Clustering COVID-19 Lung Scans

TL;DR

This paper investigates the use of unsupervised clustering methods, including PCA, K-Means++, and RCC, to differentiate COVID-19 lung scans from other respiratory illnesses, aiming to find hidden patterns without labeled data.

Contribution

It applies and compares advanced clustering algorithms to identify distinctive features of COVID-19 in lung scans, highlighting the potential of unsupervised methods in medical diagnostics.

Findings

RCC outperforms K-Means++ in clustering accuracy

Unsupervised clustering reveals significant differences between COVID-19 and other lung conditions

PCA effectively reduces dimensionality for clustering tasks

Abstract

With the ongoing COVID-19 pandemic, understanding the characteristics of the virus has become an important and challenging task in the scientific community. While tests do exist for COVID-19, the goal of our research is to explore other methods of identifying infected individuals. Our group applied unsupervised clustering techniques to explore a dataset of lungscans of COVID-19 infected, Viral Pneumonia infected, and healthy individuals. This is an important area to explore as COVID-19 is a novel disease that is currently being studied in detail. Our methodology explores the potential that unsupervised clustering algorithms have to reveal important hidden differences between COVID-19 and other respiratory illnesses. Our experiments use: Principal Component Analysis (PCA), K-Means++ (KM++) and the recently developed Robust Continuous Clustering algorithm (RCC). We evaluate the performance of KM++ and RCC in clustering COVID-19 lung scans using the Adjusted Mutual Information (AMI) score.