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

arXiv: https://arxiv.org/abs/2503.06748 · HTML: https://mlsanity.com/paper/2503.06748/

## Key facts

- Cited by 5 papers in the map (data through 14 Oct 2026).
- Builds on 15 of its 29 references that are in the map.
- First posted on arXiv 9 Mar 2025.

## Builds on (most cited first, 15 of 15)

- [U-Net: Convolutional Networks for Biomedical Image Segmentation](https://mlsanity.com/paper/1505.04597/) (2015)
- [Domain Adaptation for Medical Image Analysis: A Survey](https://mlsanity.com/paper/2102.09508/) (2021)
- [Diffusion Models for Medical Image Analysis: A Comprehensive Survey](https://mlsanity.com/paper/2211.07804/) (2022)
- [UCTransNet: Rethinking the Skip Connections in U-Net from a Channel-wise Perspective with Transformer](https://mlsanity.com/paper/2109.04335/) (2021)
- [Metrics reloaded: Recommendations for image analysis validation](https://mlsanity.com/paper/2206.01653/) (2022)
- [Medical Image Segmentation Review: The success of U-Net](https://mlsanity.com/paper/2211.14830/) (2022)
- [MedSegDiff-V2: Diffusion based Medical Image Segmentation with Transformer](https://mlsanity.com/paper/2301.11798/) (2023)
- [Evaluation of Algorithms for Multi-Modality Whole Heart Segmentation: An Open-Access Grand Challenge](https://mlsanity.com/paper/1902.07880/) (2019)
- [Ambiguous Medical Image Segmentation using Diffusion Models](https://mlsanity.com/paper/2304.04745/) (2023)
- [FlowSDF: Flow Matching for Medical Image Segmentation Using Distance Transforms](https://mlsanity.com/paper/2405.18087/) (2024)
- [HiDiff: Hybrid Diffusion Framework for Medical Image Segmentation](https://mlsanity.com/paper/2407.03548/) (2024)
- [A Survey on Diffusion Models for Anomaly Detection](https://mlsanity.com/paper/2501.11430/) (2025)
- [Cross-Modality Multi-Atlas Segmentation via Deep Registration and Label Fusion](https://mlsanity.com/paper/2202.02000/) (2022)
- [Continual atlas-based segmentation of prostate MRI](https://mlsanity.com/paper/2311.00548/) (2023)
- [Hybrid diffusion models: combining supervised and generative pretraining for label-efficient fine-tuning of segmentation models](https://mlsanity.com/paper/2408.03433/) (2024)

## Built on by (most cited first, 5 of 5)

- [GenMed: A Pairwise Generative Reformulation of Medical Diagnostic Tasks](https://mlsanity.com/paper/2605.10645/) (2026)
- [AortaDiff: A Unified Multitask Diffusion Framework For Contrast-Free AAA Imaging](https://mlsanity.com/paper/2510.01498/) (2025)
- [AS-Bridge: A Bidirectional Generative Framework Bridging Next-Generation Astronomical Surveys](https://mlsanity.com/paper/2603.11928/) (2026)
- [MUMINS: Metadata-conditioned Uncertainty-aware Medical Image Next-state Synthesis](https://mlsanity.com/paper/2609.17169/) (2026)
- [AnchorGen: Anchored Optimization for Customizable Generative 3D Design](https://mlsanity.com/paper/2610.06135/) (2026)

## Abstract (arXiv)

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.