EUVIMEDEUVIMED entdecken
Vergleichsstudie

Application of Large Language Models in TN Staging and Treatment Response Evaluation for Patients With Nasopharyngeal Carcinoma: A Comparative Performance Analysis of ChatGPT ‐4o‐Latest and DeepSeek ‐V3‐0324

Yifan Yang iD, Fan Yang, Shengsheng Xiao, Kaiqi Hou, Kexin Chen, Zaiyi Liu iD, Changhong Liang iD, Xiaobo Chen, Guangyi Wang iD

Journal of Magnetic Resonance Imaging · 2025

DOI: 10.1002/jmri.70140 ↗

Kurz gefasst

Vergleichsstudie in der Zeitschrift Journal of Magnetic Resonance Imaging, 2025. Verfasst von Yifan Yang und 8 weiteren Autor:innen. Beteiligte Einrichtung: School of Medicine South China University of Technology, Guangzhou, China. Hauptthemen laut MEDLINE: Nasopharyngeal Carcinoma, Magnetic Resonance Imaging, Nasopharyngeal Neoplasms. Die Arbeit wurde bisher 3-mal zitiert (Crossref) und nennt 18 Literaturangaben. Gefördert von: Beijing Medical Award Foundation, the National Natural Scientific Foundation of China, the Natural Science Foundation of Guangdong Province.

AbstractSchlagwörterBibliografische AngabenZitierenVerwandte Studien

Abstract (Originalsprache)

Background

Accurate tumor staging and treatment response evaluation (TRE) are critical for nasopharyngeal carcinoma (NPC) clinical decisions. Conventional methods relying on manual imaging analysis are expertise‐dependent, time‐consuming, and prone to inter‐observer variability and errors.

Purpose

To assess the performance of two large language models (LLMs): ChatGPT‐4o‐latest and DeepSeek‐V3‐0324 in automating T, N staging and TRE for NPC patients. Study Type Retrospective. Population Three hundred seven NPC patients from three centers (mean age: 45.5 ± 11.3 years; 216 men, 91 women). Field Strength/Sequence All imaging was conducted using 3.0T or 1.5T scanners. The imaging sequence included axial T1‐weighted fast spin‐echo, T2‐weighted fast spin‐echo, T2‐weighted fat‐suppressed spin‐echo, and Contrast‐Enhanced T1‐weighted fast spin‐echo. Assessment Two radiologists established the reference standards for TN staging at baseline and for TRE at two time points: post‐induction chemotherapy (TRE‐1) and post‐concurrent chemoradiotherapy (TRE‐2), based on the 9th version of AJCC/UICC guidelines and the RECIST1.1 criteria. LLMs were via few‐shot chain‐of‐thought prompting and tested on 277 patients with 831 reports. Additionally, four radiologists independently assessed 68 cases both with and without the assistance of LLMs and compared the performance and efficiency in both conditions. Statistical Tests McNemar–Bowker test, Wilcoxon signed–rank test. p < 0.05 was considered statistically significant.

Results

DeepSeek‐V3‐0324 significantly outperformed GPT‐4o‐latest in TRE‐1 staging (96.5% vs. 82.9%, p < 0.001). For T staging (95.3% vs. 93.5%, p = 0.24), N staging (93.8% vs. 89.6%, p = 0.265), and TRE‐2 (94.9% vs. 93.2%, p = 0.556), the accuracy between DeepSeek‐V3‐0324 and ChatGPT‐4o‐latest showed no significant difference. DeepSeek‐V3‐0324 also showed stronger agreement with expert annotation ( κ = 0.85–0.90), compared to ChatGPT‐4o‐latest ( κ = 0.49–0.86). Significant improvements in time efficiency were observed across all radiologists with LLM assistance ( p < 0.001). Data Conclusion LLMs, particularly DeepSeek‐V3‐0324, can automate NPC TN staging and TRE with high accuracy, enhancing clinical efficiency. LLMs integration may improve diagnostic consistency, especially for junior clinicians. Level of Evidence 3. Technical Efficacy Stage 4.

Schlagwörter

MeSH-Schlagwörter (MEDLINE)

Nasopharyngeal CarcinomaMagnetic Resonance ImagingNasopharyngeal NeoplasmsHumansFemaleMaleMiddle AgedNeoplasm StagingRetrospective StudiesAdultTreatment OutcomeReproducibility of ResultsImage Interpretation, Computer-AssistedAgedLarge Language ModelsGenerative Artificial Intelligence

Stichwörter der Autor:innen

large language modelsmagnetic resonance imagingnasopharyngeal carcinoma

Autor:innen und Institutionen

  • School of Medicine South China University of Technology, Guangzhou, China.
  • Guangdong Provincial People's Hospital (Guangdong Academy of Medical Sciences), Southern Medical University, Guangzhou, China.
  • Guangdong Provincial Key Laboratory of Artificial Intelligence in Medical Image Analysis and Application, Guangzhou, China.
  • Guangdong Cardiovascular Institute, Guangdong Provincial People's Hospital, Guangdong Academy of Medical Sciences, Guangzhou, China.

ORCID-Profile: Yifan Yang, Zaiyi Liu, Changhong Liang, Guangyi Wang

Förderung

  • Beijing Medical Award Foundation
  • the National Natural Scientific Foundation of China
  • the Natural Science Foundation of Guangdong Province
  • Natural Science Foundation of Guangdong Province

Zitieren

APA

Yang, Y., Yang, F., Xiao, S., Hou, K., Chen, K., Liu, Z., Liang, C., Chen, X., & Wang, G. (2025). Application of Large Language Models in TN Staging and Treatment Response Evaluation for Patients With Nasopharyngeal Carcinoma: A Comparative Performance Analysis of ChatGPT ‐4o‐Latest and DeepSeek ‐V3‐0324. Journal of Magnetic Resonance Imaging. https://doi.org/10.1002/jmri.70140

Vancouver

Yang Y, Yang F, Xiao S, Hou K, Chen K, Liu Z, et al. Application of Large Language Models in TN Staging and Treatment Response Evaluation for Patients With Nasopharyngeal Carcinoma: A Comparative Performance Analysis of ChatGPT ‐4o‐Latest and DeepSeek ‐V3‐0324. Journal of Magnetic Resonance Imaging. 2025. doi:10.1002/jmri.70140

BibTeX
@article{Yang2025,
  author = {Yang, Yifan and Yang, Fan and Xiao, Shengsheng and Hou, Kaiqi and Chen, Kexin and Liu, Zaiyi and Liang, Changhong and Chen, Xiaobo and Wang, Guangyi},
  title = {Application of Large Language Models in TN Staging and Treatment Response Evaluation for Patients With Nasopharyngeal Carcinoma: A Comparative Performance Analysis of ChatGPT ‐4o‐Latest and DeepSeek ‐V3‐0324},
  journal = {Journal of Magnetic Resonance Imaging},
  year = {2025},
  doi = {10.1002/jmri.70140}
}
Kostenlos starten →