Back to all papers

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

May 16, 2026pubmed logopapers

Authors

Hao MY,Xiong YX,Mo ZJ,Feng CY,Hu J,Zhang SM,Yang YX,Jia LC,Li H,Da He Y,Sun XQ,Zhou GQ,Sun Y

Affiliations (6)

  • State Key Laboratory of Oncology in South China, Guangdong Key Laboratory of Nasopharyngeal Carcinoma Diagnosis and Therapy, Guangdong Provincial Clinical Research Center for Cancer, Sun Yat-sen University Cancer Center, Guangzhou 510060, P. R. China; Zhongshan School of Medicine, Sun Yat-sen University, Guangzhou, 510060, China. Electronic address: [email protected].
  • State Key Laboratory of Oncology in South China, Guangdong Key Laboratory of Nasopharyngeal Carcinoma Diagnosis and Therapy, Guangdong Provincial Clinical Research Center for Cancer, Sun Yat-sen University Cancer Center, Guangzhou 510060, P. R. China.
  • Shanghai United Imaging Healthcare Co., Ltd. Shanghai, 201807, China.
  • State Key Laboratory of Oncology in South China, Guangdong Key Laboratory of Nasopharyngeal Carcinoma Diagnosis and Therapy, Guangdong Provincial Clinical Research Center for Cancer, Sun Yat-sen University Cancer Center, Guangzhou 510060, P. R. China; Zhongshan School of Medicine, Sun Yat-sen University, Guangzhou, 510060, China.
  • State Key Laboratory of Oncology in South China, Guangdong Key Laboratory of Nasopharyngeal Carcinoma Diagnosis and Therapy, Guangdong Provincial Clinical Research Center for Cancer, Sun Yat-sen University Cancer Center, Guangzhou 510060, P. R. China. Electronic address: [email protected].
  • State Key Laboratory of Oncology in South China, Guangdong Key Laboratory of Nasopharyngeal Carcinoma Diagnosis and Therapy, Guangdong Provincial Clinical Research Center for Cancer, Sun Yat-sen University Cancer Center, Guangzhou 510060, P. R. China. Electronic address: [email protected].

Abstract

To develop a deep learning model for automated metabolic tumor volume (MTV) delineation on routine computed tomography (CT) without positron emission tomography (PET) and validate its prognostic value in nasopharyngeal carcinoma (NPC). A retrospective cohort of 392 NPC patients undergoing pre-radiotherapy <sup>18</sup>F-FDG 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 (GTVp). A seven-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 nnUNetV2, Pix2Pix, and 3D-CycleGAN primarily using Dice similarity coefficient (DSC) and sensitivity. Radiomic features were extracted from predicted MTV (Pred_MTV) and GT_MTV to construct Cox proportional hazards models for event-free survival (EFS), 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. MedNext-Insight achieved the highest MTV delineation DSC (Mean ± SD: 0.808 ± 0.110 versus 0.740-0.782, all P < 0.05) with improved sensitivity. After excluding 12 patients with baseline distant metastasis from EFS 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 = 0.730). MTV-based radiomics outperformed GTVp-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 < 0.05). 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 radiotherapy in NPC.

Topics

Journal Article

Ready to Sharpen Your Edge?

Subscribe to join 11k+ peers who rely on RadAI Slice. Get the essential weekly briefing that empowers you to navigate the future of radiology.

We respect your privacy. Unsubscribe at any time.