An Automated Framework for Pneumonia Severity Scoring on Chest Radiographs: A Transfer Learning and Multi-Task Learning Approach
Bibliographic record
Abstract
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.
Fetched live from OpenAlex and de-inverted. Abstracts are not stored in this database: the inverted indexes are 8.6 GB of the frame’s 9.3 GB of text, and the host has 13 GB free.
How this classification was reachedexpand
Full frame machine prediction
Teacher imitationNot calibrated prevalence, not ground truth. Human validation pending. The Gemma side is a direct model label for every work in the frame, read from the title-only record. The Codex side is a classifier learned from the 10,348 direct Codex labels and calibrated to design-weighted sample rates; fields without enough sample support carry no Codex call. Candidate is the union of the two sides; consensus is their intersection. These outputs are machine_predicted_unvalidated and are not human labels.
Distilled classifier scores by category (both heads)
| Category | Codex | Gemma |
|---|---|---|
| Metaresearch | 0.002 | 0.003 |
| Meta-epidemiology (narrow) | 0.002 | 0.001 |
| Meta-epidemiology (broad) | 0.001 | 0.001 |
| Bibliometrics | 0.001 | 0.001 |
| Science and technology studies | 0.001 | 0.001 |
| Scholarly communication | 0.001 | 0.001 |
| Open science | 0.002 | 0.002 |
| Research integrity | 0.002 | 0.002 |
| Insufficient payload (model declined to judge) | 0.002 | 0.001 |
Machine scores (provisional)
The two teacher heads of the student model, read on this work. A score orders the frame for review; it never asserts a category, and the validation status ships verbatim with every row.
Baseline scores from an immature model (maturity gate not passed, 7 training rounds). Scores rank; they never assert a category.
score_only:v0-immature-baseline · verbatim from the scoring run: score_only means the number may rank works, and no category label ships from itClassification
machine, unvalidatedMachine predicted; a candidate call from one source (direct Gemma or distilled Codex), not a consensus.
How this classification was reached, model by model and score by score, is at the end of the page under "How this classification was reached".