ALTER: Modeling Longitudinal Changes via Regional Differencing for 3D CT Report Generation
This work addresses the challenge that existing 3D CT report generation methods struggle to accurately capture fine-grained longitudinal changes in patients, particularly due to the absence of anatomical region-level difference modeling. To overcome this limitation, we propose a change-aware report generation framework that integrates historical imaging and reports through Global Prior Integration (GPI). Our approach introduces a Region Proxy Differencing (RPD) mechanism to retrieve corresponding historical regions for each anatomical area and compute localized temporal differences. Furthermore, an Interval Change Fusion (ICF) strategy aggregates these multi-region temporal variations into a unified soft prompt to guide report generation. This method represents the first attempt to model longitudinal changes at the anatomical region level, significantly improving the accuracy and completeness of generated reports on the RadGenome-ChestCT and CTRG-Chest-548K datasets.