发表机构
Medical Ultrasound Image Computing (MUSIC) Lab, School of Artificial Intelligence, Shenzhen University; College of Computer Science and Software Engineering, Shenzhen University; National Engineering Laboratory for Big Data System Computing Technology, Shenzhen University; School of Biomedical Engineering, Medical School, Shenzhen University; School of Biomedical Engineering and Informatics, Nanjing Medical University（医学超声图像计算（MUSIC）实验室，深圳大学人工智能学院; 深圳大学计算机科学与软件学院; 深圳大学大数据系统计算技术国家工程实验室; 深圳大学医学院生物医学工程学院; 南京医科大学生物医学工程与信息学院）
机构由 AI 辅助整理，请以论文原文为准。AI 中文总结
研究针对产前超声异常诊断，提出AnomExpert框架，利用可学习平面原型和疾病感知稀疏选择机制，仅通过病例级监督实现解剖平面识别与选择，实验显示其优于多种方法，提升了弱监督多平面产前超声异常分类效果。
AI 中文摘要
危及生命的先天性异常需要准确的产前诊断以进行适当的临床决策制定。产前超声检查涉及多个解剖平面，诊断依赖于识别解剖平面并为每个异常选择诊断相关平面。现有自动化方法要么依赖平面级注释，要么聚合异构图像而未明确建模这些诊断能力。我们提出AnomExpert，一个仅使用病例级监督的用于产前超声异常诊断的原型驱动框架。AnomExpert引入可学习的平面原型，将无序图像组织成与解剖平面对应的潜在表示，无需平面注释。一种疾病感知稀疏选择机制进一步为每个异常选择诊断相关平面。在3654例的多中心数据集上的实验表明，AnomExpert始终优于九种有代表性的多实例学习方法。使用ViT-small骨干网络，它在保持参数效率的同时，实现了86.9%的准确率和84.2%的F1分数。这些发现表明，对解剖平面识别和疾病特定平面选择进行建模可改善弱监督多平面产前超声异常分类。代码可在该https网址获取。
英文摘要
Life-limiting congenital anomalies require accurate prenatal diagnosis for appropriate clinical decision-making. Prenatal ultrasound (US) examinations involve multiple anatomical planes, and diagnosis depends on identifying anatomical planes and selecting diagnostically relevant planes for each anomaly. Existing automated methods either rely on plane-level annotations or aggregate heterogeneous images without explicitly modeling these diagnostic capabilities. We propose AnomExpert, a prototype-driven framework for prenatal US anomaly diagnosis using only case-level supervision. AnomExpert introduces learnable plane prototypes to organize unordered images into latent representations corresponding to anatomical planes without requiring plane annotations. A disease-aware sparse selection mechanism further selects diagnostically relevant planes for each anomaly. Experiments on a multi-center dataset of 3,654 cases show that AnomExpert consistently outperforms nine representative multi-instance learning methods. Using a ViT-small backbone, it achieves 86.9% accuracy and 84.2% F1-score while maintaining parameter efficiency. These findings indicate that modeling anatomical plane identification and disease-specific plane selection improves weakly supervised multi-plane prenatal US anomaly classification. The code is available at https://github.com/TIanCat/AnomExpert.
CommentsIt has been accepted early by MICCAI2026
