Papers › HarDNet-DFUS: An Enhanced Harmonically-Connected Network for Diabetic Foot Ulcer Image...

HarDNet-DFUS: An Enhanced Harmonically-Connected Network for Diabetic Foot Ulcer Image Segmentation and Colonoscopy Polyp Segmentation

15 Sep 2022arXiv:2209.07313archive 2025-07-28

Ting-Yu Liao, Ching-Hui Yang, Yu-Wen Lo, Kuan-Ying Lai, Po-Huai Shen, Youn-Long Lin

We present a neural network architecture for medical image segmentation of diabetic foot ulcers and colonoscopy polyps. Diabetic foot ulcers are caused by neuropathic and vascular complications of diabetes mellitus. In order to provide a proper diagnosis and treatment, wound care professionals need to extract accurate morphological features from the foot wounds. Using computer-aided systems is a promising approach to extract related morphological features and segment the lesions. We propose a convolution neural network called HarDNet-DFUS by enhancing the backbone and replacing the decoder of HarDNet-MSEG, which was SOTA for colonoscopy polyp segmentation in 2021. For the MICCAI 2022 Diabetic Foot Ulcer Segmentation Challenge (DFUC2022), we train HarDNet-DFUS using the DFUC2022 dataset and increase its robustness by means of five-fold cross validation, Test Time Augmentation, etc. In the validation phase of DFUC2022, HarDNet-DFUS achieved 0.7063 mean dice and was ranked third among all participants. In the final testing phase of DFUC2022, it achieved 0.7287 mean dice and was the first place winner. HarDNet-DFUS also deliver excellent performance for the colonoscopy polyp segmentation task. It achieves 0.924 mean Dice on the famous Kvasir dataset, an improvement of 1.2\% over the original HarDNet-MSEG. The codes are available on https://github.com/kytimmylai/DFUC2022 (for Diabetic Foot Ulcers Segmentation) and https://github.com/YuWenLo/HarDNet-DFUS (for Colonoscopy Polyp Segmentation).

PaperPDFCode

Code

yuwenlo/hardnet-dfus officialmentioned in papermentioned on GitHubpytorch report
kytimmylai/dfuc2022 officialmentioned in paperpytorch report

Repository list and official/mentioned flags are the archive's, frozen 2025-07-28. Reachability, where shown, is from one Syntology probe window (2026-09-16 to 2026-09-18); repositories not probed show nothing. GitHub stars are not tracked.

Code Syntology ran Syntology

Not run by Syntology. Nothing on this page verifies that the listed code works.

Tasks

DecoderImage SegmentationMedical Image SegmentationSegmentationSemantic Segmentation

Results from the paper archive 2025-07-28

TaskDatasetModelMetricValueRank at snapshotLeaderboardReport
Medical Image Segmentation CVC-ClinicDB HarDNet-DFUS mean Dice 0.939 #21 of 48 Archive leaderboard report
Medical Image Segmentation CVC-ColonDB HarDNet-DFUS mean Dice 0.774 #17 of 25 Archive leaderboard report
Medical Image Segmentation ETIS-LARIBPOLYPDB HarDNet-DFUS mean Dice 0.730 #19 of 25 Archive leaderboard report
Medical Image Segmentation Kvasir-SEG HarDNet-DFUS mIoU 0.8894 #11 of 58 Archive leaderboard report
Medical Image Segmentation Kvasir-SEG HarDNet-DFUS mean Dice 0.9363 #11 of 58 Archive leaderboard report

Ranks are positions in the archive's leaderboards as they stood at the 2025-07-28 snapshot. Results published since then are not among these rows, so a rank here is not a current standing.

Methods

ConvolutionTest

Report a problem or propose a change · a person checks every report against the paper or source before anything changes; decisions are listed on /corrections