EUVIMEDEUVIMED entdecken
Crossref

Multimodal Generative Artificial Intelligence Model for Creating Radiology Reports for Chest Radiographs in Patients Undergoing Tuberculosis Screening

Eun Kyoung Hong, Hae Won Kim, Ok Kyu Song, Kyu-Chong Lee, Dong Kyu Kim, Jae-Bock Cho, Jungbin Kim, Seungho Lee, Woong Bae, Byungseok Roh

American Journal of Roentgenology · 2025-10 · 225 (4)

DOI: 10.2214/ajr.25.33059 ↗

Kurz gefasst

Fachartikel in der Zeitschrift American Journal of Roentgenology, 2025-10. Verfasst von Eun Kyoung Hong und 9 weiteren Autor:innen. Beteiligte Einrichtung: Department of Radiology, Mass General Brigham, Brigham & Women's Hospital, 75 Francis St, Boston, MA 02115. Hauptthemen laut MEDLINE: Artificial Intelligence, Radiography, Thoracic, Tuberculosis, Pulmonary, Radiographic Image Interpretation, Computer-Assisted. Die Arbeit wurde bisher 10-mal zitiert (Crossref) und nennt 24 Literaturangaben.

AbstractSchlagwörterBibliografische AngabenZitierenVerwandte Studien

Abstract (Originalsprache)

BACKGROUND. Chest radiographs play a crucial role in tuberculosis screening in high-prevalence regions, although widespread radiographic screening requires expertise that may be unavailable in settings with limited medical resources. OBJECTIVE. The purpose of this study was to evaluate a multimodal generative artificial intelligence (AI) model for detecting tuberculosis-associated abnormalities on chest radiography in patients undergoing tuberculosis screening. METHODS. This retrospective study evaluated 800 chest radiographs obtained from two public datasets originating from tuberculosis screening programs. A generative AI model was used to create free-text reports for the radiographs. AI-generated reports were classified in terms of presence versus absence and laterality of tuberculosis-related abnormalities. Two radiologists independently reviewed the radiographs for tuberculosis presence and laterality in separate sessions, without and with use of AI-generated reports, and recorded if they would accept the report without modification. Two additional radiologists reviewed radiographs and clinical readings from the datasets to determine the reference standard. RESULTS. By the reference standard, 378 of 800 radiographs were positive for tuberculosis-related abnormalities. For detection of tuberculosis-related abnormalities, sensitivity, specificity, and accuracy were 95.2%, 86.7%, and 90.8% for AI-generated reports; 93.1%, 93.6%, and 93.4% for reader 1 without AI-generated reports; 93.1%, 95.0%, and 94.1% for reader 1 with AI-generated reports; 95.8%, 87.2%, and 91.3% for reader 2 without AI-generated reports; and 95.8%, 91.5%, and 93.5% for reader 2 with AI-generated reports. Accuracy was significantly lower for AI-generated reports than for both readers alone (p < .001), but significantly higher with than without AI-generated reports for one reader (reader 1: p = .47; reader 2: p = .03). Localization performance was significantly lower (p < .001) for AI-generated reports (63.3%) than for reader 1 (79.8%) and reader 2 (77.9%) without AI-generated reports and did not significantly change for either reader with AI-generated reports (reader 1: 78.7%, p = .71; reader 2: 81.5%, p = .23). Among normal and abnormal radiographs, reader 1 accepted 91.7% and 52.4%, whereas reader 2 accepted 83.2% and 37.0%, respectively, of AI-generated reports. CONCLUSION. Although AI-generated reports may augment radiologists' diagnostic assessments, the current model requires human oversight, given inferior standalone performance. CLINICAL IMPACT. The generative AI model could have potential application to aid tuberculosis screening programs in medically underserved regions, although technical improvements remain required.

Schlagwörter

MeSH-Schlagwörter (MEDLINE)

Artificial IntelligenceRadiography, ThoracicTuberculosis, PulmonaryRadiographic Image Interpretation, Computer-AssistedHumansRetrospective StudiesFemaleMaleSensitivity and SpecificityMiddle AgedAdultMass ScreeningAgedGenerative Artificial Intelligence

Stichwörter der Autor:innen

artificial intelligencechest radiographgenerative AItuberculosis

Autor:innen und Institutionen

  • Department of Radiology, Mass General Brigham, Brigham & Women's Hospital, 75 Francis St, Boston, MA 02115.
  • Department of Radiology, St. Mary's Hospital, Seoul, South Korea.
  • Department of Radiology, Korea University College of Medicine, Seoul, South Korea.
  • Department of Radiology, Severance Hospital, Seoul, South Korea.
  • SoombitAI, Seoul, South Korea.
  • Kakaobrain, Seoul, South Korea.

Zitieren

APA

Hong, E. K., Kim, H. W., Song, O. K., Lee, K. C., Kim, D. K., Cho, J. B., Kim, J., Lee, S., Bae, W., & Roh, B. (2025). Multimodal Generative Artificial Intelligence Model for Creating Radiology Reports for Chest Radiographs in Patients Undergoing Tuberculosis Screening. American Journal of Roentgenology, 225(4). https://doi.org/10.2214/ajr.25.33059

Vancouver

Hong EK, Kim HW, Song OK, Lee KC, Kim DK, Cho JB, et al. Multimodal Generative Artificial Intelligence Model for Creating Radiology Reports for Chest Radiographs in Patients Undergoing Tuberculosis Screening. American Journal of Roentgenology. 2025;225(4). doi:10.2214/ajr.25.33059

BibTeX
@article{Hong2025,
  author = {Hong, Eun Kyoung and Kim, Hae Won and Song, Ok Kyu and Lee, Kyu-Chong and Kim, Dong Kyu and Cho, Jae-Bock and Kim, Jungbin and Lee, Seungho and Bae, Woong and Roh, Byungseok},
  title = {Multimodal Generative Artificial Intelligence Model for Creating Radiology Reports for Chest Radiographs in Patients Undergoing Tuberculosis Screening},
  journal = {American Journal of Roentgenology},
  year = {2025},
  volume = {225},
  number = {4},
  doi = {10.2214/ajr.25.33059}
}
Kostenlos starten →