Integrating Text and Image Analysis: Exploring GPT-4V’s Capabilities in Advanced Radiological Applications Across Subspecialties

Felix Busch; Tianyu Han; Marcus R. Makowski; Daniel Truhn; Keno K. Bressem; Lisa Adams

doi:10.2196/54948

Integrating Text and Image Analysis: Exploring GPT-4V’s Capabilities in Advanced Radiological Applications Across Subspecialties

Felix Busch, Tianyu Han, Marcus R. Makowski, Daniel Truhn, Keno K. Bressem, Lisa Adams

Chair of Radiology

Research output: Contribution to journal › Article › peer-review

3 Scopus citations

Abstract

This study demonstrates that GPT-4V outperforms GPT-4 across radiology subspecialties in analyzing 207 cases with 1312 images from the Radiological Society of North America Case Collection.

Original language	English
Article number	e54948
Journal	Journal of Medical Internet Research
Volume	26
DOIs	https://doi.org/10.2196/54948
State	Published - 2024

Keywords

AI applications in medicine
ChatGPT
GPT-4
Generative Pre-Trained Transformer
artificial intelligence
clinical decision support systems
diagnostic radiology
generative AI
medical image analysis
multimodal large language models

Access to Document

10.2196/54948

Cite this

@article{a51aa2ea9f9045c3a51d1528bbba6e74,

title = "Integrating Text and Image Analysis: Exploring GPT-4V{\textquoteright}s Capabilities in Advanced Radiological Applications Across Subspecialties",

abstract = "This study demonstrates that GPT-4V outperforms GPT-4 across radiology subspecialties in analyzing 207 cases with 1312 images from the Radiological Society of North America Case Collection.",

keywords = "AI applications in medicine, ChatGPT, GPT-4, Generative Pre-Trained Transformer, artificial intelligence, clinical decision support systems, diagnostic radiology, generative AI, medical image analysis, multimodal large language models",

author = "Felix Busch and Tianyu Han and Makowski, {Marcus R.} and Daniel Truhn and Bressem, {Keno K.} and Lisa Adams",

year = "2024",

doi = "10.2196/54948",

language = "English",

volume = "26",

journal = "Journal of Medical Internet Research",

issn = "1438-8871",

publisher = "JMIR Publications Inc.",

}

TY - JOUR

T1 - Integrating Text and Image Analysis

T2 - Exploring GPT-4V’s Capabilities in Advanced Radiological Applications Across Subspecialties

AU - Busch, Felix

AU - Han, Tianyu

AU - Makowski, Marcus R.

AU - Truhn, Daniel

AU - Bressem, Keno K.

AU - Adams, Lisa

PY - 2024

Y1 - 2024

N2 - This study demonstrates that GPT-4V outperforms GPT-4 across radiology subspecialties in analyzing 207 cases with 1312 images from the Radiological Society of North America Case Collection.

AB - This study demonstrates that GPT-4V outperforms GPT-4 across radiology subspecialties in analyzing 207 cases with 1312 images from the Radiological Society of North America Case Collection.

KW - AI applications in medicine

KW - ChatGPT

KW - GPT-4

KW - Generative Pre-Trained Transformer

KW - artificial intelligence

KW - clinical decision support systems

KW - diagnostic radiology

KW - generative AI

KW - medical image analysis

KW - multimodal large language models

UR - http://www.scopus.com/inward/record.url?scp=85192042066&partnerID=8YFLogxK

U2 - 10.2196/54948

DO - 10.2196/54948

M3 - Article

C2 - 38691404

AN - SCOPUS:85192042066

SN - 1438-8871

VL - 26

JO - Journal of Medical Internet Research

JF - Journal of Medical Internet Research

M1 - e54948

ER -

Integrating Text and Image Analysis: Exploring GPT-4V’s Capabilities in Advanced Radiological Applications Across Subspecialties

Abstract

Keywords

Access to Document

Other files and links

Fingerprint

Cite this