper Details

Date Published: 24 March 2014
PDF: 6 pages
Proc. SPIE 9035, Medical Imaging 2014: Computer-Aided Diagnosis, 90353F (24 March 2014); doi: 10.1117/12.2043286
Show Author Affiliations
Viktor Chekh, Univ. of New Mexico (United States)
Peter Soliz, VisionQuest Biomedical, LLC (United States)
Elizabeth McGrew, VisionQuest Biomedical, LLC (United States)
Simon Barriga, VisionQuest Biomedical, LLC (United States)
Mark Burge, Univ. of New Mexico (United States)
Shuang Luan, Univ. of New Mexico (United States)


Published in SPIE Proceedings Vol. 9035:
Medical Imaging 2014: Computer-Aided Diagnosis
Stephen Aylward; Lubomir M. Hadjiiski, Editor(s)

© SPIE. Terms of Use
Back to Top