Exploiting Unlabeled Structures through Task Consistency Training for Versatile Medical Image Segmentation Article Swipe

MAKE IMPACT

Shengqian Zhu , Jiafei Wu , Xiaogang Xu , Chengrong Yu , Ying Song , Yi Zhang , Guangjun Li , Junjie Hu · YOU? · · 2025 · Open Access · · DOI: https://doi.org/10.48550/arxiv.2509.04732

Versatile medical image segmentation (VMIS) targets the segmentation of multiple classes, while obtaining full annotations for all classes is often impractical due to the time and labor required. Leveraging partially labeled datasets (PLDs) presents a promising alternative; however, current VMIS approaches face significant class imbalance due to the unequal category distribution in PLDs. Existing methods attempt to address this by generating pseudo-full labels. Nevertheless, these typically require additional models and often result in potential performance degradation from label noise. In this work, we introduce a Task Consistency Training (TCT) framework to address class imbalance without requiring extra models. TCT includes a backbone network with a main segmentation head (MSH) for multi-channel predictions and multiple auxiliary task heads (ATHs) for task-specific predictions. By enforcing a consistency constraint between the MSH and ATH predictions, TCT effectively utilizes unlabeled anatomical structures. To avoid error propagation from low-consistency, potentially noisy data, we propose a filtering strategy to exclude such data. Additionally, we introduce a unified auxiliary uncertainty-weighted loss (UAUWL) to mitigate segmentation quality declines caused by the dominance of specific tasks. Extensive experiments on eight abdominal datasets from diverse clinical sites demonstrate our approach's effectiveness.

Type

preprint

Language

en

Landing Page

http://arxiv.org/abs/2509.04732

PDF

https://arxiv.org/pdf/2509.04732

OA Status

green

OpenAlex ID

https://openalex.org/W4414759608

Raw OpenAlex JSON

OpenAlex ID

https://openalex.org/W4414759608

Canonical identifier for this work in OpenAlex

DOI

https://doi.org/10.48550/arxiv.2509.04732

Digital Object Identifier

Title

Exploiting Unlabeled Structures through Task Consistency Training for Versatile Medical Image Segmentation

Work title

Type

preprint

OpenAlex work type

Language

en

Primary language

Publication year

2025

Year of publication

Publication date

2025-09-05

Full publication date if available

Authors

Shengqian Zhu, Jiafei Wu, Xiaogang Xu, Chengrong Yu, Ying Song, Yi Zhang, Guangjun Li, Junjie Hu

List of authors in order

Landing page

https://arxiv.org/abs/2509.04732

Publisher landing page

PDF URL

https://arxiv.org/pdf/2509.04732

Direct link to full text PDF

Open access

Yes

Whether a free full text is available

OA status

green

Open access status per OpenAlex

OA URL

https://arxiv.org/pdf/2509.04732

Direct OA link when available

Cited by

0

Total citation count in OpenAlex

Full payload