Self-Supervision and Multi-Task Learning: Challenges in Fine-Grained COVID-19 Multi-Class Classification from Chest X-rays

TL;DR

This paper explores the use of self-supervised pre-training and multi-task learning to improve fine-grained COVID-19 classification from chest X-rays, addressing challenges in clinical viability and annotation dependence.

Contribution

It introduces the combination of self-supervised learning and multi-task training to enhance COVID-19 classification accuracy and reduces reliance on annotated data.

Findings

Self-supervised pre-training improves model performance.

Multi-task learning enhances differentiation of COVID-19 infection types.

Critical evaluation highlights challenges in clinical deployment.

Abstract

Quick and accurate diagnosis is of paramount importance to mitigate the effects of COVID-19 infection, particularly for severe cases. Enormous effort has been put towards developing deep learning methods to classify and detect COVID-19 infections from chest radiography images. However, recently some questions have been raised surrounding the clinical viability and effectiveness of such methods. In this work, we investigate the impact of multi-task learning (classification and segmentation) on the ability of CNNs to differentiate between various appearances of COVID-19 infections in the lung. We also employ self-supervised pre-training approaches, namely MoCo and inpainting-CXR, to eliminate the dependence on expensive ground truth annotations for COVID-19 classification. Finally, we conduct a critical evaluation of the models to assess their deploy-readiness and provide insights into the difficulties of fine-grained COVID-19 multi-class classification from chest X-rays.