Multi-level SVM Based CAD Tool for Classifying Structural MRIs

TL;DR

This paper presents a multi-level SVM-based CAD tool that combines NMF and Haralick features for improved classification of neural lesions in MRIs, achieving over 86% accuracy in distinguishing CVA from other disorders.

Contribution

It introduces a novel multi-level classification system integrating NMF and Haralick features with SVM for better diagnostic accuracy in MRI analysis.

Findings

Classification accuracy over 86%

Improved sensitivity and specificity

Enhanced efficiency over single-feature systems

Abstract

The revolutionary developments in the field of supervised machine learning have paved way to the development of CAD tools for assisting doctors in diagnosis. Recently, the former has been employed in the prediction of neurological disorders such as Alzheimer's disease. We propose a CAD (Computer Aided Diagnosis tool for differentiating neural lesions caused by CVA (Cerebrovascular Accident) from the lesions caused by other neural disorders by using Non-negative Matrix Factorisation (NMF) and Haralick features for feature extraction and SVM (Support Vector Machine) for pattern recognition. We also introduce a multi-level classification system that has better classification efficiency, sensitivity and specificity when compared to systems using NMF or Haralick features alone as features for classification. Cross-validation was performed using LOOCV (Leave-One-Out Cross Validation) method and our proposed system has a classification accuracy of over 86%.