Finding-Centric Structuring of Japanese Radiology Reports and Analysis of Performance Gaps for Multiple Facilities
Yuki Tagawa, Yohei Momoki, Norihisa Nakano, Ryota Ozaki, Motoki Taniguchi, Masatoshi Hori, Noriyuki Tomiyama
Abstract
This study addresses two key challenges in structuring radiology reports: the lack of a practical structuring schema and datasets to evaluate model generalizability. To address these challenges, we propose a “Finding-Centric Structuring,” which organizes reports around individual findings, facilitating secondary use. We also construct JRadFCS, a large-scale dataset with annotated named entities (NEs) and relations, comprising 8,428 Japanese Computed Tomography (CT) reports from seven facilities, providing a comprehensive resource for evaluating model generalizability. Our experiments reveal performance gaps when applying models trained on single-facility reports to those from other facilities. We further analyze factors contributing to these gaps and demonstrate that augmenting the training set based on these performance-correlated factors can efficiently enhance model generalizability.
BibTeX
@inproceedings{tagawa-etal-2025-finding,
title = "Finding-Centric Structuring of {J}apanese Radiology Reports and Analysis of Performance Gaps for Multiple Facilities",
author = "Tagawa, Yuki and
Momoki, Yohei and
Nakano, Norihisa and
Ozaki, Ryota and
Taniguchi, Motoki and
Hori, Masatoshi and
Tomiyama, Noriyuki",
editor = "Chen, Weizhu and
Yang, Yi and
Kachuee, Mohammad and
Fu, Xue-Yong",
booktitle = "Proceedings of the 2025 Conference of the Nations of the Americas Chapter of the Association for Computational Linguistics: Human Language Technologies (Volume 3: Industry Track)",
month = apr,
year = "2025",
address = "Albuquerque, New Mexico",
publisher = "Association for Computational Linguistics",
url = "https://aclanthology.org/2025.naacl-industry.7/",
pages = "70--85",
ISBN = "979-8-89176-194-0"
}