Diagnosis of Carpal Tunnel Syndrome from Thermal Images Using Artificial Neural Networks

Thermography is an excellent method of examination, useful in the field of medicine for its safety, lack of pain and invasiveness, easy reproducibility and low running costs. As such it represents a possible alternative to more common methods for diagnosis of carpal tunnel syndrome (e.g. electromyography). However, manual analysis of thermal images can be a tedious job, requiring some patience and accuracy. Here we present a software-based intelligent system for diagnosis of carpal tunnel syndrome. Artificial neural networks, known as a well established data mining technique, were used for thermal image analysis. Reliability was tested on 44 images (23 depicting pathological hands and 21 healthy). Results acquired are presented.