Automated triage of COVID-19 from various lung abnormalities using chest CT features

TL;DR

This paper presents an AI system that automatically analyzes chest CT scans to accurately distinguish COVID-19 from other lung abnormalities, aiding rapid diagnosis during the pandemic.

Contribution

It introduces a comprehensive feature-based machine learning approach for COVID-19 triage using chest CT scans, with extensive feature analysis and validation.

Findings

Achieved 90.8% sensitivity and 85.4% specificity

Demonstrated 94.0% ROC-AUC performance

Validated on 2191 CT cases

Abstract

The outbreak of COVID-19 has lead to a global effort to decelerate the pandemic spread. For this purpose chest computed-tomography (CT) based screening and diagnosis of COVID-19 suspected patients is utilized, either as a support or replacement to reverse transcription-polymerase chain reaction (RT-PCR) test. In this paper, we propose a fully automated AI based system that takes as input chest CT scans and triages COVID-19 cases. More specifically, we produce multiple descriptive features, including lung and infections statistics, texture, shape and location, to train a machine learning based classifier that distinguishes between COVID-19 and other lung abnormalities (including community acquired pneumonia). We evaluated our system on a dataset of 2191 CT cases and demonstrated a robust solution with 90.8% sensitivity at 85.4% specificity with 94.0% ROC-AUC. In addition, we present an elaborated feature analysis and ablation study to explore the importance of each feature.