Virtual mouse brain histology from multi-contrast MRI via deep learning.
Virtual mouse brain histology from multi-contrast MRI via deep learning.
复制标题
DOI：
10.7554/elife.72331
复制
发表时间：
2022-01-28
期刊：
影响因子：
7.7
通讯作者：
Zhang J
中科院分区：
文献类型：
--
作者：
Liang Z;Lee CH;Arefin TM;Dong Z;Walczak P;Shi SH;Knoll F;Ge Y;Ying L;Zhang J
1H MRI通过利用组织微环境中的不均匀性的多用途对比，无创地绘制大脑结构和功能。然而，由于MRI信号和细胞结构之间缺乏直接联系，从磁共振成像（MRI）结果推断组织病理学信息仍然具有挑战性。在这里，我们展示了使用共同注册的多对比MRI和小鼠大脑的组织学数据开发的深度卷积神经网络，可以直接从每个体素的MRI信号中估计组织学染色强度。结果提供了轴突和髓鞘的三维地图与组织对比，密切模仿目标组织学和增强的敏感性和特异性相比，传统的MRI标记。此外，网络中每个MRI对比的相对贡献可用于优化多对比MRI采集。我们希望我们的方法能够成为神经生物学家将MRI结果转化为易于理解的虚拟组织学的起点，并为验证新的MRI技术提供资源。
1H MRI maps brain structure and function non-invasively through versatile contrasts that exploit inhomogeneity in tissue micro-environments. Inferring histopathological information from magnetic resonance imaging (MRI) findings, however, remains challenging due to absence of direct links between MRI signals and cellular structures. Here, we show that deep convolutional neural networks, developed using co-registered multi-contrast MRI and histological data of the mouse brain, can estimate histological staining intensity directly from MRI signals at each voxel. The results provide three-dimensional maps of axons and myelin with tissue contrasts that closely mimic target histology and enhanced sensitivity and specificity compared to conventional MRI markers. Furthermore, the relative contribution of each MRI contrast within the networks can be used to optimize multi-contrast MRI acquisition. We anticipate our method to be a starting point for translation of MRI results into easy-to-understand virtual histology for neurobiologists and provide resources for validating novel MRI techniques.