Diabetic Foot Ulcer Segmentation Using Convolutional and Transformer-Based Models.

Diabetes is a rising global epidemic, it was estimated that in 2017 there are 451 million (aged 18–99 years) people with diabetes worldwide, and it is expected to increase to 693 million by 2045. Diabetic Foot Ulcers (DFU) is a serious disease affecting diabetic patients and can lead to limb amputation, while more serious cases can even lead to death. In an effort to improve patient care, we are taking part in the Diabetic Foot Ulcer Segmentation Challenge 2022 (DFUC2022) competition to design automated computer methods for ulcers segmentation. This paper summarises our proposed method for the DFUC2022 conducted in conjunction with MICCAI 2022. Our experiments are based on convolutional and transformer-based models. The best performing model of our proposed method was the SegFormer model, which achieved a dice coefficient of 69.89% and a Jaccard coefficient of 59.21%. The code and the link to the pre-trained models are available at: https://github.com/Maramattia/Diabetic-Foot-Ulcer-Challenge.git .