Automated deep learning segmentation of high-resolution 7 T postmortem MRI for quantitative analysis of structure-pathology correlations in neurodegenerative diseases

Postmortem MRI allows brain anatomy to be examined at high resolution and to link pathology measures with morphometric measurements. However, automated segmentation methods for brain mapping in postmortem MRI are not well developed, primarily due to limited availability of labeled datasets, and hete...

Full description

Saved in:
Bibliographic Details
Published in:arXiv.org 2023-10
Main Authors: Khandelwal, Pulkit, Michael Tran Duong, Sadaghiani, Shokufeh, Lim, Sydney, Denning, Amanda, Chung, Eunice, Ravikumar, Sadhana, Arezoumandan, Sanaz, Peterson, Claire, Madigan Bedard, Capp, Noah, Ittyerah, Ranjit, Migdal, Elyse, Choi, Grace, Kopp, Emily, Loja, Bridget, Eusha Hasan, Li, Jiacheng, Bahena, Alejandra, Prabhakaran, Karthik, Mizsei, Gabor, Gabrielyan, Marianna, Schuck, Theresa, Trotman, Winifred, Robinson, John, Ohm, Daniel, Lee, Edward B, Trojanowski, John Q, McMillan, Corey, Grossman, Murray, Irwin, David J, Detre, John, Tisdall, M Dylan, Das, Sandhitsu R, Wisse, Laura E M, Wolk, David A, Yushkevich, Paul A
Format: Article
Language:English
Subjects:
Automation
Availability
Brain
Datasets
Deep learning
Heterogeneity
High resolution
Histology
Image acquisition
Image segmentation
Magnetic resonance imaging
Quantitative analysis
Scanners
Thalamus
Thickness measurement
Online Access:Get full text
Tags: Add Tag
No Tags, Be the first to tag this record!
Description
Summary:Postmortem MRI allows brain anatomy to be examined at high resolution and to link pathology measures with morphometric measurements. However, automated segmentation methods for brain mapping in postmortem MRI are not well developed, primarily due to limited availability of labeled datasets, and heterogeneity in scanner hardware and acquisition protocols. In this work, we present a high resolution of 135 postmortem human brain tissue specimens imaged at 0.3 mm\(^{3}\) isotropic using a T2w sequence on a 7T whole-body MRI scanner. We developed a deep learning pipeline to segment the cortical mantle by benchmarking the performance of nine deep neural architectures, followed by post-hoc topological correction. We then segment four subcortical structures (caudate, putamen, globus pallidus, and thalamus), white matter hyperintensities, and the normal appearing white matter. We show generalizing capabilities across whole brain hemispheres in different specimens, and also on unseen images acquired at 0.28 mm^3 and 0.16 mm^3 isotropic T2*w FLASH sequence at 7T. We then compute localized cortical thickness and volumetric measurements across key regions, and link them with semi-quantitative neuropathological ratings. Our code, Jupyter notebooks, and the containerized executables are publicly available at: https://pulkit-khandelwal.github.io/exvivo-brain-upenn
ISSN:2331-8422