Saved in:
Bibliographic Details
Main Authors: Zhang, Han, Luo, Xiangde, Chen, Yong, Li, Kang
Format: Preprint
Published: 2025
Subjects:
Online Access:https://arxiv.org/abs/2507.13087
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1866918137156337664
author Zhang, Han
Luo, Xiangde
Chen, Yong
Li, Kang
author_facet Zhang, Han
Luo, Xiangde
Chen, Yong
Li, Kang
contents Annotation variability remains a substantial challenge in medical image segmentation, stemming from ambiguous imaging boundaries and diverse clinical expertise. Traditional deep learning methods producing single deterministic segmentation predictions often fail to capture these annotator biases. Although recent studies have explored multi-rater segmentation, existing methods typically focus on a single perspective -- either generating a probabilistic ``gold standard'' consensus or preserving expert-specific preferences -- thus struggling to provide a more omni view. In this study, we propose DiffOSeg, a two-stage diffusion-based framework, which aims to simultaneously achieve both consensus-driven (combining all experts' opinions) and preference-driven (reflecting experts' individual assessments) segmentation. Stage I establishes population consensus through a probabilistic consensus strategy, while Stage II captures expert-specific preference via adaptive prompts. Demonstrated on two public datasets (LIDC-IDRI and NPC-170), our model outperforms existing state-of-the-art methods across all evaluated metrics. Source code is available at https://github.com/string-ellipses/DiffOSeg .
format Preprint
id arxiv_https___arxiv_org_abs_2507_13087
institution arXiv
publishDate 2025
record_format arxiv
spellingShingle DiffOSeg: Omni Medical Image Segmentation via Multi-Expert Collaboration Diffusion Model
Zhang, Han
Luo, Xiangde
Chen, Yong
Li, Kang
Computer Vision and Pattern Recognition
Annotation variability remains a substantial challenge in medical image segmentation, stemming from ambiguous imaging boundaries and diverse clinical expertise. Traditional deep learning methods producing single deterministic segmentation predictions often fail to capture these annotator biases. Although recent studies have explored multi-rater segmentation, existing methods typically focus on a single perspective -- either generating a probabilistic ``gold standard'' consensus or preserving expert-specific preferences -- thus struggling to provide a more omni view. In this study, we propose DiffOSeg, a two-stage diffusion-based framework, which aims to simultaneously achieve both consensus-driven (combining all experts' opinions) and preference-driven (reflecting experts' individual assessments) segmentation. Stage I establishes population consensus through a probabilistic consensus strategy, while Stage II captures expert-specific preference via adaptive prompts. Demonstrated on two public datasets (LIDC-IDRI and NPC-170), our model outperforms existing state-of-the-art methods across all evaluated metrics. Source code is available at https://github.com/string-ellipses/DiffOSeg .
title DiffOSeg: Omni Medical Image Segmentation via Multi-Expert Collaboration Diffusion Model
topic Computer Vision and Pattern Recognition
url https://arxiv.org/abs/2507.13087