Figure - PMC

Skip to main content

An official website of the United States government

Here's how you know

Here's how you know

Official websites use .gov
A .gov website belongs to an official government organization in the United States.

Secure .gov websites use HTTPS
A lock ( ) or https:// means you've safely connected to the .gov website. Share sensitive information only on official, secure websites.

View full-text article in PMC

. 2024 Jan 11;34(5):e13239. doi: 10.1111/bpa.13239

Search in PMC
Search in PubMed
View in NLM Catalog
Add to search

© 2024 The Authors. Brain Pathology published by John Wiley & Sons Ltd on behalf of International Society of Neuropathology.

This is an open access article under the terms of the http://creativecommons.org/licenses/by-nc/4.0/ License, which permits use, distribution and reproduction in any medium, provided the original work is properly cited and is not used for commercial purposes.

PMC Copyright notice

Histology‐based classification of MPE subtypes MPE‐A and MPE‐B. (A) Validation accuracies of CLAM models during training for various downscale levels (left panel). The accuracy can be further optimized by rejecting samples with high uncertainty (right panel). (B) Representative patches for the two MPE subtypes with high attention scores from the test and validation set at 8× downscale. (C) Percentage of tissue area per slide labeled to exhibit predominant myxoid changes/microcysts, hyalinized vessels or blood by RandomForest. Hyalinized vessels and blood show statistically significant differences (one‐sided t‐tests, p < 0.05), whereas myxoid changes/microcysts are not specific to a MPE subgroup.