Multicenter Study of Multimodal MRI Radiomics and Deep Learning-Based Segmentation for Predicting Local Recurrence of Nasopharyngeal Carcinoma.
Simple Summary: Predicting local recurrence in nasopharyngeal carcinoma (NPC) remains challenging using standard imaging assessment alone. This study developed and externally validated a prognostic framework using multimodal MRI radiomics based on expert-reviewed tumor regions and supplemented this...
| Publicado en: | Cancers Vol. 18; no. 8; pp. 1265 - 1281 |
|---|---|
| Autores principales: | , , , , , |
| Formato: | diagnostic images research tables/charts Journal Article |
| Publicado: |
MDPI
Apr2026
|
| Acceso en línea: | Ver este registro en EBSCOhost |
| fields | @attributes: recordID: 1 pdfLink: plink: https://search.ebscohost.com/login.aspx?direct=true&db=ccm&AN=193441310&site=ehost-live header: @attributes: shortDbName: ccm uiTerm: 193441310 longDbName: CINAHL Complete uiTag: AN controlInfo: bkinfo: dissinfo: jinfo: jid: 20726694 B74B jtl: Cancers issn: 20726694 maglogo: N pubinfo: dt: Apr2026 vid: 18 iid: 8 pid: 97109 pub: MDPI artinfo: ui: 193441310 193441310 193441310 10.3390/cancers18081265 193441310 ppf: 1265 ppct: 16 formats: tig: atl: Multicenter Study of Multimodal MRI Radiomics and Deep Learning-Based Segmentation for Predicting Local Recurrence of Nasopharyngeal Carcinoma. aug: au: Yao, Dongfang Lai, Yongjing Bin, Xiang Li, Jingyu Chen, Biaoyou Tang, Anzhou affil: Department of Otolaryngology–Head and Neck Surgery, The First Affiliated Hospital of Guangxi Medical University, Nanning 530021, China sug: subj: Nasopharyngeal Carcinoma Prognosis Neoplasm Recurrence, Local Prognosis Magnetic Resonance Imaging Radiomics Deep Learning Prediction Models Human Multicenter Studies Prospective Studies Retrospective Design Record Review Boosting Machine Learning Algorithms Sensitivity and Specificity Automation Machine Learning Descriptive Statistics Pearson's Correlation Coefficient Predictive Value of Tests Data Analysis Software McNemar's Test Image Processing, Computer Assisted Chi Square Test Fisher's Exact Test Mann-Whitney U Test T-Tests Funding Source ab: Simple Summary: Predicting local recurrence in nasopharyngeal carcinoma (NPC) remains challenging using standard imaging assessment alone. This study developed and externally validated a prognostic framework using multimodal MRI radiomics based on expert-reviewed tumor regions and supplemented this by evaluating an automated deep learning tumor segmentation pipeline to enhance recurrence risk evaluation. Analyzing data from 1074 patients across two clinical centers, we found that integrating T1-weighted, T2-weighted, and contrast-enhanced MRI signals captures complementary features of intratumoral heterogeneity. While the deep learning segmentation module demonstrated consistent but moderate overlap with expert contours (reflecting the complex infiltrative boundaries of NPC), the derived prognostic model achieved high discriminative performance in an independent external validation cohort (AUC: 0.910). The multimodal model showed numerical improvement over single-sequence approaches, suggesting that fusing diverse imaging signals provides a more comprehensive assessment of individual recurrence risk. This objective tool may support personalized surveillance planning and prospective clinical decision-making for NPC patients. Background/Objectives: We developed and validated a multimodal magnetic resonance imaging (MRI) framework combining deep learning segmentation with radiomics to predict local recurrence in nasopharyngeal carcinoma (NPC). Methods: This retrospective two-center study included 1074 NPC patients treated between 2015 and 2019. Center 1 cases were split 8:2 into training and internal test sets, while Center 2 served for external validation. A multimodal Swin UNet model automatically segmented tumors from pretreatment T1-weighted, T2-weighted, and contrast-enhanced T1 (CET1) images. Radiomics features were extracted from expert-reviewed regions of interest, selected, and modeled using extreme gradient boosting for recurrence prediction. Results: The multimodal segmentation model maintained consistent but moderate Dice similarity coefficients (0.737, 0.666, and 0.726 for T1WI, T2WI, and CET1 in external validation). These values reflect the moderate overlap typical for nasopharyngeal carcinoma, given its highly infiltrative growth and ill-defined boundaries along complex anatomic interfaces. For local recurrence prediction, single-modality models reached external AUCs between 0.754 and 0.781. Importantly, the multimodal fusion model demonstrated numerical improvement over single modalities in the external validation set (e.g., vs. T1WI, p = 0.141), achieving an AUC of 0.910, accuracy of 0.908, sensitivity of 0.805, specificity of 0.946, and F1-score of 0.825. Conclusions: The multimodal MRI radiomics model, developed alongside a deep learning segmentation module, demonstrated favorable multicenter performance for evaluating NPC recurrence risk. The primary prognostic analysis was based on expert-reviewed regions of interest; a supplementary analysis using fully automatic segmentation masks yielded comparable, non-significantly different performance across all cohorts (Training AUC: 0.887; Internal Test AUC: 0.892; External Validation AUC: 0.885 vs. 0.910, p = 0.145), supporting the feasibility of future end-to-end deployment. Fusing multimodal features yielded numerical improvements over single-sequence models in external validation, providing a basis for post-treatment surveillance planning. pubtype: Academic Journal doctype: diagnostic images research tables/charts Journal Article ougenre: Article language: English refInfo: holdings: @attributes: islocal: N |
|---|