ACE：组合与分解中的解剖学一致性嵌入
ACE: Anatomically Consistent Embeddings in Composition and Decomposition
AI总结：
针对现有自监督学习未利用医学图像可组合/可分解解剖结构属性的问题，提出ACE方法，通过全局与局部一致性双分支学习解剖一致嵌入，在多数据集多骨干上验证了更优的鲁棒性、迁移性与临床价值。
摘要：
通过标准化流程采集的医学图像呈现出一致的宏观或微观解剖结构，且这些结构由可组合/可分解的器官和组织构成，但现有自监督学习（SSL）方法并未重视医学图像固有的这种可组合/可分解结构属性。为克服这一局限，本文提出一种名为ACE的新型自监督学习方法，通过组合与分解学习解剖学一致性嵌入，包含两个关键分支：（1）全局一致性分支，通过提取全局特征捕捉具有判别性的宏观结构；（2）局部一致性分支，通过对应矩阵匹配从可组合/可分解的斑块特征中学习细粒度解剖细节。在6个数据集、2种骨干网络上开展的实验涵盖少样本学习、微调及属性分析评估，结果表明ACE具备更优的鲁棒性、迁移性及临床潜力。ACE的创新点在于采用网格式图像裁剪，利用医学图像组合性与分解性的内在属性，弥合从高层病理到低层组织异常的语义鸿沟，为医学成像领域提供了一种新的自监督学习方法。
英文摘要：
Medical images acquired from standardized protocols show consistent macroscopic or microscopic anatomical structures, and these structures consist of composable/decomposable organs and tissues, but existing self-supervised learning (SSL) methods do not appreciate such composable/decomposable structure attributes inherent to medical images. To overcome this limitation, this paper introduces a novel SSL approach called ACE to learn anatomically consistent embedding via composition and decomposition with two key branches: (1) global consistency, capturing discriminative macro-structures via extracting global features; (2) local consistency, learning fine-grained anatomical details from composable/decomposable patch features via corresponding matrix matching. Experimental results across 6 datasets 2 backbones, evaluated in few-shot learning, fine-tuning, and property analysis, show ACE's superior robustness, transferability, and clinical potential. The innovations of our ACE lie in grid-wise image cropping, leveraging the intrinsic properties of compositionality and decompositionality of medical images, bridging the semantic gap from high-level pathologies to low-level tissue anomalies, and providing a new SSL method for medical imaging.
机构、总结、中文摘要均由AI分析而来，可能存在错误，请以论文正文为准。
