DiffAtlas: GenAI-fying Atlas Segmentation via Image-Mask Diffusion

Fuente: arXiv
Saved in:
Bibliographic Details
Main Authors: Zhang, Hantao, Liu, Yuhe, Yang, Jiancheng, Guo, Weidong, Wang, Xinyuan, Fua, Pascal
Format: Preprint
Published: 2025
Subjects:
Online Access:
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1866913727381504000
author Zhang, Hantao
Liu, Yuhe
Yang, Jiancheng
Guo, Weidong
Wang, Xinyuan
Fua, Pascal
author_facet Zhang, Hantao
Liu, Yuhe
Yang, Jiancheng
Guo, Weidong
Wang, Xinyuan
Fua, Pascal
contents Accurate medical image segmentation is crucial for precise anatomical delineation. Deep learning models like U-Net have shown great success but depend heavily on large datasets and struggle with domain shifts, complex structures, and limited training samples. Recent studies have explored diffusion models for segmentation by iteratively refining masks. However, these methods still retain the conventional image-to-mask mapping, making them highly sensitive to input data, which hampers stability and generalization. In contrast, we introduce DiffAtlas, a novel generative framework that models both images and masks through diffusion during training, effectively ``GenAI-fying'' atlas-based segmentation. During testing, the model is guided to generate a specific target image-mask pair, from which the corresponding mask is obtained. DiffAtlas retains the robustness of the atlas paradigm while overcoming its scalability and domain-specific limitations. Extensive experiments on CT and MRI across same-domain, cross-modality, varying-domain, and different data-scale settings using the MMWHS and TotalSegmentator datasets demonstrate that our approach outperforms existing methods, particularly in limited-data and zero-shot modality segmentation. Code is available at https://github.com/M3DV/DiffAtlas.
format Preprint
id arxiv_https___arxiv_org_abs_2503_06748
institution arXiv
publishDate 2025
record_format arxiv
spellingShingle DiffAtlas: GenAI-fying Atlas Segmentation via Image-Mask Diffusion
Zhang, Hantao
Liu, Yuhe
Yang, Jiancheng
Guo, Weidong
Wang, Xinyuan
Fua, Pascal
Computer Vision and Pattern Recognition
Accurate medical image segmentation is crucial for precise anatomical delineation. Deep learning models like U-Net have shown great success but depend heavily on large datasets and struggle with domain shifts, complex structures, and limited training samples. Recent studies have explored diffusion models for segmentation by iteratively refining masks. However, these methods still retain the conventional image-to-mask mapping, making them highly sensitive to input data, which hampers stability and generalization. In contrast, we introduce DiffAtlas, a novel generative framework that models both images and masks through diffusion during training, effectively ``GenAI-fying'' atlas-based segmentation. During testing, the model is guided to generate a specific target image-mask pair, from which the corresponding mask is obtained. DiffAtlas retains the robustness of the atlas paradigm while overcoming its scalability and domain-specific limitations. Extensive experiments on CT and MRI across same-domain, cross-modality, varying-domain, and different data-scale settings using the MMWHS and TotalSegmentator datasets demonstrate that our approach outperforms existing methods, particularly in limited-data and zero-shot modality segmentation. Code is available at https://github.com/M3DV/DiffAtlas.
title DiffAtlas: GenAI-fying Atlas Segmentation via Image-Mask Diffusion
topic Computer Vision and Pattern Recognition
url https://arxiv.org/abs/2503.06748