Deep-Learning Language-Modeling Approach for Automated, Personalized, and Iterative Radiology-Pathology Correlation

摘要

Purpose: Radiology-pathology correlation has long been foundational to continuing education, peer learning, quality assurance, and multidisciplinary patient care. The objective of this study was to determine whether modern deep-learning language-modeling techniques could reliably match pathology reports to pertinent radiology reports.