提出新自监督学习方法ACE，让医学图像嵌入更符合解剖结构
ACE: Anatomically Consistent Embeddings in Composition and Decomposition
- 通过全局与局部一致性分支，学习医学图像的解剖一致性嵌入
- 在6个数据集、2种主干网络上验证，少样本等场景表现更优
- 适合医学影像分析、病理检测等需要解剖先验的任务
标准协议获取的医学图像具有稳定的宏观或微观解剖结构，这些结构由可组合/可分解的器官和组织构成，但现有自监督学习方法未考虑此类属性。本文提出一种新方法ACE，通过组合与分解实现解剖一致嵌入：(1) 全局一致性，提取全局特征捕捉显著解剖结构；(2) 局部一致性，通过对应矩阵匹配学习可组合/可分解块的细粒度解剖细节。在6个数据集、2种骨干网络上，经少样本学习、微调及属性分析评估，证明ACE具备更强鲁棒性、可迁移性与临床潜力。创新点包括逐格图像裁剪，利用医学图像的组合性与分解性内在特性，弥合从高级病变到低级组织异常的语义鸿沟，为医学影像提供新自监督学习范式。
原文摘要 · Abstract (English)
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.
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。