Scale-aware Adaptive Supervised Network with Limited Medical Annotations

Fuente: arXiv
Saved in:
Bibliographic Details
Main Authors: Li, Zihan, Shan, Dandan, Li, Yunxiang, Kinahan, Paul E., Hong, Qingqi
Format: Preprint
Published: 2026
Subjects:
Online Access:
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1866909980253224960
author Li, Zihan
Shan, Dandan
Li, Yunxiang
Kinahan, Paul E.
Hong, Qingqi
author_facet Li, Zihan
Shan, Dandan
Li, Yunxiang
Kinahan, Paul E.
Hong, Qingqi
contents Medical image segmentation faces critical challenges in semi-supervised learning scenarios due to severe annotation scarcity requiring expert radiological knowledge, significant inter-annotator variability across different viewpoints and expertise levels, and inadequate multi-scale feature integration for precise boundary delineation in complex anatomical structures. Existing semi-supervised methods demonstrate substantial performance degradation compared to fully supervised approaches, particularly in small target segmentation and boundary refinement tasks. To address these fundamental challenges, we propose SASNet (Scale-aware Adaptive Supervised Network), a dual-branch architecture that leverages both low-level and high-level feature representations through novel scale-aware adaptive reweight mechanisms. Our approach introduces three key methodological innovations, including the Scale-aware Adaptive Reweight strategy that dynamically weights pixel-wise predictions using temporal confidence accumulation, the View Variance Enhancement mechanism employing 3D Fourier domain transformations to simulate annotation variability, and segmentation-regression consistency learning through signed distance map algorithms for enhanced boundary precision. These innovations collectively address the core limitations of existing semi-supervised approaches by integrating spatial, temporal, and geometric consistency principles within a unified optimization framework. Comprehensive evaluation across LA, Pancreas-CT, and BraTS datasets demonstrates that SASNet achieves superior performance with limited labeled data, surpassing state-of-the-art semi-supervised methods while approaching fully supervised performance levels. The source code for SASNet is available at https://github.com/HUANGLIZI/SASNet.
format Preprint
id arxiv_https___arxiv_org_abs_2601_01005
institution arXiv
publishDate 2026
record_format arxiv
spellingShingle Scale-aware Adaptive Supervised Network with Limited Medical Annotations
Li, Zihan
Shan, Dandan
Li, Yunxiang
Kinahan, Paul E.
Hong, Qingqi
Image and Video Processing
Artificial Intelligence
Computer Vision and Pattern Recognition
Medical image segmentation faces critical challenges in semi-supervised learning scenarios due to severe annotation scarcity requiring expert radiological knowledge, significant inter-annotator variability across different viewpoints and expertise levels, and inadequate multi-scale feature integration for precise boundary delineation in complex anatomical structures. Existing semi-supervised methods demonstrate substantial performance degradation compared to fully supervised approaches, particularly in small target segmentation and boundary refinement tasks. To address these fundamental challenges, we propose SASNet (Scale-aware Adaptive Supervised Network), a dual-branch architecture that leverages both low-level and high-level feature representations through novel scale-aware adaptive reweight mechanisms. Our approach introduces three key methodological innovations, including the Scale-aware Adaptive Reweight strategy that dynamically weights pixel-wise predictions using temporal confidence accumulation, the View Variance Enhancement mechanism employing 3D Fourier domain transformations to simulate annotation variability, and segmentation-regression consistency learning through signed distance map algorithms for enhanced boundary precision. These innovations collectively address the core limitations of existing semi-supervised approaches by integrating spatial, temporal, and geometric consistency principles within a unified optimization framework. Comprehensive evaluation across LA, Pancreas-CT, and BraTS datasets demonstrates that SASNet achieves superior performance with limited labeled data, surpassing state-of-the-art semi-supervised methods while approaching fully supervised performance levels. The source code for SASNet is available at https://github.com/HUANGLIZI/SASNet.
title Scale-aware Adaptive Supervised Network with Limited Medical Annotations
topic Image and Video Processing
Artificial Intelligence
Computer Vision and Pattern Recognition
url https://arxiv.org/abs/2601.01005