arXiv 2311.085442023-10-22q-bio.NCcs.CVeess.IV

JOSA：基于表面的脑几何与功能联合配准及图谱构建

JOSA: Joint surface-based registration and atlas construction of brain geometry and function

McGovern Institute for Brain Research, MIT（麦戈文脑科学研究所（麻省理工学院））；Harvard University（哈佛大学）；Computer Science and Artificial Intelligence Laboratory, MIT（计算机科学与人工智能实验室（麻省理工学院））

Jian Li, Greta Tuckute, Evelina Fedorenko, Brian L. Edlow, Adrian V. Dalca, Bruce Fischl

备注：: A. V. Dalca and B. Fischl are co-senior authors with equal contribution. arXiv admin note: text overlap with arXiv:2303.01592

阅读 PDF

arXiv 页面 ↗HTML 原文 ↗

AI总结：

JOSA提出一种联合建模几何与功能不匹配的皮层配准框架，通过半监督学习实现无偏图谱构建，在配准性能上超越现有方法，且推理时无需功能数据。

摘要：

基于表面的皮层配准是医学图像分析中的一个重要课题，并促进了许多下游应用。当前的皮层配准方法主要由几何特征驱动，如沟深和曲率，并且通常假设折叠模式的配准会导致脑功能的对齐。然而，解剖学上对应区域在不同受试者之间的功能变异性已被广泛报道，特别是在高级认知区域。在这项工作中，我们提出了JOSA，一种新颖的皮层配准框架，它联合建模了几何与功能之间的不匹配，同时学习一个无偏的人群特异性图谱。通过半监督训练策略，JOSA在几何和功能方面均达到了优于现有最先进方法的配准性能，且在推理时不需要功能数据。该学习框架可以扩展到任何在训练时可用但在推理时难以或无法获得的辅助数据，以指导球形配准，例如分区、构筑学身份、转录组信息和分子谱。通过识别几何与功能之间的不匹配，JOSA为未来使用脑结构与功能联合分析的配准方法发展提供了新的见解。

英文摘要：

Surface-based cortical registration is an important topic in medical image analysis and facilitates many downstream applications. Current approaches for cortical registration are mainly driven by geometric features, such as sulcal depth and curvature, and often assume that registration of folding patterns leads to alignment of brain function. However, functional variability of anatomically corresponding areas across subjects has been widely reported, particularly in higher-order cognitive areas. In this work, we present JOSA, a novel cortical registration framework that jointly models the mismatch between geometry and function while simultaneously learning an unbiased population-specific atlas. Using a semi-supervised training strategy, JOSA achieves superior registration performance in both geometry and function to the state-of-the-art methods but without requiring functional data at inference. This learning framework can be extended to any auxiliary data to guide spherical registration that is available during training but is difficult or impossible to obtain during inference, such as parcellations, architectonic identity, transcriptomic information, and molecular profiles. By recognizing the mismatch between geometry and function, JOSA provides new insights into the future development of registration methods using joint analysis of the brain structure and function.

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。