通过物理合成与中心图监督，提升微出血检测精度
CenSynCMB: Centre Maps and Physics-Guided Synthesis for Microbleed Detection
- 用中心图引导+物理合成数据增强模型定位能力
- 在VALDO和AIBL数据集上分别达74.3%和88.5%的召回率
- 适合大规模未标注MRI数据中的微出血自动提取
脑微出血（CMBs）是小血管病和淀粉样蛋白相关影像异常（ARIA-H）的重要MRI标志物，但其尺寸小、分布稀疏，且易与血管、钙化灶及伪影混淆，导致自动化检测困难。本文提出CenSynCMB框架，结合3D注意力U-Net、辅助中心图监督、基于漏检的重加权机制，以及分折物理引导的正样本与标注负样本合成。合成数据使检测器在不泄露验证/测试集的前提下接触紧凑病变与常见假阳性。在VALDO Task 2中，该方法达到最优局部对比病变级F1值74.3%（p=0.020）；在外部AIBL SWI数据集上，召回率达88.5%（p=0.0058），F1为65.0%（p=0.0016）。结果表明该方法可实现大规模无标注MRI队列中微出血候选的可扩展提取，下一步需针对不同队列进行校准以实现可靠负担估计。
原文摘要 · Abstract (English)
Cerebral microbleeds (CMBs) are MRI markers of small vessel disease and the microbleed component of amyloid related imaging abnormalities (ARIA-H), but their small size, sparsity, and similarity to vessels, calcification-like foci, and artefacts make automated detection difficult. We propose CenSynCMB, a centre-guided and mimic-aware framework combining a 3D Attention U-Net, auxiliary centre-map supervision, false-negative-driven reweighting, and fold-wise physics-guided synthesis of positive CMBs and labelled hard negatives. Synthetic data expose the detector to compact lesions and common mimics without validation or test leakage. On VALDO Task 2, CenSynCMB achieved the best local-comparison lesion-level F1 (74.3%, p = 0.020); on external AIBL SWI, it achieved the highest local-comparison recall (88.5%, p = 0.0058) and F1 (65.0%, p = 0.0016). Together, these results support scalable CMB candidate extraction in large, unlabelled MRI cohorts, while highlighting cohort-specific calibration as the next step toward reliable burden estimation.
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。