用合成影像训练乳腺钙化分割模型，大幅减少人工标注需求。
BAC-JEPA: Label-Efficient Breast Arterial Calcification Segmentation via Synthetic Mammography-Guided Supervision
- 通过生成带精确掩码的合成乳腺影像，实现无像素级标注的训练。
- 在真实数据集上达到0.6357的Dice系数和0.8719的分类AUROC。
- 适合心血管风险筛查、医学图像合成与少样本学习研究者使用。
乳腺动脉钙化（BAC）是筛查乳腺钼靶中的新兴心血管风险生物标志物，但定量分析需可重复的分割结果，而专家级像素级标注成本高昂。本文提出BAC-JEPA，一种标签高效的分割框架，利用程序生成的动脉钙化插入真实乳腺背景并配以精确掩码进行训练。候选背景选自模型筛选出的低预测BAC响应钼靶图像；生成器模拟动脉结构、病变负荷、放射学外观及硬负样本（如非动脉性钙化和金属物）。合成掩码与自监督视觉变压器编码器及高分辨率卷积解码器结合，生成全分辨率分割图。研究使用34,956名患者的75,472张钼靶图像筛选背景并进行表征学习，以10,000个背景生成的合成图像训练模型，选择1,000个开发背景验证，并在1,000张人工标注的BacSeg合成2D钼靶图像上评估迁移性能。在预留的合成验证数据上，大模型取得IoU 0.5325、Dice 0.6357；基于分割概率图的图像级分类在BacSeg上达到AUROC 0.8719（小模型为0.8547）。四视图推理在RTX 5090 GPU上耗时110.68–213.63毫秒，严重预设合成图像生成平均每个2.7071秒（多核工作站）。结果表明，特定于BAC的合成监督可在无需人工像素级标注的情况下实现有效图像级迁移，但临床验证仍需专家评审的真实乳腺图像分割。
原文摘要 · Abstract (English)
Breast arterial calcification (BAC) on screening mammograms is an emerging cardiovascular risk biomarker, but quantitative use requires reproducible segmentation and expert pixel-level labels are costly. We present BAC-JEPA, a label-efficient segmentation framework trained on procedurally generated arterial calcification inserted into real mammographic backgrounds with exact masks. Candidate backgrounds were selected from model-screened mammograms with low predicted BAC response; the generator samples arterial structure, disease burden, radiographic appearance, and hard-negative distractors including nonarterial calcifications and metallic objects. Synthetic masks are paired with mammography self-supervised Vision Transformer encoders and a high-resolution convolutional decoder to produce full-resolution segmentation maps. The study used 75,472 mammography studies from 34,956 patients for background selection and representation learning, trained on synthetic images from 10,000 backgrounds, selected checkpoints with 1,000 development backgrounds, and evaluated transfer on all 1,000 human-labeled BacSeg synthetic 2D mammograms. On held-out synthetic validation data, the larger backbone achieved IoU 0.5325 and Dice 0.6357. On BacSeg, image-level classification from segmentation probability maps reached AUROC 0.8719, with 0.8547 for the smaller backbone. Four-view inference required 110.68--213.63 ms on an RTX 5090 GPU, and severe-preset synthetic image generation averaged 2.7071 s per image on a multicore workstation. These results indicate that BAC-specific synthetic supervision can produce useful image-level transfer without human pixel-level training masks, while expert-reviewed real-mammogram segmentation remains necessary for clinical validation and calibration.
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。