Infrared Thermography Based on Artificial Intelligence for Carpal Tunnel Syndrome Diagnosis

Abstract

Thermography for the measurement of surface temperatures is well known in industry, although is not established in medicine despite its safety, lack of pain and invasiveness, easy reproducibility, and low running costs. Promising results have been achieved in nerve entrapment syndromes, although thermography has never represented a real alternative to electromyography. Here an attempt is described to improve the diagnosis of carpal tunnel syndrome with thermography using a computer-based system employing artificial neural networks to analyse the images. Method reliability was tested on 112 images (depicting the dorsal and palmar sides of 26 healthy and 30 pathological hands), with the hand divided into 12 segments and compared relative to a reference. Palmar segments appeared to have no beneficial influence on classification outcome, whereas dorsal segments gave improved outcome with classification success rates near to or over 80%, and finger segments influenced by the median nerve appeared to be of greatest importance. These are preliminary results from a limited number of images and further research will be undertaken as our image database grows.

Infrared Thermography Based on Artificial Intelligence as a Screening Method for Carpal Tunnel Syndrome Diagnosis

“…As our preliminary results 8 showed no beneficial influence of palmar segments on the outcome of classification, this study focused on dorsal segments. The mean classification success rate of five classification runs, when only dorsal segments were included and no distinction was made between patients with different NCS severities, was 72.2% (Table 1).…”

“…As reported previously, 8 all images were taken with a Neo Thermo TVS-700 camera (NEC Avio Infrared Technologies, Tokyo, Japan) with a resolution of 320 × 240 pixels from a standard distance of 80 cm under similar ambient conditions (room temperature 23 ± 2°C; relative humidity 56 ± 8%). The thermography guidelines issued by the International Academy of Clinical Thermography were taken into consideration.…”

“…ANN topology and training process parameters were chosen according to the results of our previous work. 8,14 Each classification was repeated five times, each time using a randomly selected training set of 80% of all hands (200 or 148 hands when mild and moderate CTS cases were omitted), and the percentage of successful classifications was calculated from the mean of the five attempts.…”

“…This led us to look for a better, more accurate method which resulted in our software module being developed, which consists of two modules: the first module performs image segmentation and extracts temperature readings, while the second module performs image analysis and attempts to diagnose CTS. 8 Diagnosis relies on previously acquired knowledge from other images stored in an artificial neural network (ANN). The results appeared to be very reliable: classification success rates were usually > 80% when focusing on the dorsal side of the hand, 8 which suggests that this artificial intelligence-based IRT technology could be used to diagnose CTS.…”

“…8 Diagnosis relies on previously acquired knowledge from other images stored in an artificial neural network (ANN). The results appeared to be very reliable: classification success rates were usually > 80% when focusing on the dorsal side of the hand, 8 which suggests that this artificial intelligence-based IRT technology could be used to diagnose CTS. However, only 112 images were available (with 56 dorsal views), 8 which was not very many bearing in mind the important role that the learning process plays in ANN development.…”