EUVIMEDEUVIMED entdecken
Crossref

Exploring chat generated pre-trained transformer-3 ability to interpret MRI knee images and generate reports

Sonal Saran, Kapil Shirodkar, Sisith Ariyaratne, Karthikeyan Iyengar, Nathan Jenko, B. K. Durgaprasad, Rajesh Botchu

Journal of Arthroscopic Surgery and Sports Medicine · 2024

DOI: 10.25259/jassm_16_2024 ↗

Kurz gefasst

Fachartikel in der Zeitschrift Journal of Arthroscopic Surgery and Sports Medicine, 2024. Verfasst von Sonal Saran und 6 weiteren Autor:innen. Die Arbeit wurde bisher 2-mal zitiert (Crossref) und nennt 10 Literaturangaben.

AbstractBibliografische AngabenZitierenVerwandte Studien

Abstract (Originalsprache)

Objectives

The study’s objective was to determine if Chat Generated Pre-Trained Transformer-3 (ChatGPT)-4V can interpret magnetic resonance imaging (MRI) knees and generate preliminary reports based on images and clinical history provided by the radiologist. Materials and Methods: This cross-sectional observational study involved selecting 10 MRI knees with representative imaging findings from the institution’s radiology reporting database. Key MRI images were then input into the ChatGPT-4V model, which was queried with four questions: (i) What does the image show?; (ii) What is the sequence?; (iii) What is the key finding?; and, (iv) Finally, the model generated a report based on the provided clinical history and key finding. Responses from ChatGPT-4 were documented and independently evaluated by two musculoskeletal radiologists through Likert scoring.

Results

The mean scores for various questions in the assessment were as follows: 2 for “What does the image show?,” 2.10 for “What is the sequence?,” 1.15 for “What is the key finding?,” and the highest mean score of 4.10 for the command “Write a report of MRI of the…” Radiologists consistently gave mean scores ranging from 2.0 to 2.5 per case, with no significant differences observed between different cases ( P > 0.05). The interclass correlation coefficient between the two raters was 0.92 (95% Confidence interval: 0.85–0.96).

Conclusion

ChatGPT-4V excelled in generating reports based on user-fed clinical information and key findings, with a mean score of 4.10 (good to excellent proficiency). However, its performance in interpreting medical images was subpar, scoring ≤2.10. ChatGPT-4V, as of now, cannot interpret medical images accurately and generate reports.

Zitieren

APA

Saran, S., Shirodkar, K., Ariyaratne, S., Iyengar, K., Jenko, N., Durgaprasad, B. K., & Botchu, R. (2024). Exploring chat generated pre-trained transformer-3 ability to interpret MRI knee images and generate reports. Journal of Arthroscopic Surgery and Sports Medicine. https://doi.org/10.25259/jassm_16_2024

Vancouver

Saran S, Shirodkar K, Ariyaratne S, Iyengar K, Jenko N, Durgaprasad BK, et al. Exploring chat generated pre-trained transformer-3 ability to interpret MRI knee images and generate reports. Journal of Arthroscopic Surgery and Sports Medicine. 2024. doi:10.25259/jassm_16_2024

BibTeX
@article{Saran2024,
  author = {Saran, Sonal and Shirodkar, Kapil and Ariyaratne, Sisith and Iyengar, Karthikeyan and Jenko, Nathan and Durgaprasad, B. K. and Botchu, Rajesh},
  title = {Exploring chat generated pre-trained transformer-3 ability to interpret MRI knee images and generate reports},
  journal = {Journal of Arthroscopic Surgery and Sports Medicine},
  year = {2024},
  doi = {10.25259/jassm_16_2024}
}
Kostenlos starten →