Saved in:
Bibliographic Details
Main Authors: Ramirez, Jonathan Williams, Zemlyanker, Dina, Deden-Binder, Lucas, Herisse, Rogeny, Pallares, Erendira Garcia, Gopinath, Karthik, Gazula, Harshvardhan, Mount, Christopher, Kozanno, Liana N., Marshall, Michael S., Connors, Theresa R., Frosch, Matthew P., Montine, Mark, Oakley, Derek H., Mac Donald, Christine L., Keene, C. Dirk, Hyman, Bradley T., Iglesias, Juan Eugenio
Format: Preprint
Published: 2025
Subjects:
Online Access:https://arxiv.org/abs/2508.09805
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1866918186767613952
author Ramirez, Jonathan Williams
Zemlyanker, Dina
Deden-Binder, Lucas
Herisse, Rogeny
Pallares, Erendira Garcia
Gopinath, Karthik
Gazula, Harshvardhan
Mount, Christopher
Kozanno, Liana N.
Marshall, Michael S.
Connors, Theresa R.
Frosch, Matthew P.
Montine, Mark
Oakley, Derek H.
Mac Donald, Christine L.
Keene, C. Dirk
Hyman, Bradley T.
Iglesias, Juan Eugenio
author_facet Ramirez, Jonathan Williams
Zemlyanker, Dina
Deden-Binder, Lucas
Herisse, Rogeny
Pallares, Erendira Garcia
Gopinath, Karthik
Gazula, Harshvardhan
Mount, Christopher
Kozanno, Liana N.
Marshall, Michael S.
Connors, Theresa R.
Frosch, Matthew P.
Montine, Mark
Oakley, Derek H.
Mac Donald, Christine L.
Keene, C. Dirk
Hyman, Bradley T.
Iglesias, Juan Eugenio
contents Advances in image registration and machine learning have recently enabled volumetric analysis of postmortem brain tissue from conventional photographs of coronal slabs, which are routinely collected in brain banks and neuropathology laboratories worldwide. One caveat of this methodology is the requirement of segmentation of the tissue from photographs, which currently requires costly manual intervention. In this article, we present a deep learning model to automate this process. The automatic segmentation tool relies on a U-Net architecture that was trained with a combination of 1,414 manually segmented images of both fixed and fresh tissue, from specimens with varying diagnoses, photographed at two different sites. Automated model predictions on a subset of photographs not seen in training were analyzed to estimate performance compared to manual labels, including both inter- and intra-rater variability. Our model achieved a median Dice score over 0.98, mean surface distance under 0.4mm, and 95\% Hausdorff distance under 1.60mm, which approaches inter-/intra-rater levels. Our tool is publicly available at surfer.nmr.mgh.harvard.edu/fswiki/PhotoTools.
format Preprint
id arxiv_https___arxiv_org_abs_2508_09805
institution arXiv
publishDate 2025
record_format arxiv
spellingShingle Automated Segmentation of Coronal Brain Tissue Slabs for 3D Neuropathology
Ramirez, Jonathan Williams
Zemlyanker, Dina
Deden-Binder, Lucas
Herisse, Rogeny
Pallares, Erendira Garcia
Gopinath, Karthik
Gazula, Harshvardhan
Mount, Christopher
Kozanno, Liana N.
Marshall, Michael S.
Connors, Theresa R.
Frosch, Matthew P.
Montine, Mark
Oakley, Derek H.
Mac Donald, Christine L.
Keene, C. Dirk
Hyman, Bradley T.
Iglesias, Juan Eugenio
Computer Vision and Pattern Recognition
Artificial Intelligence
Advances in image registration and machine learning have recently enabled volumetric analysis of postmortem brain tissue from conventional photographs of coronal slabs, which are routinely collected in brain banks and neuropathology laboratories worldwide. One caveat of this methodology is the requirement of segmentation of the tissue from photographs, which currently requires costly manual intervention. In this article, we present a deep learning model to automate this process. The automatic segmentation tool relies on a U-Net architecture that was trained with a combination of 1,414 manually segmented images of both fixed and fresh tissue, from specimens with varying diagnoses, photographed at two different sites. Automated model predictions on a subset of photographs not seen in training were analyzed to estimate performance compared to manual labels, including both inter- and intra-rater variability. Our model achieved a median Dice score over 0.98, mean surface distance under 0.4mm, and 95\% Hausdorff distance under 1.60mm, which approaches inter-/intra-rater levels. Our tool is publicly available at surfer.nmr.mgh.harvard.edu/fswiki/PhotoTools.
title Automated Segmentation of Coronal Brain Tissue Slabs for 3D Neuropathology
topic Computer Vision and Pattern Recognition
Artificial Intelligence
url https://arxiv.org/abs/2508.09805