Personalized Impression Generation for PET Reports Using Large Language Models.

Large language models (LLMs) have shown promise in accelerating radiology reporting by summarizing clinical findings into impressions. However, automatic impression generation for whole-body PET reports presents unique challenges and has received little attention. Our study aimed to evaluate whether...

Full description

Bibliographic Details
Published in:Journal of Digital Imaging Vol. 37; no. 2; pp. 471 - 489
Main Authors: Tie, Xin, Shin, Muheon, Pirasteh, Ali, Ibrahim, Nevein, Huemann, Zachary, Castellino, Sharon M., Kelly, Kara M., Garrett, John, Hu, Junjie, Cho, Steve Y., Bradshaw, Tyler J.
Format: research tables/charts Journal Article
Published: Springer Nature Apr2024
Online Access:View this record in EBSCOhost
fields @attributes:
  recordID: 1
pdfLink:
plink: https://search.ebscohost.com/login.aspx?direct=true&db=ccm&AN=177626022&site=ehost-live
header:
  @attributes:
    shortDbName: ccm
    uiTerm: 177626022
    longDbName: CINAHL Complete
    uiTag: AN
  controlInfo:
    bkinfo:
    dissinfo:
    jinfo:
      jid:
        08971889
        DOQ
      jtl: Journal of Digital Imaging
      issn: 08971889
      maglogo: N
    pubinfo:
      dt: Apr2024
      vid: 37
      iid: 2
      pid: 237
      pub: Springer Nature
      place: New York, New York
    artinfo:
      ui:
        177626022
        177626022
        177626022
        10.1007/s10278-024-00985-3
        177626022
      ppf: 471
      ppct: 18
      formats:
        fmt:
          – @attributes:
              type: T
          – @attributes:
              type: P
      tig:
        atl: Personalized Impression Generation for PET Reports Using Large Language Models.
      aug:
        au:
          Tie, Xin
          Shin, Muheon
          Pirasteh, Ali
          Ibrahim, Nevein
          Huemann, Zachary
          Castellino, Sharon M.
          Kelly, Kara M.
          Garrett, John
          Hu, Junjie
          Cho, Steve Y.
          Bradshaw, Tyler J.
        affil: Department of Radiology, School of Medicine and Public Health, University of Wissconsin, Madison, WI, USA
      sug:
        subj:
          Artificial Intelligence
          Positron-Emission Tomography
          Reports
          Image Processing, Computer Assisted
          Human
          Retrospective Design
          Algorithms
          Descriptive Statistics
          Physicians
          Funding Source
      ab: Large language models (LLMs) have shown promise in accelerating radiology reporting by summarizing clinical findings into impressions. However, automatic impression generation for whole-body PET reports presents unique challenges and has received little attention. Our study aimed to evaluate whether LLMs can create clinically useful impressions for PET reporting. To this end, we fine-tuned twelve open-source language models on a corpus of 37,370 retrospective PET reports collected from our institution. All models were trained using the teacher-forcing algorithm, with the report findings and patient information as input and the original clinical impressions as reference. An extra input token encoded the reading physician's identity, allowing models to learn physician-specific reporting styles. To compare the performances of different models, we computed various automatic evaluation metrics and benchmarked them against physician preferences, ultimately selecting PEGASUS as the top LLM. To evaluate its clinical utility, three nuclear medicine physicians assessed the PEGASUS-generated impressions and original clinical impressions across 6 quality dimensions (3-point scales) and an overall utility score (5-point scale). Each physician reviewed 12 of their own reports and 12 reports from other physicians. When physicians assessed LLM impressions generated in their own style, 89% were considered clinically acceptable, with a mean utility score of 4.08/5. On average, physicians rated these personalized impressions as comparable in overall utility to the impressions dictated by other physicians (4.03, P = 0.41). In summary, our study demonstrated that personalized impressions generated by PEGASUS were clinically useful in most cases, highlighting its potential to expedite PET reporting by automatically drafting impressions.
      pubtype: Academic Journal
      doctype:
        research
        tables/charts
        Journal Article
      ougenre: Article
    language: English
    refInfo:
    holdings:
      @attributes:
        islocal: N