Papers › DCSAU-Net: A Deeper and More Compact Split-Attention U-Net for Medical Image Segmentation

DCSAU-Net: A Deeper and More Compact Split-Attention U-Net for Medical Image Segmentation

2 Feb 2022arXiv:2202.00972archive 2025-07-28

Qing Xu, Zhicheng Ma, Na He, Wenting Duan

Deep learning architecture with convolutional neural network (CNN) achieves outstanding success in the field of computer vision. Where U-Net, an encoder-decoder architecture structured by CNN, makes a great breakthrough in biomedical image segmentation and has been applied in a wide range of practical scenarios. However, the equal design of every downsampling layer in the encoder part and simply stacked convolutions do not allow U-Net to extract sufficient information of features from different depths. The increasing complexity of medical images brings new challenges to the existing methods. In this paper, we propose a deeper and more compact split-attention u-shape network (DCSAU-Net), which efficiently utilises low-level and high-level semantic information based on two novel frameworks: primary feature conservation and compact split-attention block. We evaluate the proposed model on CVC-ClinicDB, 2018 Data Science Bowl, ISIC-2018 and SegPC-2021 datasets. As a result, DCSAU-Net displays better performance than other state-of-the-art (SOTA) methods in terms of the mean Intersection over Union (mIoU) and F1-socre. More significantly, the proposed model demonstrates excellent segmentation performance on challenging images. The code for our work and more technical details can be found at https://github.com/xq141839/DCSAU-Net.

PaperPDFCode

In Syntology Open this paper in Syntology's Atlas, the map of the papers in Syntology's graph and their citations.

Code

xq141839/DCSAU-Net 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

DecoderImage SegmentationLesion SegmentationMedical Image SegmentationSemantic Segmentation

Results from the paper archive 2025-07-28

TaskDatasetModelMetricValueRank at snapshotLeaderboardReport
Lesion Segmentation ISIC 2018 Task 1 DCSAU-Net mIoU 0.8301 #1 of 1 Archive leaderboard report
Medical Image Segmentation 2018 Data Science Bowl DCSAU-Net Recall 0.9240 #10 of 10 Archive leaderboard report
Medical Image Segmentation 2018 Data Science Bowl DCSAU-Net mIoU 0.8501 #10 of 10 Archive leaderboard report
Medical Image Segmentation ISIC 2018 DCSAU-Net DSC 90.35 #2 of 2 Archive leaderboard report
Medical Image Segmentation ISIC2018 U2netme Accuracy 0.94216 #2 of 3 Archive leaderboard report
Medical Image Segmentation ISIC2018 U2netme Precision 0.89502 #2 of 3 Archive leaderboard report
Medical Image Segmentation ISIC2018 U2netme Test F1-Score 0.90604 #2 of 3 Archive leaderboard report
Medical Image Segmentation ISIC2018 U2netme mean Dice 0.905 #2 of 3 Archive leaderboard report
Medical Image Segmentation SegPC-2021 DCSAU-Net mIoU 0.8048 #1 of 1 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

Concatenated Skip ConnectionConvolutionMax PoolingReLUU-Net

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