Large Language Models for Cardiac MRI Diagnosis Based on Standardized Text Descriptions
Journal of Magnetic Resonance Imaging · 2026-07 · 64 (1) · 153-165
DOI: 10.1002/jmri.70327 ↗Kurz gefasst
Fachartikel in der Zeitschrift Journal of Magnetic Resonance Imaging, online erschienen am 23.04.2026. Verfasst von Hongbo Zhang und 9 weiteren Autor:innen. Beteiligte Einrichtung: Department of Interventional Diagnosis and Treatment, Beijing Anzhen Hospital Affiliated to Capital Medical University, Beijing, China. Hauptthemen laut MEDLINE: Large Language Models, Magnetic Resonance Imaging, Heart Diseases, Image Interpretation, Computer-Assisted. Die Arbeit wurde bisher 3-mal zitiert (Crossref) und nennt 36 Literaturangaben. Gefördert von: National Natural Science Foundation of China, National Key Research and Development Program of China.
Abstract (Originalsprache)
Background
MRI is important for cardiac disease evaluation, but accurate diagnosis remains challenging in less experienced centers. Although large language models (LLMs) have shown promise in medical imaging diagnosis, their application in cardiac MRI is limited. Hypothesis LLMs may be effective in achieving cardiac MRI diagnosis based on standardized descriptions. Study Type Retrospective. Population A total of 203 hypertrophic cardiomyopathy, 186 dilated cardiomyopathy, 46 hypertensive heart disease, 198 ischemic cardiomyopathy, 38 constrictive pericarditis, 45 cardiac amyloidosis, 91 myocarditis, and 144 normal controls. Field Strength/Sequences Balanced steady‐state free‐precession, short tau inversion recovery, and breath‐hold inversion‐recovery segmented gradient‐echo sequences at 3.0 T. Assessment Clinical and cardiac MRI information from each subject was converted into standardized descriptions and input into Generative Pre‐trained Transformer‐4.5 (GPT‐4.5), GPT‐4 Omni (GPT‐4o), Deepseek‐V3, and Deepseek‐R1 LLMs. Cardiac MRI information included LV function, wall thickness and motion, and abnormalities on T2WI, perfusion and late gadolinium enhancement sequences. Each model was asked to generate an imaging diagnosis. In addition, a medical student (8 months experience) and three radiologists (junior, mid‐level and senior: with 3, 6, and 10 years' experience, respectively) provided diagnoses based on cardiac MRI images and clinical information. Statistic Tests Frequency‐weighted sensitivity and specificity were calculated. The diagnostic performances of the LLMs and human readers were compared using the McNemar test with Bonferroni correction. A p value < 0.05 was considered significant.
Results
All LLMs showed excellent frequency‐weighted specificity (0.973–0.983). The frequency‐weighted sensitivities of all LLMs were not significantly different from that of the junior radiologist, were significantly higher than that of the medical student, and significantly inferior to those of the senior radiologist (GPT‐4.5: 0.863, GPT‐4o: 0.821, Deepseek‐V3: 0.843, and Deepseek‐R1: 0.851 vs. junior radiologist: 0.850, all adjusted p = 1.000; vs. medical student: 0.731, all adjusted p < 0.001; vs. senior radiologist: 0.942, all adjusted p < 0.001). Additionally, the mid‐level radiologist achieved a frequency‐weighted sensitivity of 0.895, outperforming all LLMs except GPT‐4.5. Data Conclusion LLMs may generate accurate diagnoses from standardized cardiac MRI descriptions, potentially benefiting less experienced physicians. Level of Evidence 4. Technical Efficacy Stage 5.
Schlagwörter
MeSH-Schlagwörter (MEDLINE)
Stichwörter der Autor:innen
Autor:innen und Institutionen
- Department of Interventional Diagnosis and Treatment, Beijing Anzhen Hospital Affiliated to Capital Medical University, Beijing, China.
- Department of Radiology, Beijing Anzhen Hospital Affiliated to Capital Medical University, Beijing, China.
- Capital Medical University, Beijing, China.
ORCID-Profile: Hongbo Zhang, Guanyu Lu, Lei Zhao, Xiaohai Ma
Förderung
- National Natural Science Foundation of China
- National Key Research and Development Program of China
Zitieren
APA
Zhang, H., Zhou, J., Zhang, C., Lu, G., Lu, Z., Wang, L., Wang, L., Gong, H., Zhao, L., & Ma, X. (2026). Large Language Models for Cardiac MRI Diagnosis Based on Standardized Text Descriptions. Journal of Magnetic Resonance Imaging, 64(1), 153-165. https://doi.org/10.1002/jmri.70327
Vancouver
Zhang H, Zhou J, Zhang C, Lu G, Lu Z, Wang L, et al. Large Language Models for Cardiac MRI Diagnosis Based on Standardized Text Descriptions. Journal of Magnetic Resonance Imaging. 2026;64(1):153-165. doi:10.1002/jmri.70327
BibTeX
@article{Zhang2026,
author = {Zhang, Hongbo and Zhou, Junjie and Zhang, Chen and Lu, Guanyu and Lu, Zhihui and Wang, Lanling and Wang, Lili and Gong, Huiwen and Zhao, Lei and Ma, Xiaohai},
title = {Large Language Models for Cardiac MRI Diagnosis Based on Standardized Text Descriptions},
journal = {Journal of Magnetic Resonance Imaging},
year = {2026},
volume = {64},
number = {1},
pages = {153--165},
doi = {10.1002/jmri.70327}
}
EUVIMED