CT-AGRG: Automated Abnormality-Guided Report Generation from 3D Chest CT Volumes
This addresses the workload of radiologists by automating report generation, but it is incremental as it builds on existing methods by adding explicit abnormality guidance.
The paper tackled the problem of generating radiology reports from 3D chest CT scans by proposing an anomaly-guided model that first predicts abnormalities and then generates targeted descriptions, resulting in significant improvements in report quality and clinical relevance.
The rapid increase of computed tomography (CT) scans and their time-consuming manual analysis have created an urgent need for robust automated analysis techniques in clinical settings. These aim to assist radiologists and help them managing their growing workload. Existing methods typically generate entire reports directly from 3D CT images, without explicitly focusing on observed abnormalities. This unguided approach often results in repetitive content or incomplete reports, failing to prioritize anomaly-specific descriptions. We propose a new anomaly-guided report generation model, which first predicts abnormalities and then generates targeted descriptions for each. Evaluation on a public dataset demonstrates significant improvements in report quality and clinical relevance. We extend our work by conducting an ablation study to demonstrate its effectiveness.