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

. 2023 Feb 15;5:1009638. doi: 10.3389/fmedt.2023.1009638

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

© 2023 Chen, Streeter, Hunt, Sardar, Gunn, Tafe, Paydarfar, Pogue, Paulsen and Samkoe.

This is an open-access article distributed under the terms of the Creative Commons Attribution License (CC BY). The use, distribution or reproduction in other forums is permitted, provided the original author(s) and the copyright owner(s) are credited and that the original publication in this journal is cited, in accordance with accepted academic practice. No use, distribution or reproduction is permitted which does not comply with these terms.

PMC Copyright notice

Model hyperparameter optimization through LOOCV and feature selection. (A) Heatmap depicts the LOOCV mean accuracy achieved by different combinations of classifiers (rows) and feature selection algorithms (columns) when 25 top-ranked features were used. The combination of SVM classifier and MRMR feature selection showed the highest validation accuracy. (B) Hierarchical clustering of training set sub-image patches (5,470 total; vertical axis) and optomic features (1,472 total; horizontal axis) reveals natural groupings of tissue types. (C) Most frequently selected features by MRMR with the optimal hyperparameters combination during LOOCV. Horizontal axis represents the number of times that each optomic feature was selected by MRMR in all 18 folds of LOOCV.