An Automated Framework for Pneumonia Severity Scoring on Chest Radiographs: A Transfer Learning and Multi-Task Learning Approach

Chest X-ray (CXR) is a crucial imaging modality for managing pneumonia, facilitating the assessment of disease severity and lung involvement to aid in disease staging and the effective allocation of healthcare resources. However, manual severity scoring by radiologists is not only subjective but also time-consuming, underscoring the need for automated deep learning (DL) solutions. A key challenge in developing such solutions is the scarcity of CXRs scored by radiologists, which are crucial for training robust DL models. This paper introduces a DL framework that leverages transfer learning and multi-task learning to overcome these limitations. Our approach includes a lung segmentation module designed to extract the entire thorax from frontal CXRs. We utilized a U-Net model, pre-trained on 2,000 publicly available CXRs and their corresponding infection masks, as the foundation for a multi-task network that was subsequently trained on a limited dataset of 100 viral pneumonia CXRs. This network integrates shared features of severity scoring and infection segmentation to enhance severity scoring accuracy. Our results are promising, suggesting that DL networks can effectively automate pneumonia severity assessments on CXRs, offering significant potential to reduce the workload of radiologists and increase diagnostic precision.