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

• Published in: arXiv.org
• Main Authors: Chun-Fu Yeh, Cheng, Hsien-Tzu, Wei, Andy, Hsin-Ming, Chen, Po-Chen, Kuo, Keng-Chi, Liu, Mong-Chi Ko, Chen, Ray-Jade, Po-Chang, Lee, Chuang, Jen-Hsiang, Chi-Mai, Chen, Yi-Chang, Chen, Wen-Jeng, Lee, Chien, Ning, Jo-Yu, Chen, Yu-Sen, Huang, Yu-Chien, Chang, Yu-Cheng, Huang, Chou, Nai-Kuan, Kuan-Hua, Chao, Yi-Chin, Tu, Chang, Yeun-Chung, Liu, Tyng-Luh
• Format: Paper
• Language: English
• Published: Ithaca Cornell University Library, arXiv.org 30.04.2020
• Subjects: Artificial neural networks; Chest; Coronaviruses; COVID-19; Datasets; Image classification; Machine learning; Pneumonia; Screening; Severe acute respiratory syndrome coronavirus 2

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.