TY - JOUR TI - Virtual mouse brain histology from multi-contrast MRI via deep learning AU - Liang, Zifei AU - Lee, Choong H AU - Arefin, Tanzil M AU - Dong, Zijun AU - Walczak, Piotr AU - Shi, Song-Hai AU - Knoll, Florian AU - Ge, Yulin AU - Ying, Leslie AU - Zhang, Jiangyang A2 - Jbabdi, Saad A2 - de Lange, Floris P A2 - Jbabdi, Saad VL - 11 PY - 2022 DA - 2022/01/28 SP - e72331 C1 - eLife 2022;11:e72331 DO - 10.7554/eLife.72331 UR - https://doi.org/10.7554/eLife.72331 AB - 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. KW - magnetic resonance imaging KW - deep learning KW - mouse brain KW - axon KW - myelin KW - histology JF - eLife SN - 2050-084X PB - eLife Sciences Publications, Ltd ER -