MvKeTR: Chest CT Report Generation with Multi-View Perception and Knowledge Enhancement

원문 초록

CT report generation (CTRG) aims to automatically generate diagnostic reports for 3D volumes, relieving clinicians' workload and improving patient care. Despite clinical value, existing works fail to effectively incorporate diagnostic information from multiple anatomical views and lack related clinical expertise essential for accurate and reliable diagnosis. To resolve these limitations, we propose a novel Multi-view perception Knowledge-enhanced Transformer (MvKeTR) to mimic the diagnostic workflow of clinicians. Just as radiologists first examine CT scans from multiple planes, a Multi-View Perception Aggregator (MVPA) with view-aware attention effectively synthesizes diagnostic information from multiple anatomical views. Then, inspired by how radiologists further refer to relevant clinical records to guide diagnostic decision-making, a Cross-Modal Knowledge Enhancer (CMKE) retrieves the most similar reports based on the query volume to incorporate domain knowledge into the diagnosis procedure. Furthermore, instead of traditional MLPs, we employ Kolmogorov-Arnold Networks (KANs) with learnable nonlinear activation functions as the fundamental building blocks of both modules to better capture intricate diagnostic patterns in CT interpretation. Extensive experiments on the public CTRG-Chest-548K dataset demonstrate that our method outpaces prior state-of-the-art (SOTA) models across almost all metrics. The code will be made publicly available.