Deep learning in diabetic foot ulcers detection : A comprehensive evaluation

Yap, Moi Hoon and Hachiuma, R and Alavi, A and Brüngel, R and Cassidy, Bill and Goyal, M and Zhu, H and Rückert, J and Olshansky, M and Huang, X and Saito, H and Hassanpour, S and Friedrich, C M and Ascher, D B and Song, A and Kajita, H and Gillespie, David and Reeves, Neil and Pappachan, J M and O'Shea, C and Frank, E (2021) Deep learning in diabetic foot ulcers detection : A comprehensive evaluation. Computers in biology and medicine, 135: 104596. ISSN 0010-4825

Abstract

There has been a substantial amount of research involving computer methods and technology for the detection and recognition of diabetic foot ulcers (DFUs), but there is a lack of systematic comparisons of state-of-the-art deep learning object detection frameworks applied to this problem. DFUC2020 provided participants with a comprehensive dataset consisting of 2,000 images for training and 2,000 images for testing. This paper summarizes the results of DFUC2020 by comparing the deep learning-based algorithms proposed by the winning teams: Faster R–CNN, three variants of Faster R–CNN and an ensemble method; YOLOv3; YOLOv5; EfficientDet; and a new Cascade Attention Network. For each deep learning method, we provide a detailed description of model architecture, parameter settings for training and additional stages including pre-processing, data augmentation and post-processing. We provide a comprehensive evaluation for each method. All the methods required a data augmentation stage to increase the number of images available for training and a post-processing stage to remove false positives. The best performance was obtained from Deformable Convolution, a variant of Faster R–CNN, with a mean average precision (mAP) of 0.6940 and an F1-Score of 0.7434. Finally, we demonstrate that the ensemble method based on different deep learning methods can enhance the F1-Score but not the mAP.