Papers › DermoSegDiff: A Boundary-aware Segmentation Diffusion Model for Skin Lesion Delineation

DermoSegDiff: A Boundary-aware Segmentation Diffusion Model for Skin Lesion Delineation

5 Aug 2023arXiv:2308.02959archive 2025-07-28

Afshin Bozorgpour, Yousef Sadegheih, Amirhossein Kazerouni, Reza Azad, Dorit Merhof

Skin lesion segmentation plays a critical role in the early detection and accurate diagnosis of dermatological conditions. Denoising Diffusion Probabilistic Models (DDPMs) have recently gained attention for their exceptional image-generation capabilities. Building on these advancements, we propose DermoSegDiff, a novel framework for skin lesion segmentation that incorporates boundary information during the learning process. Our approach introduces a novel loss function that prioritizes the boundaries during training, gradually reducing the significance of other regions. We also introduce a novel U-Net-based denoising network that proficiently integrates noise and semantic information inside the network. Experimental results on multiple skin segmentation datasets demonstrate the superiority of DermoSegDiff over existing CNN, transformer, and diffusion-based approaches, showcasing its effectiveness and generalization in various scenarios. The implementation is publicly accessible on \href{https://github.com/mindflow-institue/dermosegdiff}{GitHub}

PaperPDFCode

Code

mindflow-institue/dermosegdiff officialmentioned in papermentioned on GitHubpytorch 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

DenoisingImage GenerationLesion SegmentationSegmentationSkin Lesion Segmentation

Results from the paper archive 2025-07-28

TaskDatasetModelMetricValueRank at snapshotLeaderboardReport
Lesion Segmentation HAM10000 DermoSegDiff-B Dice Score 0.943 #1 of 1 Archive leaderboard report
Lesion Segmentation ISIC 2018 DermoSegDiff-A mean Dice 0.9005 #8 of 17 Archive leaderboard report
Lesion Segmentation PH2 DermoSegDiff-B Dice Score 0.9467 #3 of 3 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

Diffusion

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