MRGen：基于扩散的MRI分割可控数据引擎，面向未标记的模态。

MRGen: Diffusion-based Controllable Data Engine for MRI Segmentation towards Unannotated Modalities

December 4, 2024

作者: Haoning Wu, Ziheng Zhao, Ya Zhang, Weidi Xie, Yanfeng Wang

cs.AI

摘要

近年来，深度神经网络在医学图像分割方面取得了令人瞩目的进展，然而异质模态和标注蒙版的稀缺限制了在未标注模态上开发分割模型。本文探讨了在医学应用中利用生成模型的新范式：可控合成未标注模态的数据，而无需注册数据对。具体来说，本文在以下方面做出了贡献：(i)我们收集和整理了一个大规模的放射学图像文本数据集MedGen-1M，包括模态标签、属性、区域和器官信息，以及一部分器官蒙版标注，以支持可控医学图像生成的研究；(ii)我们提出了一种基于扩散的数据引擎，称为MRGen，它能够根据文本提示和蒙版进行生成，合成缺乏蒙版标注的多样模态的MR图像，以训练未标注模态上的分割模型；(iii)我们在各种模态上进行了大量实验，表明我们的数据引擎能够有效合成训练样本，并将MRI分割扩展到未标注模态。

English

Medical image segmentation has recently demonstrated impressive progress with deep neural networks, yet the heterogeneous modalities and scarcity of mask annotations limit the development of segmentation models on unannotated modalities. This paper investigates a new paradigm for leveraging generative models in medical applications: controllably synthesizing data for unannotated modalities, without requiring registered data pairs. Specifically, we make the following contributions in this paper: (i) we collect and curate a large-scale radiology image-text dataset, MedGen-1M, comprising modality labels, attributes, region, and organ information, along with a subset of organ mask annotations, to support research in controllable medical image generation; (ii) we propose a diffusion-based data engine, termed MRGen, which enables generation conditioned on text prompts and masks, synthesizing MR images for diverse modalities lacking mask annotations, to train segmentation models on unannotated modalities; (iii) we conduct extensive experiments across various modalities, illustrating that our data engine can effectively synthesize training samples and extend MRI segmentation towards unannotated modalities.