Classification of COVID-19 via Homology of CT-SCAN

Abstract

Automated analysis of biomedical images plays a crucial role in enabling early diagnosis. In this article, we propose a novel approach based on persistent homology, a central technique from topological data analysis, for detecting traces of COVID-19 infection in CT-scan images. Our method is based on an intuitive and natural idea of analyzing shapes and opacities. We quantify these topological features using persistent homology and transform them into vector representations suitable for classification. These features are then reduced in dimensionality and classified using a support vector machine (SVM), capturing the global structure of key radiological patterns such as ground-glass opacities and consolidations.

To ensure reproducibility and external validation, we conducted experiments on two distinct publicly available datasets: the SARS-CoV-2 CT-scan and the HRCT Chest COVID dataset. Our approach achieved F1 scores of 99.4% and 99.6%, respectively.

These results demonstrate that our method offers both high performance and clinical interpretability. By leveraging stable and descriptive topological features, our approach generalizes well across datasets without requiring data augmentation or pretraining, making it especially suitable for deployment in data-limited healthcare settings.