A Cascaded Learning Strategy for Robust COVID-19 Pneumonia Chest X-Ray Screening

TL;DR

This paper presents a cascaded learning approach to improve COVID-19 pneumonia detection from chest X-ray images, effectively utilizing large non-COVID datasets to enhance model sensitivity and specificity.

Contribution

It introduces a novel cascaded training strategy that leverages non-COVID pneumonia data to improve COVID-19 detection accuracy in chest X-ray classification.

Findings

Achieved high classification performance on expanded datasets

Improved sensitivity and specificity of COVID-19 detection

Effective use of non-COVID pneumonia data for model training

Abstract

We introduce a comprehensive screening platform for the COVID-19 (a.k.a., SARS-CoV-2) pneumonia. The proposed AI-based system works on chest x-ray (CXR) images to predict whether a patient is infected with the COVID-19 disease. Although the recent international joint effort on making the availability of all sorts of open data, the public collection of CXR images is still relatively small for reliably training a deep neural network (DNN) to carry out COVID-19 prediction. To better address such inefficiency, we design a cascaded learning strategy to improve both the sensitivity and the specificity of the resulting DNN classification model. Our approach leverages a large CXR image dataset of non-COVID-19 pneumonia to generalize the original well-trained classification model via a cascaded learning scheme. The resulting screening system is shown to achieve good classification performance on the expanded dataset, including those newly added COVID-19 CXR images.