EUVIMEDEUVIMED entdecken
Übersichtsarbeit

Hi ChatGPT, I am a Radiologist, How can you help me?

Davide Bellini, Riccardo Ferrari, Simone Vicini, Marco Rengo, Carlos Leon Saletti, Iacopo Carbone

La radiologia medica · 23.07.2025 · 130 (8) · 1221-1230

DOI: 10.1007/s11547-025-02053-4 ↗

Kurz gefasst

Übersichtsarbeit in der Zeitschrift La radiologia medica, online erschienen am 23.07.2025. Verfasst von Davide Bellini und 5 weiteren Autor:innen. Beteiligte Einrichtung: Academic Diagnostic Imaging Division - I.C.O.T. Hospital, Department of Medical-Surgical Sciences and Biotechnologies, Faculty of Pharmacy and Medici…. Hauptthemen laut MEDLINE: Radiologists, Machine Learning, Radiology, Radiology Information Systems. Die Arbeit wurde bisher 3-mal zitiert (Crossref) und nennt 27 Literaturangaben.

AbstractSchlagwörterBibliografische AngabenZitierenVerwandte Studien

Abstract (Originalsprache)

This review paper explores the integration of ChatGPT, a generative AI model developed by OpenAI, into radiological practices, focusing on its potential to enhance the operational efficiency of radiologists. ChatGPT operates on the GPT architecture, utilizing advanced machine learning techniques, including unsupervised pre-training and reinforcement learning, to generate human-like text responses. While AI applications in radiology predominantly focus on imaging acquisition, reconstruction, and interpretation-commonly embedded directly within hardware-the accessibility and functional breadth of ChatGPT make it a unique tool. This interview-based review should not be intended as a detailed evaluation of all ChatGPT features. Instead, it aims to test its utility in everyday radiological tasks through real-world examples. ChatGPT demonstrated strong capabilities in structuring radiology reports according to international guidelines (e.g., PI-RADS, CT reporting for diverticulitis), designing a complete research protocol, and performing advanced statistical analysis from Excel datasets, including ROC curve generation and intergroup comparison. Although not capable of directly interpreting DICOM images, ChatGPT provided meaningful assistance in image post-processing and interpretation when images were converted to standard formats. These findings highlight its current strengths and limitations as a supportive tool for radiologists.

Schlagwörter

MeSH-Schlagwörter (MEDLINE)

RadiologistsMachine LearningRadiologyRadiology Information SystemsArtificial IntelligenceHumansGenerative Artificial Intelligence

Stichwörter der Autor:innen

Artificial intelligenceChatGPT applicationsMedical imagingRadiology workflow

Autor:innen und Institutionen

  • Academic Diagnostic Imaging Division - I.C.O.T. Hospital, Department of Medical-Surgical Sciences and Biotechnologies, Faculty of Pharmacy and Medicine, University of Rome "Sapienza", Via F. Faggiana 1668, 04100, Latina…
  • Department of Emergency Radiology, Azienda Ospedaliera S. Camillo-Forlanini, Rome, Italy.

Zitieren

APA

Bellini, D., Ferrari, R., Vicini, S., Rengo, M., Saletti, C. L., & Carbone, I. (2025). Hi ChatGPT, I am a Radiologist, How can you help me?. La radiologia medica, 130(8), 1221-1230. https://doi.org/10.1007/s11547-025-02053-4

Vancouver

Bellini D, Ferrari R, Vicini S, Rengo M, Saletti CL, Carbone I. Hi ChatGPT, I am a Radiologist, How can you help me?. La radiologia medica. 2025;130(8):1221-1230. doi:10.1007/s11547-025-02053-4

BibTeX
@article{Bellini2025,
  author = {Bellini, Davide and Ferrari, Riccardo and Vicini, Simone and Rengo, Marco and Saletti, Carlos Leon and Carbone, Iacopo},
  title = {Hi ChatGPT, I am a Radiologist, How can you help me?},
  journal = {La radiologia medica},
  year = {2025},
  volume = {130},
  number = {8},
  pages = {1221--1230},
  doi = {10.1007/s11547-025-02053-4}
}
Kostenlos starten →