3D RegNet: Deep Learning Model for COVID-19 Diagnosis on Chest CT Image

TL;DR

This paper introduces a 3D-RegNet deep learning model that improves COVID-19 diagnosis accuracy from chest CT scans by capturing spatial features lost in 2D analysis, demonstrating high F1 score and AUC.

Contribution

The paper presents a novel 3D deep learning model for COVID-19 diagnosis that leverages volumetric CT data to enhance accuracy over traditional 2D methods.

Findings

F1 score of 0.8379 on test set

AUC of 0.8807 indicating high diagnostic performance

Effective extraction of 3D features from CT images

Abstract

In this paper, a 3D-RegNet-based neural network is proposed for diagnosing the physical condition of patients with coronavirus (Covid-19) infection. In the application of clinical medicine, lung CT images are utilized by practitioners to determine whether a patient is infected with coronavirus. However, there are some laybacks can be considered regarding to this diagnostic method, such as time consuming and low accuracy. As a relatively large organ of human body, important spatial features would be lost if the lungs were diagnosed utilizing two dimensional slice image. Therefore, in this paper, a deep learning model with 3D image was designed. The 3D image as input data was comprised of two-dimensional pulmonary image sequence and from which relevant coronavirus infection 3D features were extracted and classified. The results show that the test set of the 3D model, the result: f1 score of 0.8379 and AUC value of 0.8807 have been achieved.