Papers › Rethinking the Nested U-Net Approach: Enhancing Biomarker Segmentation with Attention...

Rethinking the Nested U-Net Approach: Enhancing Biomarker Segmentation with Attention Mechanisms and Multiscale Feature Fusion

8 Apr 2025arXiv:2504.06158archive 2025-07-28

Saad Wazir, Daeyoung Kim

Identifying biomarkers in medical images is vital for a wide range of biotech applications. However, recent Transformer and CNN based methods often struggle with variations in morphology and staining, which limits their feature extraction capabilities. In medical image segmentation, where data samples are often limited, state-of-the-art (SOTA) methods improve accuracy by using pre-trained encoders, while end-to-end approaches typically fall short due to difficulties in transferring multiscale features effectively between encoders and decoders. To handle these challenges, we introduce a nested UNet architecture that captures both local and global context through Multiscale Feature Fusion and Attention Mechanisms. This design improves feature integration from encoders, highlights key channels and regions, and restores spatial details to enhance segmentation performance. Our method surpasses SOTA approaches, as evidenced by experiments across four datasets and detailed ablation studies. Code: https://github.com/saadwazir/ReN-UNet

PaperPDFCode

Code

saadwazir/ReN-UNet officialmentioned in papermentioned on GitHubtf 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

2D Semantic SegmentationImage SegmentationMedical Image SegmentationSemantic Segmentation

Results from the paper archive 2025-07-28

TaskDatasetModelMetricValueRank at snapshotLeaderboardReport
Medical Image Segmentation 2018 Data Science Bowl ReN-UNet AHD95 6.5914 #1 of 10 Archive leaderboard report
Medical Image Segmentation 2018 Data Science Bowl ReN-UNet ASD 1.7074 #1 of 10 Archive leaderboard report
Medical Image Segmentation 2018 Data Science Bowl ReN-UNet Dice 92.79 #1 of 10 Archive leaderboard report
Medical Image Segmentation 2018 Data Science Bowl ReN-UNet mIoU 87.22 #1 of 10 Archive leaderboard report
Medical Image Segmentation Electron Microscopy Dataset ReN-UNet AHD95 5.3703 #1 of 1 Archive leaderboard report
Medical Image Segmentation Electron Microscopy Dataset ReN-UNet ASD 0.3047 #1 of 1 Archive leaderboard report
Medical Image Segmentation Electron Microscopy Dataset ReN-UNet Dice 93.55 #1 of 1 Archive leaderboard report
Medical Image Segmentation Electron Microscopy Dataset ReN-UNet IoU 87.93 #1 of 1 Archive leaderboard report
Medical Image Segmentation MoNuSeg ReN-UNet AHD95 2.2422 #2 of 15 Archive leaderboard report
Medical Image Segmentation MoNuSeg ReN-UNet ASD 0.1583 #2 of 15 Archive leaderboard report
Medical Image Segmentation MoNuSeg ReN-UNet F1 84.12 #2 of 15 Archive leaderboard report
Medical Image Segmentation MoNuSeg ReN-UNet IoU 73.06 #2 of 15 Archive leaderboard report
Medical Image Segmentation TNBC ReN-UNet AHD95 10.355 #1 of 1 Archive leaderboard report
Medical Image Segmentation TNBC ReN-UNet Dice 78.99 #1 of 1 Archive leaderboard report
Medical Image Segmentation TNBC ReN-UNet IoU 66.13 #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

Absolute Position EncodingsAdamAttentionBPEDense ConnectionsDropoutLabel SmoothingLayer NormalizationLinear LayerMulti-Head AttentionPosition-Wise Feed-Forward LayerResidual ConnectionSoftmaxTransformer

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