Virtual mouse brain histology from multi-contrast MRI via deep learning Journal Article
| Authors: | Liang, Z.; Lee, C. H.; Arefin, T. M.; Dong, Z.; Walczak, P.; Shi, S. H.; Knoll, F.; Ge, Y.; Ying, L.; Zhang, J. |
| Article Title: | Virtual mouse brain histology from multi-contrast MRI via deep learning |
| Abstract: | 1H MRI maps brain structure and function non-invasively through versatile contrasts that exploit inhomogeneity in tissue micro-environments. Inferring histopathological information from 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 mimics 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. © 2022, eLife Sciences Publications Ltd. All rights reserved. |
| Keywords: | immunohistochemistry; adult; controlled study; human tissue; major clinical study; histopathology; area under the curve; nonhuman; neuroimaging; nuclear magnetic resonance imaging; sensitivity and specificity; myelin basic protein; mouse; animal tissue; signal noise ratio; animal experiment; immunofluorescence; prediction; training; image quality; image processing; ex vivo study; diffusion weighted imaging; white matter; image reconstruction; anisotropy; receiver operating characteristic; artificial neural network; image segmentation; diagnostic test accuracy study; neurofilament; retina blood vessel; three-dimensional imaging; human; male; female; article; autofluorescence imaging; nissl staining; brain histology; deep learning; convolutional neural network; local field potential |
| Journal Title: | eLife |
| Volume: | 11 |
| ISSN: | 2050-084X |
| Publisher: | eLife Sciences Publications Ltd. |
| Date Published: | 2022-01-28 |
| Start Page: | e72331 |
| Language: | English |
| DOI: | 10.7554/eLife.72331 |
| PUBMED: | 35088711 |
| PROVIDER: | scopus |
| PMCID: | PMC8837198 |
| DOI/URL: | |
| Notes: | Article -- Export Date: 1 March 2022 -- Source: Scopus |
