Machine learning of dissection photographs and surface scanning for quantitative 3D neuropathology

Authors:
Open Access
Publisher website
Google Scholar
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).
Funding Information
  • National Institute on Aging (R01AG070988)
  • National Institute on Aging (P30AG062421)
  • National Institutes of Health (RF1MH123195)
  • National Institutes of Health (R01EB031114)
  • National Institutes of Health (UM1MH130981)
  • National Institutes of Health (P30AG066509 (UW ADRC))
  • National Institutes of Health (U19AG066567)
  • National Institutes of Health (U19AG060909)
  • National Institutes of Health (K08AG065426)
  • National Institutes of Health (R01NS112161)
  • European Commission (ERC Starting Grant 677697)
  • Alzheimer’s Research UK (ARUK-IRG2019A-003)
  • Politècnica de Catalunya (Grant Ref 2021UPC-MS-67573)
  • National Institutes of Health (U01MH117023)
  • National Institutes of Health (1R01EB023281)
  • National Institutes of Health (R01EB006758)
  • National Institutes of Health (R21EB018907)
  • National Institutes of Health (R01EB019956)
  • National Institutes of Health (P41EB030006)
  • National Institutes of Health (1R56AG064027)
  • National Institutes of Health (1R01AG064027)
  • National Institutes of Health (5R01AG008122)
  • National Institutes of Health (R01AG016495)
  • National Institutes of Health (1R01AG070988)
  • National Institutes of Health (UM1MH130981)
  • National Institutes of Health (R01 MH123195)
  • National Institutes of Health (R01 MH121885)
  • National Institutes of Health (1RF1MH123195)
  • National Institutes of Health (R01NS0525851)
  • National Institutes of Health (R21NS072652)
  • National Institutes of Health (R01NS070963)
  • National Institutes of Health (R01NS083534)
  • National Institutes of Health (5U01NS086625)
  • National Institutes of Health (5U24NS10059103)
  • National Institutes of Health (R01NS105820)
  • National Institutes of Health (1S10RR023401)
  • National Institutes of Health (1S10RR019307)
  • National Institutes of Health (1S10RR023043)
  • National Institutes of Health (5U01MH093765)

This publication has 42 references indexed in Scilit: