CT-AGRG: Automated Abnormality-Guided Report Generation from 3D Chest CT Volumes

TL;DR

This paper introduces CT-AGRG, a novel model that improves automated report generation from 3D chest CT scans by explicitly focusing on abnormalities, leading to more accurate and clinically relevant reports.

Contribution

The paper presents an anomaly-guided approach that predicts abnormalities first and then generates targeted descriptions, enhancing report quality over unguided methods.

Findings

Significant improvement in report quality and clinical relevance.

Effective abnormality prediction enhances targeted report generation.

Ablation study confirms the model's effectiveness.

Abstract

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.