arXiv 2309.153582023-09-27cs.CV

迈向通过自监督从医学影像解剖结构中学习的基础模型

Towards Foundation Models Learned from Anatomy in Medical Imaging via Self-Supervision

Arizona State University（亚利桑那州立大学）；Mayo Clinic（梅奥诊所）

Mohammad Reza Hosseinzadeh Taher, Michael B. Gotway, Jianming Liang

备注：: International Conference on Medical Image Computing and Computer Assisted Intervention (MICCAI 2023)---Domain Adaptation and Representation Transfer

阅读 PDF

arXiv 页面 ↗HTML 原文 ↗

AI总结：

本文提出利用人体解剖结构层次性、局部性与组合性的自监督学习策略，预训练医学影像基础模型，在分割任务上较SSL基线提升9%至30%。

摘要：

人体解剖结构是医学影像的基础，并具有一个显著特征：其本质上的层次性，表现出两个内在属性：（1）局部性：每个解剖结构在形态上都与其他结构不同；（2）组合性：每个解剖结构都是更大整体的有机组成部分。我们设想一种医学影像基础模型，有意识、有目的地在这一基础上开发，以获得“理解”人体解剖结构的能力，并具备医学影像的基本属性。作为实现医学影像基础模型这一愿景的第一步，我们设计了一种新颖的自监督学习（SSL）策略，利用人体解剖结构的层次本质。大量实验表明，由我们的训练策略得到的SSL预训练模型，不仅优于最先进（SOTA）的全监督/自监督基线，还提升了标注效率，提供了潜在的少样本分割能力；与SSL基线相比，其在分割任务上的性能提升为9%至30%。这种性能归因于通过我们的学习策略实现解剖理解的重要性，该策略将解剖结构的内在属性——局部性和组合性——封装在嵌入空间中，而现有SSL方法忽视了这一点。所有代码和预训练模型均可在 https://github.com/JLiangLab/Eden 获取。

英文摘要：

Human anatomy is the foundation of medical imaging and boasts one striking characteristic: its hierarchy in nature, exhibiting two intrinsic properties: (1) locality: each anatomical structure is morphologically distinct from the others; and (2) compositionality: each anatomical structure is an integrated part of a larger whole. We envision a foundation model for medical imaging that is consciously and purposefully developed upon this foundation to gain the capability of "understanding" human anatomy and to possess the fundamental properties of medical imaging. As our first step in realizing this vision towards foundation models in medical imaging, we devise a novel self-supervised learning (SSL) strategy that exploits the hierarchical nature of human anatomy. Our extensive experiments demonstrate that the SSL pretrained model, derived from our training strategy, not only outperforms state-of-the-art (SOTA) fully/self-supervised baselines but also enhances annotation efficiency, offering potential few-shot segmentation capabilities with performance improvements ranging from 9% to 30% for segmentation tasks compared to SSL baselines. This performance is attributed to the significance of anatomy comprehension via our learning strategy, which encapsulates the intrinsic attributes of anatomical structures-locality and compositionality-within the embedding space, yet overlooked in existing SSL methods. All code and pretrained models are available at https://github.com/JLiangLab/Eden.

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。