Multi-modality Regional Alignment Network for Covid X-Ray Survival Prediction and Report Generation
This addresses the need for trustworthy AI tools to assist healthcare professionals with workload during the COVID-19 pandemic, though it is incremental in advancing existing radiology report generation methods.
The study tackled the problem of automating radiology report generation and survival prediction for COVID-19 X-rays by proposing MRANet, which improved performance through multi-modality regional alignment and cross LLMs alignment, as validated in multi-center experiments.
In response to the worldwide COVID-19 pandemic, advanced automated technologies have emerged as valuable tools to aid healthcare professionals in managing an increased workload by improving radiology report generation and prognostic analysis. This study proposes Multi-modality Regional Alignment Network (MRANet), an explainable model for radiology report generation and survival prediction that focuses on high-risk regions. By learning spatial correlation in the detector, MRANet visually grounds region-specific descriptions, providing robust anatomical regions with a completion strategy. The visual features of each region are embedded using a novel survival attention mechanism, offering spatially and risk-aware features for sentence encoding while maintaining global coherence across tasks. A cross LLMs alignment is employed to enhance the image-to-text transfer process, resulting in sentences rich with clinical detail and improved explainability for radiologist. Multi-center experiments validate both MRANet's overall performance and each module's composition within the model, encouraging further advancements in radiology report generation research emphasizing clinical interpretation and trustworthiness in AI models applied to medical studies. The code is available at https://github.com/zzs95/MRANet.