EUVIMEDEUVIMED entdecken
Open Access · CC BY 4.0

Investigation of clinical applicability of deep learning-based virtual contrast-enhanced MRI for nasopharyngeal carcinoma patients

Guangping Zeng, Wen Li, Xue Li, Rui Sun, Saikit Lam, Tianyu Xiong, Ho-Yin Cheung, Ho-Fun Lee, Kar-Ho Lee, Lai-Yin Cheung, Chenbin Liu, Zhou Liu und 2 weitere

Frontiers in Oncology · 14.08.2026 · 16

DOI: 10.3389/fonc.2026.1859909 ↗

Kurz gefasst

Fachartikel in der Zeitschrift Frontiers in Oncology, online erschienen am 14.08.2026. Verfasst von Guangping Zeng und 13 weiteren Autor:innen. Beteiligte Einrichtung: Department of Radiation Oncology, Jinshazhou Hospital of Guangzhou University of Chinese Medicine, Guangzhou, China. Die Arbeit nennt 40 Literaturangaben. Der Volltext ist frei zugänglich (Open Access, CC BY 4.0).

AbstractSchlagwörterBibliografische AngabenZitierenVerwandte Studien

Abstract (Originalsprache)

Purpose

There is a lack of research evaluating the clinical performance of virtual contrast-enhanced MRI (VCE-MRI). This study aims to assess the clinical utility of an established VCE-MRI technique in NPC patients and to establish patient selection criteria. Materials and methods We retrospectively collected data from 333 NPC patients across six institutions (2012-2023). VCE-MRI was synthesized from T1-weighted and T2-weighted MRI for each patient using the multimodality-guided synergistic neural network (MMgSN-Net), which was pre-trained on a large cohort of 1682 NPC patients from 14 institutions. Three experienced radiologists independently assessed image quality using a 5-point Likert scale, with scores below 4 deemed clinically unacceptable. The association between assessment results and patient clinical characteristics of corresponding patients (tumor diameter, T-stage, shape, gender, age) was analyzed to stratify the patients suitable for MMgSN-Net-based VCE-MRI.

Results

Clinically acceptability of VCE-MRI significantly decreased with larger tumor diameters (p=0.001), advanced T-stage (T1: 100%, T2: 95.1%, T3: 90.0%, T4: 69.6%; p<0.001), and complex tumor shape (regular: 94.8% vs. complex: 74.0%; p<0.001). Age and gender had no significant impact (p=0.327, 0.773). 13 unacceptable patients were found due to severe VCE-MRI artifacts. VCE-MRI achieved high clinical acceptability in T1/T2 patients (109/114, 95.6%) and T3/T4 patients with regular tumor shapes (115/120, 95.8%). In contrast, acceptability significantly decreased to 73.0% (65/89) for T3/T4 tumors with complex shapes. The T-staging result discordance rate between VCE-MRI and CE-MRI is 8.4%, with overstaging in 15 cases.

Conclusion

MMgSN-Net-based VCE-MRI demonstrates favorable clinical feasibility in selected patient subgroups, T1/T2-stage NPC and T3/T4-stage NPC with regular tumor morphology, potentially reducing GBCAs administration in 67.3% of eligible patients when applying these stratification criteria.

Schlagwörter

Stichwörter der Autor:innen

clinical applicabilitydeep learningnasopharyngeal carcinomapatient stratificationvirtual contrast-enhanced MRI

Autor:innen und Institutionen

  • Department of Radiation Oncology, Jinshazhou Hospital of Guangzhou University of Chinese Medicine, Guangzhou, China.
  • Department of Health Technology and Informatics, The Hong Kong Polytechnic University, Hong Kong, Hong Kong SAR, China.
  • Guangyuan Central Hospital, Guangyuan, Sichuan, China.
  • Chongqing University Cancer Hospital, Chongqing, China.
  • Department of Biomedical Engineering, The Hong Kong Polytechnic University, Hong Kong, Hong Kong SAR, China.
  • Radiotherapy and Oncology Centre, Hong Kong Baptist Hospital, Hong Kong, Hong Kong SAR, China.

Zitieren

APA

Zeng, G., Li, W., Li, X., Sun, R., Lam, S., Xiong, T., Cheung, H. Y., Lee, H. F., Lee, K. H., Cheung, L. Y., Liu, C., Liu, Z., Wei, X., & Cai, J. (2026). Investigation of clinical applicability of deep learning-based virtual contrast-enhanced MRI for nasopharyngeal carcinoma patients. Frontiers in Oncology, 16. https://doi.org/10.3389/fonc.2026.1859909

Vancouver

Zeng G, Li W, Li X, Sun R, Lam S, Xiong T, et al. Investigation of clinical applicability of deep learning-based virtual contrast-enhanced MRI for nasopharyngeal carcinoma patients. Frontiers in Oncology. 2026;16. doi:10.3389/fonc.2026.1859909

BibTeX
@article{Zeng2026,
  author = {Zeng, Guangping and Li, Wen and Li, Xue and Sun, Rui and Lam, Saikit and Xiong, Tianyu and Cheung, Ho-Yin and Lee, Ho-Fun and Lee, Kar-Ho and Cheung, Lai-Yin and Liu, Chenbin and Liu, Zhou and Wei, Xiaping and Cai, Jing},
  title = {Investigation of clinical applicability of deep learning-based virtual contrast-enhanced MRI for nasopharyngeal carcinoma patients},
  journal = {Frontiers in Oncology},
  year = {2026},
  volume = {16},
  doi = {10.3389/fonc.2026.1859909}
}
Kostenlos starten →