A Review of Automated Diagnosis of COVID-19 Based on Scanning Images

TL;DR

This paper reviews recent automatic COVID-19 diagnosis models using X-ray and CT images, analyzing 70 models developed in early 2020, and discusses future research directions like transfer learning and interpretability.

Contribution

It provides a comprehensive review of 70 COVID-19 diagnostic models based on imaging, highlighting their methodologies and suggesting future research directions.

Findings

70 models analyzed from early 2020

Identified key steps: preprocessing, feature extraction, classification

Highlighted future directions: domain adaptation and interpretability

Abstract

The pandemic of COVID-19 has caused millions of infections, which has led to a great loss all over the world, socially and economically. Due to the false-negative rate and the time-consuming of the conventional Reverse Transcription Polymerase Chain Reaction (RT-PCR) tests, diagnosing based on X-ray images and Computed Tomography (CT) images has been widely adopted. Therefore, researchers of the computer vision area have developed many automatic diagnosing models based on machine learning or deep learning to assist the radiologists and improve the diagnosing accuracy. In this paper, we present a review of these recently emerging automatic diagnosing models. 70 models proposed from February 14, 2020, to July 21, 2020, are involved. We analyzed the models from the perspective of preprocessing, feature extraction, classification, and evaluation. Based on the limitation of existing models, we pointed out that domain adaption in transfer learning and interpretability promotion would be the possible future directions.