Department of Electrical Engineering, Qatar University, Doha 2713, Qatar
Muhammad E. H. Chowdhury
Department of Electrical Engineering, Qatar University, Doha 2713, Qatar
Mamun Bin Ibne Reaz
Department of Electrical, Electronic and Systems Engineering, Faculty of Engineering and Built Environment, Universiti Kebangsaan Malaysia, Bangi 43600 UKM, Selangor, Malaysia
Sawal Hamid Md Ali
Department of Electrical, Electronic and Systems Engineering, Faculty of Engineering and Built Environment, Universiti Kebangsaan Malaysia, Bangi 43600 UKM, Selangor, Malaysia
Tariq O. Abbas
Urology Division, Surgery Department, Sidra Medicine, Doha 26999, Qatar
Tanvir Alam
College of Science and Engineering, Hamad Bin Khalifa University, Doha 34110, Qatar
Mohamed Arselene Ayari
College of Engineering, Qatar University, Doha 2713, Qatar
Zaid B. Mahbub
Department of Mathematics and Physics, North South University, Dhaka 1000, Bangladesh
Rumana Habib
Neurology Department, BIRDEM General Hospital, Dhaka 1000, Bangladesh
Tawsifur Rahman
Department of Electrical Engineering, Qatar University, Doha 2713, Qatar
Anas M. Tahir
Department of Electrical Engineering, Qatar University, Doha 2713, Qatar
Ahmad Ashrif A. Bakar
Department of Electrical, Electronic and Systems Engineering, Faculty of Engineering and Built Environment, Universiti Kebangsaan Malaysia, Bangi 43600 UKM, Selangor, Malaysia
Diabetes mellitus (DM) can lead to plantar ulcers, amputation and death. Plantar foot thermogram images acquired using an infrared camera have been shown to detect changes in temperature distribution associated with a higher risk of foot ulceration. Machine learning approaches applied to such infrared images may have utility in the early diagnosis of diabetic foot complications. In this work, a publicly available dataset was categorized into different classes, which were corroborated by domain experts, based on a temperature distribution parameter—the thermal change index (TCI). We then explored different machine-learning approaches for classifying thermograms of the TCI-labeled dataset. Classical machine learning algorithms with feature engineering and the convolutional neural network (CNN) with image enhancement techniques were extensively investigated to identify the best performing network for classifying thermograms. The multilayer perceptron (MLP) classifier along with the features extracted from thermogram images showed an accuracy of 90.1% in multi-class classification, which outperformed the literature-reported performance metrics on this dataset.
