Cargando…

Virtual mouse brain histology from multi-contrast MRI via deep learning

(1)H 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 M...

Descripción completa

Detalles Bibliográficos
Autores principales: Liang, Zifei, Lee, Choong H, Arefin, Tanzil M, Dong, Zijun, Walczak, Piotr, Shi, Song-Hai, Knoll, Florian, Ge, Yulin, Ying, Leslie, Zhang, Jiangyang
Formato: Online Artículo Texto
Lenguaje:English
Publicado: eLife Sciences Publications, Ltd 2022
Materias:
Acceso en línea:https://www.ncbi.nlm.nih.gov/pmc/articles/PMC8837198/
https://www.ncbi.nlm.nih.gov/pubmed/35088711
http://dx.doi.org/10.7554/eLife.72331
_version_ 1784649863644839936
author Liang, Zifei
Lee, Choong H
Arefin, Tanzil M
Dong, Zijun
Walczak, Piotr
Shi, Song-Hai
Knoll, Florian
Ge, Yulin
Ying, Leslie
Zhang, Jiangyang
author_facet Liang, Zifei
Lee, Choong H
Arefin, Tanzil M
Dong, Zijun
Walczak, Piotr
Shi, Song-Hai
Knoll, Florian
Ge, Yulin
Ying, Leslie
Zhang, Jiangyang
author_sort Liang, Zifei
collection PubMed
description (1)H 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.
format Online
Article
Text
id pubmed-8837198
institution National Center for Biotechnology Information
language English
publishDate 2022
publisher eLife Sciences Publications, Ltd
record_format MEDLINE/PubMed
spelling pubmed-88371982022-02-14 Virtual mouse brain histology from multi-contrast MRI via deep learning Liang, Zifei Lee, Choong H Arefin, Tanzil M Dong, Zijun Walczak, Piotr Shi, Song-Hai Knoll, Florian Ge, Yulin Ying, Leslie Zhang, Jiangyang eLife Medicine (1)H 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. eLife Sciences Publications, Ltd 2022-01-28 /pmc/articles/PMC8837198/ /pubmed/35088711 http://dx.doi.org/10.7554/eLife.72331 Text en © 2022, Liang et al https://creativecommons.org/licenses/by/4.0/This article is distributed under the terms of the Creative Commons Attribution License (https://creativecommons.org/licenses/by/4.0/) , which permits unrestricted use and redistribution provided that the original author and source are credited.
spellingShingle Medicine
Liang, Zifei
Lee, Choong H
Arefin, Tanzil M
Dong, Zijun
Walczak, Piotr
Shi, Song-Hai
Knoll, Florian
Ge, Yulin
Ying, Leslie
Zhang, Jiangyang
Virtual mouse brain histology from multi-contrast MRI via deep learning
title Virtual mouse brain histology from multi-contrast MRI via deep learning
title_full Virtual mouse brain histology from multi-contrast MRI via deep learning
title_fullStr Virtual mouse brain histology from multi-contrast MRI via deep learning
title_full_unstemmed Virtual mouse brain histology from multi-contrast MRI via deep learning
title_short Virtual mouse brain histology from multi-contrast MRI via deep learning
title_sort virtual mouse brain histology from multi-contrast mri via deep learning
topic Medicine
url https://www.ncbi.nlm.nih.gov/pmc/articles/PMC8837198/
https://www.ncbi.nlm.nih.gov/pubmed/35088711
http://dx.doi.org/10.7554/eLife.72331
work_keys_str_mv AT liangzifei virtualmousebrainhistologyfrommulticontrastmriviadeeplearning
AT leechoongh virtualmousebrainhistologyfrommulticontrastmriviadeeplearning
AT arefintanzilm virtualmousebrainhistologyfrommulticontrastmriviadeeplearning
AT dongzijun virtualmousebrainhistologyfrommulticontrastmriviadeeplearning
AT walczakpiotr virtualmousebrainhistologyfrommulticontrastmriviadeeplearning
AT shisonghai virtualmousebrainhistologyfrommulticontrastmriviadeeplearning
AT knollflorian virtualmousebrainhistologyfrommulticontrastmriviadeeplearning
AT geyulin virtualmousebrainhistologyfrommulticontrastmriviadeeplearning
AT yingleslie virtualmousebrainhistologyfrommulticontrastmriviadeeplearning
AT zhangjiangyang virtualmousebrainhistologyfrommulticontrastmriviadeeplearning