eLife (Jun 2024)
Machine learning of dissection photographs and surface scanning for quantitative 3D neuropathology
- Harshvardhan Gazula,
- Henry FJ Tregidgo,
- Benjamin Billot,
- Yael Balbastre,
- Jonathan Williams-Ramirez,
- Rogeny Herisse,
- Lucas J Deden-Binder,
- Adria Casamitjana,
- Erica J Melief,
- Caitlin S Latimer,
- Mitchell D Kilgore,
- Mark Montine,
- Eleanor Robinson,
- Emily Blackburn,
- Michael S Marshall,
- Theresa R Connors,
- Derek H Oakley,
- Matthew P Frosch,
- Sean I Young,
- Koen Van Leemput,
- Adrian V Dalca,
- Bruce Fischl,
- Christine L MacDonald,
- C Dirk Keene,
- Bradley T Hyman,
- Juan E Iglesias
Affiliations
- Harshvardhan Gazula
- Martinos Center for Biomedical Imaging, MGH and Harvard Medical School, Charlestown, United States
- Henry FJ Tregidgo
- ORCiD
- Centre for Medical Image Computing, University College London, London, United Kingdom
- Benjamin Billot
- Computer Science and Artificial Intelligence Laboratory, MIT, Cambridge, United States
- Yael Balbastre
- Martinos Center for Biomedical Imaging, MGH and Harvard Medical School, Charlestown, United States
- Jonathan Williams-Ramirez
- Martinos Center for Biomedical Imaging, MGH and Harvard Medical School, Charlestown, United States
- Rogeny Herisse
- Martinos Center for Biomedical Imaging, MGH and Harvard Medical School, Charlestown, United States
- Lucas J Deden-Binder
- Martinos Center for Biomedical Imaging, MGH and Harvard Medical School, Charlestown, United States
- Adria Casamitjana
- Centre for Medical Image Computing, University College London, London, United Kingdom; Biomedical Imaging Group, Universitat Politècnica de Catalunya, Barcelona, Spain
- Erica J Melief
- BioRepository and Integrated Neuropathology (BRaIN) Laboratory and Precision Neuropathology Core, UW School of Medicine, Seattle, United States
- Caitlin S Latimer
- BioRepository and Integrated Neuropathology (BRaIN) Laboratory and Precision Neuropathology Core, UW School of Medicine, Seattle, United States
- Mitchell D Kilgore
- ORCiD
- BioRepository and Integrated Neuropathology (BRaIN) Laboratory and Precision Neuropathology Core, UW School of Medicine, Seattle, United States
- Mark Montine
- BioRepository and Integrated Neuropathology (BRaIN) Laboratory and Precision Neuropathology Core, UW School of Medicine, Seattle, United States
- Eleanor Robinson
- Centre for Medical Image Computing, University College London, London, United Kingdom
- Emily Blackburn
- Centre for Medical Image Computing, University College London, London, United Kingdom
- Michael S Marshall
- Massachusetts Alzheimer Disease Research Center, MGH and Harvard Medical School, Charlestown, United States
- Theresa R Connors
- Massachusetts Alzheimer Disease Research Center, MGH and Harvard Medical School, Charlestown, United States
- Derek H Oakley
- Massachusetts Alzheimer Disease Research Center, MGH and Harvard Medical School, Charlestown, United States
- Matthew P Frosch
- Massachusetts Alzheimer Disease Research Center, MGH and Harvard Medical School, Charlestown, United States
- Sean I Young
- Martinos Center for Biomedical Imaging, MGH and Harvard Medical School, Charlestown, United States
- Koen Van Leemput
- Martinos Center for Biomedical Imaging, MGH and Harvard Medical School, Charlestown, United States; Neuroscience and Biomedical Engineering, Aalto University, Espoo, Finland
- Adrian V Dalca
- Martinos Center for Biomedical Imaging, MGH and Harvard Medical School, Charlestown, United States; Computer Science and Artificial Intelligence Laboratory, MIT, Cambridge, United States
- Bruce Fischl
- Martinos Center for Biomedical Imaging, MGH and Harvard Medical School, Charlestown, United States
- Christine L MacDonald
- Department of Neurological Surgery, UW School of Medicine, Seattle, United States
- C Dirk Keene
- ORCiD
- BioRepository and Integrated Neuropathology (BRaIN) Laboratory and Precision Neuropathology Core, UW School of Medicine, Seattle, United States
- Bradley T Hyman
- ORCiD
- Massachusetts Alzheimer Disease Research Center, MGH and Harvard Medical School, Charlestown, United States
- Juan E Iglesias
- ORCiD
- Martinos Center for Biomedical Imaging, MGH and Harvard Medical School, Charlestown, United States; Centre for Medical Image Computing, University College London, London, United Kingdom; Computer Science and Artificial Intelligence Laboratory, MIT, Cambridge, United States
- DOI
- https://doi.org/10.7554/eLife.91398
- Journal volume & issue
-
Vol. 12
Abstract
We present open-source tools for three-dimensional (3D) analysis of photographs of dissected slices of human brains, which are routinely acquired in brain banks but seldom used for quantitative analysis. Our tools can: (1) 3D reconstruct a volume from the photographs and, optionally, a surface scan; and (2) produce a high-resolution 3D segmentation into 11 brain regions per hemisphere (22 in total), independently of the slice thickness. Our tools can be used as a substitute for ex vivo magnetic resonance imaging (MRI), which requires access to an MRI scanner, ex vivo scanning expertise, and considerable financial resources. We tested our tools on synthetic and real data from two NIH Alzheimer’s Disease Research Centers. The results show that our methodology yields accurate 3D reconstructions, segmentations, and volumetric measurements that are highly correlated to those from MRI. Our method also detects expected differences between post mortem confirmed Alzheimer’s disease cases and controls. The tools are available in our widespread neuroimaging suite ‘FreeSurfer’ (https://surfer.nmr.mgh.harvard.edu/fswiki/PhotoTools).
Keywords
