Anatomy-Guided Radiology Report Generation with Pathology-Aware Regional Prompts
This work addresses the problem of improving radiology report generation for clinical use, offering a domain-specific advancement that is incremental in its method but enhances precision and relevance.
The paper tackled the challenge of generating clinically accurate radiology reports by addressing issues with subtle lesions and insufficient pathological information in existing systems, resulting in a model that outperforms state-of-the-art methods on most metrics and is validated by expert evaluations.
Radiology reporting generative AI holds significant potential to alleviate clinical workloads and streamline medical care. However, achieving high clinical accuracy is challenging, as radiological images often feature subtle lesions and intricate structures. Existing systems often fall short, largely due to their reliance on fixed size, patch-level image features and insufficient incorporation of pathological information. This can result in the neglect of such subtle patterns and inconsistent descriptions of crucial pathologies. To address these challenges, we propose an innovative approach that leverages pathology-aware regional prompts to explicitly integrate anatomical and pathological information of various scales, significantly enhancing the precision and clinical relevance of generated reports. We develop an anatomical region detector that extracts features from distinct anatomical areas, coupled with a novel multi-label lesion detector that identifies global pathologies. Our approach emulates the diagnostic process of radiologists, producing clinically accurate reports with comprehensive diagnostic capabilities. Experimental results show that our model outperforms previous state-of-the-art methods on most natural language generation and clinical efficacy metrics, with formal expert evaluations affirming its potential to enhance radiology practice.