Feature Selection based on Machine Learning in MRIs for Hippocampal Segmentation

TL;DR

This study compares four feature selection techniques for hippocampal segmentation in MRI scans, demonstrating that a subset of 23 features can achieve performance comparable to established tools like FreeSurfer.

Contribution

It introduces and evaluates four feature selection methods for voxel-based hippocampal segmentation, highlighting the effectiveness of sequential backward elimination.

Findings

23 features suffice for accurate segmentation

Comparable performance to FreeSurfer achieved

Sequential backward elimination is effective

Abstract

Neurodegenerative diseases are frequently associated with structural changes in the brain. Magnetic Resonance Imaging (MRI) scans can show these variations and therefore be used as a supportive feature for a number of neurodegenerative diseases. The hippocampus has been known to be a biomarker for Alzheimer disease and other neurological and psychiatric diseases. However, it requires accurate, robust and reproducible delineation of hippocampal structures. Fully automatic methods are usually the voxel based approach, for each voxel a number of local features were calculated. In this paper we compared four different techniques for feature selection from a set of 315 features extracted for each voxel: (i) filter method based on the Kolmogorov-Smirnov test; two wrapper methods, respectively, (ii) Sequential Forward Selection and (iii) Sequential Backward Elimination; and (iv) embedded method based on the Random Forest Classifier on a set of 10 T1-weighted brain MRIs and tested on an independent set of 25 subjects. The resulting segmentations were compared with manual reference labelling. By using only 23 features for each voxel (sequential backward elimination) we obtained comparable state of-the-art performances with respect to the standard tool FreeSurfer.