Automated classification method of COVID-19 cases from chest CT volumes using 2D and 3D hybrid CNN for anisotropic volumes

2026-07-30

AI Summary

This study addresses the critical challenge of strained healthcare resources during the COVID-19 pandemic by proposing an automated chest CT classification method based on a hybrid 2D/3D convolutional neural network for rapid identification of COVID-19 cases. The approach introduces a novel multi-planar feature extraction and fusion mechanism to effectively handle the anisotropic nature of CT volumetric data: complementary features are extracted from coronal, sagittal, and axial planes using both 2D and 3D CNNs, then fused to enhance discriminative capability. Evaluated on a clinical dataset comprising 1,288 CT volumes, the model achieves an average classification accuracy of 83.3%, significantly outperforming baseline methods employing single-structure CNN architectures.

Abstract

This paper proposes an automated classification method of chest CT volumes based on likelihood of COVID-19 cases. Novel coronavirus disease 2019 (COVID-19) spreads over the world, causing a large number of infected patients and deaths. Sudden increase in the number of COVID-19 patients causes a manpower shortage in medical institutions. Computer-aided diagnosis (CAD) system provides quick and quantitative diagnosis results. CAD system for COVID-19 enables efficient diagnosis workflow and contributes to reduce such manpower shortage. This paper proposes an automated classification method of chest CT volumes for COVID-19 diagnosis assistance. We propose a COVID-19 classification convolutional neural network (CNN) that has a 2D/3D hybrid feature extraction flows. The 2D/3D hybrid feature extraction flows are designed to effectively extract image features from anisotropic volumes such as chest CT volumes for diagnosis. The flows extract image features on three mutually perpendicular planes in CT volumes and then combine the features to perform classification. Classification accuracy of the proposed method was evaluated using a dataset that contains 1288 CT volumes. An averaged classification accuracy was 83.3%. The accuracy was higher than that of a classification CNN which does not have 2D and 3D hybrid feature extraction flows.

Problem

• COVID-19
• chest CT
• automated classification
• computer-aided diagnosis
• anisotropic volumes

Innovation

• 2D/3D hybrid CNN
• anisotropic CT volumes
• COVID-19 classification
• computer-aided diagnosis
• multi-planar feature fusion