用解剖一致性流匹配生成高质量双视角乳腺钼靶图
MammoFlow: Multiview Mammogram Synthesis with Anatomically Consistent Flow Matching
- 通过2D仿射变换对齐视图，建立解剖对应关系
- 利用地球移动距离损失确保前后组织分布一致，生成物理合理图像
- 提升下游分类任务AUC 5%，获放射科医生认可
双视角乳腺钼靶检查依赖正位（CC）和侧斜位（MLO）视图，提供三维乳房体积的互补投影，有助于精确定位异常。然而，深度学习应用面临高质量、均衡数据集获取困难。本文提出一种新方法，利用CC与MLO视图间的固有几何关系合成多视角乳腺钼靶图像。为在生成过程中引入隐式三维一致性先验，我们设计一个对齐模块，在二维仿射变换子空间中搜索最优解剖对应。基于此对齐，提出一种像素空间自一致性损失，计算生成图像沿前后轴（AP）组织分布的地球移动距离（EMD）。该损失集成于预训练流匹配模型中，强制合成图像对共享从胸壁到乳头的物理上合理的组织分布。据我们所知，这是首个利用隐式几何组织对应指导多视角乳腺钼靶生成的工作。实验表明，该方法生成图像质量优异，通过放射科医生评估，并使下游分类任务的AUC提升5%。代码已开源：https://github.com/XYPB/MammoFlow
原文摘要 · Abstract (English)
Multiview mammography relies on paired craniocaudal (CC) and mediolateral oblique (MLO) views to provide complementary projections of a 3D breast volume, enabling precise anomaly localization. However, acquiring high-quality, balanced datasets remains challenging for deep learning applications. We propose a novel method to synthesize multiview mammograms by leveraging the inherent geometric relationship between CC and MLO views. To enforce an implicit 3D consistency prior during generation, we develop an alignment module that searches a 2D affine transformation subspace to establish optimal anatomical correspondence. Leveraging this alignment, we introduce a pixel-space self-consistency loss based on the Earth Mover's Distance (EMD) between the 1D anteroposterior (AP) axis tissue distributions of the generated images. Integrated into a pretrained flow matching model, MammoFlow forces synthesized pairs to share physically plausible tissue distributions from the chest wall to the nipple. To our knowledge, this is the first work to guide multiview mammogram generation using implicit geometric tissue correspondence. Our method demonstrates superior image quality, passes expert radiologist evaluation, and generates physically consistent pairs that improve downstream classification AUC by 5%. Code is available at https://github.com/XYPB/MammoFlow
Thank you to arXiv for use of its open access interoperability. PaperDance 不是 arXiv 官方产品；中文卡片由大模型生成，请以原文为准。