Classification of Hepatic Lesions using the Matching Metric

TL;DR

This paper introduces a novel method for classifying liver lesions using topological data analysis, specifically multidimensional persistent homology and the matching metric, combined with support vector machines, showing promising results.

Contribution

It demonstrates the effectiveness of topological features, especially 2D persistent homology, in hepatic lesion classification, advancing medical image analysis techniques.

Findings

Topological features aid in classifying hepatic lesions.

2D persistent homology outperforms 1D in this task.

The method achieves promising classification accuracy.

Abstract

In this paper we present a methodology of classifying hepatic (liver) lesions using multidimensional persistent homology, the matching metric (also called the bottleneck distance), and a support vector machine. We present our classification results on a dataset of 132 lesions that have been outlined and annotated by radiologists. We find that topological features are useful in the classification of hepatic lesions. We also find that two-dimensional persistent homology outperforms one-dimensional persistent homology in this application.