Classification of COVID-19 from CXR Images in a 15-class Scenario: an\n Attempt to Avoid Bias in the System

2021/09/25 by Chinmoy K Bose, Bose, Chinmoy, Anirvan Basu +1
Computer Science · Medicine · #AI in cancer detection #COVID-19 diagnosis using AI #Computer Vision and Pattern Recognition (cs.CV) #FOS: Computer and information sciences #FOS: Electrical engineering #Image and Video Processing (eess.IV) #Machine Learning (cs.LG) #Radiomics and Machine Learning in Medical Imaging #electronic engineering #information engineering

paper · pdf · doi:10.48550/arxiv.2109.12453

openalex publication_date 2021/09/25 · openalex created_date 2022/07/25 · openalex updated_date 2026/07/28

Abstract

As of June 2021, the World Health Organization (WHO) has reported 171.7\nmillion confirmed cases including 3,698,621 deaths from COVID-19. Detecting\nCOVID-19 and other lung diseases from Chest X-Ray (CXR) images can be very\neffective for emergency diagnosis and treatment as CXR is fast and cheap. The\nobjective of this study is to develop a system capable of detecting COVID-19\nalong with 14 other lung diseases from CXRs in a fair and unbiased manner. The\nproposed system consists of a CXR image selection technique and a deep learning\nbased model to classify 15 diseases including COVID-19. The proposed CXR\nselection technique aims to retain the maximum variation uniformly and\neliminate poor quality CXRs with the goal of reducing the training dataset size\nwithout compromising classifier accuracy. More importantly, it reduces the\noften hidden bias and unfairness in decision making. The proposed solution\nexhibits a promising COVID-19 detection scheme in a more realistic situation\nthan most existing studies as it deals with 15 lung diseases together. We hope\nthe proposed method will have wider adoption in medical image classification\nand other related fields.\n

Citations

• Very Deep Convolutional Networks for Large-Scale Image Recognition
• Densely Connected Convolutional Networks
• MobileNets: Efficient Convolutional Neural Networks for Mobile Vision Applications
• MURA: Large Dataset for Abnormality Detection in Musculoskeletal Radiographs
• Chest X-rays Classification: A Multi-Label and Fine-Grained Problem
• Deep Residual Learning for Image Recognition
• Xception: Deep Learning with Depthwise Separable Convolutions
• COVID-19 Image Data Collection
• Prediction models for diagnosis and prognosis of covid-19: systematic review and critical appraisal
• CovidAID: COVID-19 Detection Using Chest X-Ray
• COVID-DA: Deep Domain Adaptation from Typical Pneumonia to COVID-19
• Deep Convolutional Neural Networks to Diagnose COVID-19 and other Pneumonia Diseases from Posteroanterior Chest X-Rays
• COVID-Net: a tailored deep convolutional neural network design for detection of COVID-19 cases from chest X-ray images

Related

• Screening COVID-19 Based on CT/CXR Images & Building a Publicly Available CT-scan Dataset of COVID-19
• COVID-19 Classification of X-ray Images Using Deep Neural Networks
• Using Deep Convolutional Neural Networks to Diagnose COVID-19 From Chest X-Ray Images
• Classification of COVID-19 on chest X-Ray images using Deep Learning model with Histogram Equalization and Lungs Segmentation
• Fast and accurate detection of Covid-19-related pneumonia from chest X-ray images with novel deep learning model