Papers › S2S2: Semantic Stacking for Robust Semantic Segmentation in Medical Imaging

S2S2: Semantic Stacking for Robust Semantic Segmentation in Medical Imaging

17 Dec 2024arXiv:2412.13156archive 2025-07-28

Yimu Pan, Sitao Zhang, Alison D. Gernand, Jeffery A. Goldstein, James Z. Wang

Robustness and generalizability in medical image segmentation are often hindered by scarcity and limited diversity of training data, which stands in contrast to the variability encountered during inference. While conventional strategies -- such as domain-specific augmentation, specialized architectures, and tailored training procedures -- can alleviate these issues, they depend on the availability and reliability of domain knowledge. When such knowledge is unavailable, misleading, or improperly applied, performance may deteriorate. In response, we introduce a novel, domain-agnostic, add-on, and data-driven strategy inspired by image stacking in image denoising. Termed ``semantic stacking,'' our method estimates a denoised semantic representation that complements the conventional segmentation loss during training. This method does not depend on domain-specific assumptions, making it broadly applicable across diverse image modalities, model architectures, and augmentation techniques. Through extensive experiments, we validate the superiority of our approach in improving segmentation performance under diverse conditions. Code is available at https://github.com/ymp5078/Semantic-Stacking.

PaperPDFCode

Code

ymp5078/semantic-stacking 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

DiversityImage SegmentationMedical Image SegmentationSegmentationSemantic Segmentation

Results from the paper archive 2025-07-28

TaskDatasetModelMetricValueRank at snapshotLeaderboardReport
Medical Image Segmentation Automatic Cardiac Diagnosis Challenge (ACDC) TransUNet Avg DSC 90.4 #15 of 20 Archive leaderboard report
Medical Image Segmentation CVC-ClinicDB FCBFormer mean Dice 0.9488 #8 of 48 Archive leaderboard report
Medical Image Segmentation Kvasir-SEG FCBFormer mean Dice 0.932 #13 of 58 Archive leaderboard report
Medical Image Segmentation Synapse multi-organ CT TransUNet Avg DSC 81.19 #16 of 23 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.

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