# Deep Learning in Diabetic Foot Ulcers Detection: A Comprehensive Evaluation

arXiv: https://arxiv.org/abs/2010.03341 · HTML: https://mlsanity.com/paper/2010.03341/

## Key facts

- Cited by 19 papers in the map (data through 14 Oct 2026).
- First posted on arXiv 7 Oct 2020.

## Built on by (most cited first, 19 of 19)

- [Medical Image Understanding with Pretrained Vision Language Models: A Comprehensive Study](https://mlsanity.com/paper/2209.15517/) (2022)
- [Translating Clinical Delineation of Diabetic Foot Ulcers into Machine Interpretable Segmentation](https://mlsanity.com/paper/2204.11618/) (2022)
- [Analysis Towards Classification of Infection and Ischaemia of Diabetic Foot Ulcers](https://mlsanity.com/paper/2104.03068/) (2021)
- [Backbones-Review: Feature Extraction Networks for Deep Learning and Deep Reinforcement Learning Approaches](https://mlsanity.com/paper/2206.08016/) (2022)
- [Diabetic Foot Ulcer Grand Challenge 2021: Evaluation and Summary](https://mlsanity.com/paper/2111.10376/) (2021)
- [Development of Diabetic Foot Ulcer Datasets: An Overview](https://mlsanity.com/paper/2201.00163/) (2022)
- [An Enhanced Harmonic Densely Connected Hybrid Transformer Network Architecture for Chronic Wound Segmentation Utilising Multi-Colour Space Tensor Merging](https://mlsanity.com/paper/2410.03359/) (2024)
- [TransUNet-GradCAM: A Hybrid Transformer-U-Net with Self-Attention and Explainable Visualizations for Foot Ulcer Segmentation](https://mlsanity.com/paper/2508.03758/) (2025)
- [Incident Detection on Junctions Using Image Processing](https://mlsanity.com/paper/2104.13437/) (2021)
- [Boosting EfficientNets Ensemble Performance via Pseudo-Labels and Synthetic Images by pix2pixHD for Infection and Ischaemia Classification in Diabetic Foot Ulcers](https://mlsanity.com/paper/2112.00065/) (2021)
- [Quantifying the Effect of Image Similarity on Diabetic Foot Ulcer Classification](https://mlsanity.com/paper/2304.12987/) (2023)
- [Beyond Labels: Zero-Shot Diabetic Foot Ulcer Wound Segmentation with Self-attention Diffusion Models and the Potential for Text-Guided Customization](https://mlsanity.com/paper/2504.17628/) (2025)
- [Deep Subspace analysing for Semi-Supervised multi-label classification of Diabetic Foot Ulcer](https://mlsanity.com/paper/2110.01795/) (2021)
- [Diabetic foot ulcers monitoring by employing super resolution and noise reduction deep learning techniques](https://mlsanity.com/paper/2209.09880/) (2022)
- [Automated Medical Device Display Reading Using Deep Learning Object Detection](https://mlsanity.com/paper/2210.01325/) (2022)
- [Diabetic Foot Ulcer Grand Challenge 2022 Summary](https://mlsanity.com/paper/2304.12001/) (2023)
- [Venn Diagram Multi-label Class Interpretation of Diabetic Foot Ulcer with Color and Sharpness Enhancement](https://mlsanity.com/paper/2305.01044/) (2023)
- [Domain-Specific Deep Learning Feature Extractor for Diabetic Foot Ulcer Detection](https://mlsanity.com/paper/2311.16312/) (2023)
- [Gaussian Random Fields as an Abstract Representation of Patient Metadata for Multimodal Medical Image Segmentation](https://mlsanity.com/paper/2503.05214/) (2025)

## Abstract (arXiv)

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 summarises 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 enhanced the F1-Score but not the mAP.