ZScribbleSeg: A comprehensive segmentation framework with modeling of efficient annotation and maximization of scribble supervision

Fuente: arXiv
Saved in:
Bibliographic Details
Main Authors: Zhang, Ke, Wang, Bomin, Zhou, Hangqi, Zhuang, Xiahai
Format: Preprint
Published: 2026
Subjects:
Online Access:
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1866915989470314496
author Zhang, Ke
Wang, Bomin
Zhou, Hangqi
Zhuang, Xiahai
author_facet Zhang, Ke
Wang, Bomin
Zhou, Hangqi
Zhuang, Xiahai
contents Curating fully annotated datasets for medical image segmentation is labour-intensive and expertise-demanding. To alleviate this problem, prior studies have explored scribble annotations for weakly supervised segmentation. Existing solutions mainly compute losses on annotated areas and generate pseudo labels by propagating annotations to adjacent regions. However, these methods often suffer from inaccurate and unrealistic segmentations due to insufficient supervision and incomplete shape information. In contrast, we first investigate the principle of good scribble annotations, which leads to efficient scribble forms via supervision maximization and randomness simulation. We further introduce regularization terms to encode the spatial relationship and the shape constraints, where the EM algorithm is utilized to estimate the mixture ratios of label classes. These ratios are critical in identifying the unlabeled pixels for each class and correcting erroneous predictions, thus the accurate estimation lays the foundation for the incorporation of spatial prior. Finally, we integrate the efficient scribble supervision with the prior into a framework, referred to as ZScribbleSeg, and apply it to multiple scenarios. Leveraging only scribble annotations, ZScribbleSeg achieves competitive performance on six segmentation tasks including ACDC, MSCMRseg, BTCV, MyoPS, Decathlon-BrainTumor and Decathlon-Prostate. Our code will be released via https://github.com/DLwbm123/ZScribbleSeg.
format Preprint
id arxiv_https___arxiv_org_abs_2605_06266
institution arXiv
publishDate 2026
record_format arxiv
spellingShingle ZScribbleSeg: A comprehensive segmentation framework with modeling of efficient annotation and maximization of scribble supervision
Zhang, Ke
Wang, Bomin
Zhou, Hangqi
Zhuang, Xiahai
Computer Vision and Pattern Recognition
Curating fully annotated datasets for medical image segmentation is labour-intensive and expertise-demanding. To alleviate this problem, prior studies have explored scribble annotations for weakly supervised segmentation. Existing solutions mainly compute losses on annotated areas and generate pseudo labels by propagating annotations to adjacent regions. However, these methods often suffer from inaccurate and unrealistic segmentations due to insufficient supervision and incomplete shape information. In contrast, we first investigate the principle of good scribble annotations, which leads to efficient scribble forms via supervision maximization and randomness simulation. We further introduce regularization terms to encode the spatial relationship and the shape constraints, where the EM algorithm is utilized to estimate the mixture ratios of label classes. These ratios are critical in identifying the unlabeled pixels for each class and correcting erroneous predictions, thus the accurate estimation lays the foundation for the incorporation of spatial prior. Finally, we integrate the efficient scribble supervision with the prior into a framework, referred to as ZScribbleSeg, and apply it to multiple scenarios. Leveraging only scribble annotations, ZScribbleSeg achieves competitive performance on six segmentation tasks including ACDC, MSCMRseg, BTCV, MyoPS, Decathlon-BrainTumor and Decathlon-Prostate. Our code will be released via https://github.com/DLwbm123/ZScribbleSeg.
title ZScribbleSeg: A comprehensive segmentation framework with modeling of efficient annotation and maximization of scribble supervision
topic Computer Vision and Pattern Recognition
url https://arxiv.org/abs/2605.06266