In diabetic foot, the occurrence of an ulcer is often associated with hyperthermia. Hyperthermia is defined as a temperature greater than 2.2 ^o C in a given region of one of the foot compared to the temperature of the same region of the contralateral foot. Unfortunately, hyperthermia is not yet assessed in current diabetic foot therapy. In this paper, we propose an easy way to detect a possible hyperthermia by using an infrared camera. A specific acquisition protocol of the thermal images is proposed. A dedicated image analysis is developed: it is composed of a contour detection of the 2 feet using the Chan and Vese active contour method associated to the ICP rigid registration technique. Among 85 type II diabetes persons recruited in the Dos de Mayo hospital in Lima, Peru, 9 individuals show significant hyperthermia. It is expected that the new possibility of detecting hyperthermia in hospitals or in diabetic health centers which is now available, thanks to the proposed method, will help in reducing foot ulcer occurrence for diabetic persons.

Diabetes mellitus (DM) is a metabolic disorder characterized by increased blood glucose. The pathology can manifest itself with different conditions, including neuropathy, the main consequence of diabetic disease. Statistics show worrying figures worldwide, diagnosed an estimated 1.6 million people with DM by 2025. In this sense, alternative and automated methods are necessary to detect DM, allowing it to take the pertinent measures in its treatment and avoid critical complications, such as the diabetic foot. On the other hand, foot thermography is a promising tool that allows visualization of thermal patterns, patterns that are altered as a consequence of shear and friction associated with lower limb neuropathy. Based on these considerations, we explored different strategies to detect patients with DM from foot thermography in this research. Initially, the study focused on finding a classification index like Thermal Change Index (TCI). Subsequently, we used the deep convolutional neural networks paradigm, implementing 12 different data augmentation methods, of which four are conventional, and 8 are newly proposed methods. The results showed that the proposed and the conventional methods increased the network’s performance, where a 100% detection was achieved by weighting the DM probability percentages for both images of the feet. Finally, it was also possible to demonstrate the importance of transfer learning, which does not depend on the type of database, but on the data corpus with which the transfer was trained.

The changes in diameter of retinal vessels are an important sign of diseases such as hypertension, arteriosclerosis and diabetes. Obtaining precise measurements of vascular widths is a critical and demanding process in automated retinal image analysis. This paper presents the development of a prototype for measuring the vessel diameters to calculate the arteriovenous ratio (AVR) by using different techniques including Gabor wavelet, gradients, morphological operations and Niblack. The diameter measurement is based on the image skeleton and the perpendicular segment of the vessel. An executable tool is developed using MATLAB ^® and the results are evaluated.

Prevention of serious diabetic foot complication like ulceration or infection is an important issue. As the development of thermal graphic technologies, foot temperature-guided avoidance therapy has been recommended. Doctors from Hospital National Dos de Mayo are studying on the risk of the diabetic foot passing from Grade 0 to Grade 1 in the Wagner Scale. This risk to develop ulcers is related to the temperature difference of corresponding area between left and right foot. Generally speaking, the diabetic foot with greater mean temperature difference has more potential to develop ulcers; especially, area whose temperature difference of more than 2.2°C is where doctors and patients must pay much attention to potential problems like ulceration or infection. A system in Visual Studio was developed taking the thermal images as input and producing image with absolute mean temperature difference of 7different regions or four plantar angiosomes as output. The program process contained essential medical image processing issues such as segmentation, location and regionalization, in which adapted algorithms were implemented. From a database of 85 patients provided only 60 were used due to the quality of acquisition.