Efficacy of a large language model in classifying branch-duct intraductal papillary mucinous neoplasms.
Objectives: Appropriate categorization based on magnetic resonance imaging (MRI) findings is important for managing intraductal papillary mucinous neoplasms (IPMNs). In this study, a large language model (LLM) that classifies IPMNs based on MRI findings was developed, and its performance was compare...
| Publicado en: | Abdominal Radiology Vol. 51; no. 1; pp. 417 - 424 |
|---|---|
| Autores principales: | , , , , , , |
| Formato: | Journal Article |
| Publicado: |
Springer Nature
Jan2026
|
| Acceso en línea: | Ver este registro en EBSCOhost |
| fields | @attributes: recordID: 1 pdfLink: plink: https://search.ebscohost.com/login.aspx?direct=true&db=ccm&AN=191138666&site=ehost-live header: @attributes: shortDbName: ccm uiTerm: 191138666 longDbName: CINAHL Complete uiTag: AN controlInfo: bkinfo: dissinfo: jinfo: jid: 2366004X JT14 jtl: Abdominal Radiology issn: 2366004X maglogo: N pubinfo: dt: Jan2026 vid: 51 iid: 1 pid: 237 pub: Springer Nature place: New York, New York artinfo: ui: 191138666 185856879 10.1007/s00261-025-05062-z 191138666 ppf: 417 ppct: 7 formats: fmt: – @attributes: type: T – @attributes: type: P tig: atl: Efficacy of a large language model in classifying branch-duct intraductal papillary mucinous neoplasms. aug: au: Sato, Mai Yasaka, Koichiro Abe, Shimon Kurashima, Joji Asari, Yusuke Kiryu, Shigeru Abe, Osamu affil: https://ror.org/057zh3y96 The University of Tokyo, Tokyo, Japan sug: ab: Objectives: Appropriate categorization based on magnetic resonance imaging (MRI) findings is important for managing intraductal papillary mucinous neoplasms (IPMNs). In this study, a large language model (LLM) that classifies IPMNs based on MRI findings was developed, and its performance was compared with that of less experienced human readers. Methods: The medical image management and processing systems of our hospital were searched to identify MRI reports of branch-duct IPMNs (BD-IPMNs). They were assigned to the training, validation, and testing datasets in chronological order. The model was trained on the training dataset, and the best-performing model on the validation dataset was evaluated on the test dataset. Furthermore, two radiology residents (Readers 1 and 2) and an intern (Reader 3) manually sorted the reports in the test dataset. The accuracy, sensitivity, and time required for categorizing were compared between the model and readers. Results: The accuracy of the fine-tuned LLM for the test dataset was 0.966, which was comparable to that of Readers 1 and 2 (0.931–0.972) and significantly better than that of Reader 3 (0.907). The fine-tuned LLM had an area under the receiver operating characteristic curve of 0.982 for the classification of cyst diameter ≥ 10 mm, which was significantly superior to that of Reader 3 (0.944). Furthermore, the fine-tuned LLM (25 s) completed the test dataset faster than the readers (1,887–2,646 s). Conclusion: The fine-tuned LLM classified BD-IPMNs based on MRI findings with comparable performance to that of radiology residents and significantly reduced the time required. pubtype: Academic Journal doctype: Journal Article ougenre: Article language: English refInfo: holdings: @attributes: islocal: N |
|---|