Published November 6, 2026 | Version v1

Brain slab dissection photograph segmentation dataset

Description

This dataset consists of 1,573 paired dissection photographs and manual segmentation masks of brain tissue slabs, acquired at Massachusetts General Hospital's Alzheimers Disease Research Center, and University of Washington's Department of Laboratory Medicine and Pathology. Segmentations masks were manually annotated to delineate the slab face, excluding background and out-of-slice tissue. This dataset is released alongside the paper "A public generalizable AI tool for automated segmentation of coronal brain tissue slabs for 3D neuropathology."
This dataset is intended to support the workflow for volumetric analysis of postmortem brain tissue. The segmentation mask serve as training data for an automatic segmentation model, facilitating image preprocessing for volumetric analysis tools such as FreeSurfer's photo tools https://surfer.nmr.mgh.harvard.edu/fswiki/PhotoTools which require segmentation of the slab face.

Files

images.zip

Files (758.0 MB)

Name Size
md5:30cbb334e52e592a33af834eb7d480af
753.3 MB Preview Download
md5:b1c7a421a6c58e2ef048de2dc8a60a3d
4.7 MB Preview Download

Additional details

References

  • Ramirez, J.W., Zemlyanker, D., Deden-Binder, L., Herisse, R., Pallares, E.G., Gopinath, K., Gazula, H., Mount, C., Kozanno, L.N., Marshall, M.S. and Connors, T.R., 2025. Automated Segmentation of Coronal Brain Tissue Slabs for 3D Neuropathology. arXiv preprint arXiv:2508.09805.