Automatic detection of diabetic foot complications with infrared thermography by asymmetric analysis

Abstract

Early identification of diabetic foot complications and their precursors is essential in preventing their devastating consequences, such as foot infection and amputation. Frequent, automatic risk assessment by an intelligent telemedicine system might be feasible and cost effective. Infrared thermography is a promising modality for such a system. The temperature differences between corresponding areas on contralateral feet are the clinically significant parameters. This asymmetric analysis is hindered by (1) foot segmentation errors, especially when the foot temperature and the ambient temperature are comparable, and by (2) different shapes and sizes between contralateral feet due to deformities or minor amputations. To circumvent the first problem, we used a color image and a thermal image acquired synchronously. Foot regions, detected in the color image, were rigidly registered to the thermal image. This resulted in 97.8% ± 1.1% sensitivity and 98.4% ± 0.5% specificity over 76 high-risk diabetic patients with manual annotation as a reference. Nonrigid landmark-based registration with B-splines solved the second problem. Corresponding points in the two feet could be found regardless of the shapes and sizes of the feet. With that, the temperature difference of the left and right feet could be obtained.

Telehealth and telemedicine applications for the diabetic foot: A systematic review

“…Liu et al demonstrated a sensitivity of 85% and a specificity of 98.4% for computer‐based automated detection of foot complications (e.g. callus, blisters, redness or ulceration) using asymmetric analysis of thermal images in combination with color imaging . Surprisingly, a large cohort study of 362 patients with a foot ulcer and a concomitant infection showed no significant change in left‐to‐right foot temperature difference …”

Some selected quantitative methods of thermal image analysis in Matlab

“…The measurement of foot temperature changes in time is used in many areas of medicine. It is indispensable in the widely understood diagnosis of: perfusion of diabetic foot – the changes in mean temperatures of some selected areas of the foot during administration of drugs (insulin and others) are of interest; hyperhidrosis – in assessing the impact of the patient's emotional state and other factors on perspiration; Raynaud's disease – in assessing the impact of treatment, and primarily the performed physiotherapy procedures, on feet cooling/warming; atherosclerosis – in assessing the degree of pathology and the impact of reliever medication on changes in blood supply and thereby temperature; foot mycosis (interdigital tinea) – in assessing the progress of treatment. …”

“…perfusion of diabetic foot – the changes in mean temperatures of some selected areas of the foot during administration of drugs (insulin and others) are of interest;…”

An intelligent telemedicine system for detection of diabetic foot complications

“…thermal imaging [120], and multispectral imaging [40], to automatically detect diabetic foot complications and to differentiate among these complications.…”

“…Details about this have been addressed in [120]. In this way, the PSI reconstruction would be focused on the foot area only to avoid the influence of the background.…”