Tracking Cancer Through Text: Longitudinal Extraction from Radiology Reports using Open-source Large Language Models

Radiology reports capture crucial longitudinal information on tumor burden, treatment response, and disease progression, yet their unstructured narrative format complicates automated analysis. We present a fully open-source, locally deployable pipeline for longitudinal information extraction from radiology reports, implemented using the llm_extractinator framework. The system applies the qwen2.5-72b model to extract and link target, non-target, and new lesion data across time points in accordance with RECIST criteria.