EUVIMEDEUVIMED entdecken
Crossref

MedNext-Insight Model for Automated Metabolic Tumor Volume Delineation on Computed Tomography and Prognostic Value in Nasopharyngeal Carcinoma

Meng-Yu Hao, Yu-Xi Xiong, Yu Li, Zi-Jie Mo, Chen-Yang Feng, Jiang Hu, Su-Man Zhang, Yu-Xian Yang, Le-Cheng Jia, Hua Li, Yi-Da He, Xiao-Qing Sun und 3 weitere

International Journal of Radiation Oncology*Biology*Physics · 2026

DOI: 10.1016/j.ijrobp.2026.05.005 ↗

Kurz gefasst

Fachartikel in der Zeitschrift International Journal of Radiation Oncology*Biology*Physics, 2026. Verfasst von Meng-Yu Hao und 14 weiteren Autor:innen. Beteiligte Einrichtung: Department of Radiation Oncology, State Key Laboratory of Oncology in South China, Guangdong Key Laboratory of Nasopharyngeal Carcinoma Diagnosis and…. Hauptthemen laut MEDLINE: Tumor Burden, Nasopharyngeal Neoplasms, Nasopharyngeal Carcinoma, Deep Learning. Die Arbeit nennt 48 Literaturangaben. Gefördert von: Guangzhou Science and Technology Program Key Projects, Guangzhou Municipal Health Commission, Sun Yat-sen University Cancer Center.

AbstractSchlagwörterBibliografische AngabenZitierenVerwandte Studien

Abstract (Originalsprache)

PURPOSES: To develop a deep learning model for automated metabolic tumor volume (MTV) delineation on routine computed tomography (CT) without positron emission tomography (PET) and to validate its prognostic value in nasopharyngeal carcinoma (NPC). METHODS AND MATERIALS: A retrospective cohort of 392 patients with NPC undergoing pre-radiotherapy 2-deoxy-2-[fluorine-18]fluoro-D-glucose PET/CT in 2021 was enrolled and randomly divided into training (n = 314, including 63 for validation) and test (n = 78) cohorts. Ground-truth MTV (GT_MTV) was generated from PET-registered CT using standardized uptake value SUV > 2.5 within the primary gross tumor volume. A 7-layer MedNext-Insight model with dual-window CT inputs and Dice-Focal loss was trained to predict MTV using CT alone. Segmentation performance was compared with no-new-U-Net version 2 (nnUNetV2), Conditional Generative Adversarial Network for Image-to-Image Translation (Pix2Pix), and three-dimensional Cycle-Consistent Generative Adversarial Network (3D-CycleGAN) p rimarily using Dice Similarity Coefficient and sensitivity. Radiomic features were extracted from predicted MTV (Pred_MTV) and GT_MTV to construct Cox proportional hazards models for event-free survival, evaluated by concordance index (C-index). Robustness was further assessed in an internal temporal validation cohort from 2022 with different scanners (n = 135) using planning CT as the sole input. RESULTS: MedNext-Insight achieved the highest MTV delineation Dice Similarity Coefficient (Mean ± SD, 0.808 ± 0.110 vs 0.740-0.782; all P < .05) with improved sensitivity. After excluding 12 patients with baseline distant metastasis from event-free survival analysis, Pred_MTV-derived radiomics showed strong reproducibility (median intraclass correlation coefficient, 0.816) and comparable prognostic performance to GT_MTV (C-index [95% CI], 0.712 [0.516-0.899] vs 0.744 [0.601-0.884]; P = .730). MTV-based radiomics outperformed primary gross tumor volume-derived features, particularly when combined with clinical variables (C-index, 0.809 [0.678-0.919]). In the internal temporal validation cohort, CT-only Pred_MTV maintained stable segmentation accuracy and prognostic discrimination (log-rank test, P < .05). CONCLUSION: MedNext-Insight enables accurate PET-free MTV delineation on routine CT with prognostic value, supporting a resource-efficient approach for risk stratification and informing potential future biology-guided adaptive radiation therapy in NPC.

Schlagwörter

MeSH-Schlagwörter (MEDLINE)

Tumor BurdenNasopharyngeal NeoplasmsNasopharyngeal CarcinomaDeep LearningTomography, X-Ray ComputedPositron Emission Tomography Computed TomographyHumansPrognosisRetrospective StudiesFluorodeoxyglucose F18Middle AgedFemaleAdultAgedGenerative Adversarial NetworksRadiopharmaceuticals

Substanzen

Fluorodeoxyglucose F18Radiopharmaceuticals

Autor:innen und Institutionen

  • Department of Radiation Oncology, State Key Laboratory of Oncology in South China, Guangdong Key Laboratory of Nasopharyngeal Carcinoma Diagnosis and Therapy, Guangdong Provincial Clinical Research Center for Cancer, Su…
  • Shanghai United Imaging Healthcare Co., Ltd. Shanghai, China.
  • Information Technology Center, State Key Laboratory of Oncology in South China, Guangdong Provincial Clinical Research Center for Cancer, Sun Yat-sen University Cancer Center, Guangzhou, 510060, China.
  • Department of Oncology, The Eighth Affiliated Hospital of Sun Yat-sen University, Shenzhen, China.

Förderung

  • Guangzhou Science and Technology Program Key Projects
  • Guangzhou Municipal Health Commission
  • Sun Yat-sen University Cancer Center
  • Fundamental Research Funds for the Central Universities
  • National Natural Science Foundation of China

Zitieren

APA

Hao, M. Y., Xiong, Y. X., Li, Y., Mo, Z. J., Feng, C. Y., Hu, J., Zhang, S. M., Yang, Y. X., Jia, L. C., Li, H., He, Y. D., Sun, X. Q., Xu, S., Zhou, G. Q., & Sun, Y. (2026). MedNext-Insight Model for Automated Metabolic Tumor Volume Delineation on Computed Tomography and Prognostic Value in Nasopharyngeal Carcinoma. International Journal of Radiation Oncology*Biology*Physics. https://doi.org/10.1016/j.ijrobp.2026.05.005

Vancouver

Hao MY, Xiong YX, Li Y, Mo ZJ, Feng CY, Hu J, et al. MedNext-Insight Model for Automated Metabolic Tumor Volume Delineation on Computed Tomography and Prognostic Value in Nasopharyngeal Carcinoma. International Journal of Radiation Oncology*Biology*Physics. 2026. doi:10.1016/j.ijrobp.2026.05.005

BibTeX
@article{Hao2026,
  author = {Hao, Meng-Yu and Xiong, Yu-Xi and Li, Yu and Mo, Zi-Jie and Feng, Chen-Yang and Hu, Jiang and Zhang, Su-Man and Yang, Yu-Xian and Jia, Le-Cheng and Li, Hua and He, Yi-Da and Sun, Xiao-Qing and Xu, Sha and Zhou, Guan-Qun and Sun, Ying},
  title = {MedNext-Insight Model for Automated Metabolic Tumor Volume Delineation on Computed Tomography and Prognostic Value in Nasopharyngeal Carcinoma},
  journal = {International Journal of Radiation Oncology*Biology*Physics},
  year = {2026},
  doi = {10.1016/j.ijrobp.2026.05.005}
}
Kostenlos starten →