Diabetic foot ulcers segmentation challenge report: benchmark and analysis

Yap, Moi Hoon ORCID: https://orcid.org/0000-0001-7681-4287, Cassidy, Bill ORCID: https://orcid.org/0000-0003-3741-8120, Byra, Michal, Liao, Ting-Yu, Yi, Huahui, Galdran, Adrian, Chen, Yung-Han, Brüngel, Raphael, Koitka, Sven, Friedrich, Christoph M, Lo, Yu-wen, Yang, Ching-hui, Li, Kang, Lao, Qicheng, Ballester, Miguel A González, Carneiro, Gustavo, Ju, Yi-Jen, Huang, Juinn-Dar, Pappachan, Joseph M, Reeves, Neil D ORCID: https://orcid.org/0000-0001-9213-4580, Chandrabalan, Vishnu, Dancey, Darren ORCID: https://orcid.org/0000-0001-7251-8958 and Kendrick, Connah (2024) Diabetic foot ulcers segmentation challenge report: benchmark and analysis. Medical Image Analysis, 94. 103153. ISSN 1361-8415

Preview

Published Version Available under License Creative Commons Attribution Non-commercial. Download (3MB) | Preview

Abstract

Monitoring the healing progress of diabetic foot ulcers is a challenging process. Accurate segmentation of foot ulcers can help podiatrists to quantitatively measure the size of wound regions to assist prediction of healing status. The main challenge in this field is the lack of publicly available manual delineation, which can be time consuming and laborious. Recently, methods based on deep learning have shown excellent results in automatic segmentation of medical images, however, they require large-scale datasets for training, and there is limited consensus on which methods perform the best. The 2022 Diabetic Foot Ulcers segmentation challenge was held in conjunction with the 2022 International Conference on Medical Image Computing and Computer Assisted Intervention, which sought to address these issues and stimulate progress in this research domain. A training set of 2000 images exhibiting diabetic foot ulcers was released with corresponding segmentation ground truth masks. Of the 72 (approved) requests from 47 countries, 26 teams used this data to develop fully automated systems to predict the true segmentation masks on a test set of 2000 images, with the corresponding ground truth segmentation masks kept private. Predictions from participating teams were scored and ranked according to their average Dice similarity coefficient of the ground truth masks and prediction masks. The winning team achieved a Dice of 0.7287 for diabetic foot ulcer segmentation. This challenge has now entered a live leaderboard stage where it serves as a challenging benchmark for diabetic foot ulcer segmentation.