Search research articles

ABOUT JoVE

Overview Leadership Blog JoVE Help Center

AUTHORS

Publishing Process Editorial Board Scope & Policies Peer Review FAQ Submit

LIBRARIANS

Testimonials Subscriptions Access Resources Library Advisory Board FAQ

RESEARCH

JoVE Journal Methods Collections JoVE Encyclopedia of Experiments Archive

EDUCATION

JoVE Core JoVE Business JoVE Science Education JoVE Lab Manual Faculty Resource Center Faculty Site

Terms & Conditions of Use

Related Concept Videos

You might also read

Related Articles

Articles linked to this work by shared authors, journal, and citation graph.

Sort by

Same author

CT imaging parameters of the oval window region can predict the extent of stapes footplate exposure in patients with otosclerosis.

Acta oto-laryngologica·2026

Same author

Geographic and population disparities in cutaneous melanoma in the United States: state-level trends and national population-level analyses.

BMC public health·2026

Same author

Targeted Epstein-Barr virus capture sequencing identifies BBLF4-L322M as an independent prognostic variant in nasopharyngeal carcinoma.

Microbiology spectrum·2026

Same author

Deep learning for discriminating cochlear malformations on temporal bone CT.

Brazilian journal of otorhinolaryngology·2026

Same author

Tree shrew immune cell atlas identifies NR1H3⁺ tissue macrophages with conserved anti-inflammatory function.

Nature communications·2026

Same author

Prognostic significance of quantitative EBV biomarkers in extranodal NK/T-cell lymphoma: a meta-analysis of EBV DNA load and EBER-positive cell proportion.

Infectious agents and cancer·2026

Search research articles

Related Experiment Video

Updated: May 5, 2026

Application of Deep Learning-Based Medical Image Segmentation via Orbital Computed Tomography

Application of Deep Learning-Based Medical Image Segmentation via Orbital Computed Tomography

Published on: November 30, 2022

Multicenter Study of Multimodal MRI Radiomics and Deep Learning-Based Segmentation for Predicting Local Recurrence of

Dongfang Yao¹, Yongjing Lai¹, Xiang Bin¹

¹Department of Otolaryngology-Head and Neck Surgery, The First Affiliated Hospital of Guangxi Medical University, Nanning 530021, China.

|May 4, 2026

Summary

A new multimodal magnetic resonance imaging (MRI) radiomics model combined deep learning segmentation to predict nasopharyngeal carcinoma (NPC) recurrence. The model showed strong multicenter performance, aiding in post-treatment surveillance planning.

Keywords:

Swin UNet automatic segmentation deep learning magnetic resonance imaging nasopharyngeal carcinoma radiomics recurrence prediction

More Related Videos

Author Spotlight: Advancing 3D Modeling for Enhanced Diagnosis and Treatment of Pulmonary Nodules in Early-Stage Lung Cancer

Author Spotlight: Advancing 3D Modeling for Enhanced Diagnosis and Treatment of Pulmonary Nodules in Early-Stage Lung Cancer

Published on: October 13, 2023

Machine Learning Algorithms for Early Detection of Bone Metastases in an Experimental Rat Model

Machine Learning Algorithms for Early Detection of Bone Metastases in an Experimental Rat Model

Published on: August 16, 2020

Related Experiment Videos

Last Updated: May 5, 2026

Application of Deep Learning-Based Medical Image Segmentation via Orbital Computed Tomography

Application of Deep Learning-Based Medical Image Segmentation via Orbital Computed Tomography

Published on: November 30, 2022

Author Spotlight: Advancing 3D Modeling for Enhanced Diagnosis and Treatment of Pulmonary Nodules in Early-Stage Lung Cancer

Author Spotlight: Advancing 3D Modeling for Enhanced Diagnosis and Treatment of Pulmonary Nodules in Early-Stage Lung Cancer

Published on: October 13, 2023

Machine Learning Algorithms for Early Detection of Bone Metastases in an Experimental Rat Model

Machine Learning Algorithms for Early Detection of Bone Metastases in an Experimental Rat Model

Published on: August 16, 2020

Area of Science:

Oncology
Radiology
Artificial Intelligence

Background:

Nasopharyngeal carcinoma (NPC) recurrence poses a significant clinical challenge.
Accurate prediction of local recurrence is crucial for effective treatment planning and patient management.
Multimodal magnetic resonance imaging (MRI) and radiomics offer potential for improved prognostic assessment.

Purpose of the Study:

To develop and validate a multimodal MRI framework integrating deep learning segmentation and radiomics for predicting local recurrence in NPC.
To assess the performance of the multimodal model across different centers and compare it with single-modality approaches.

Main Methods:

A retrospective two-center study involving 1074 NPC patients.
Development of a multimodal Swin UNet model for automatic tumor segmentation from T1-weighted, T2-weighted, and contrast-enhanced T1 MRI.
Extraction and selection of radiomics features, followed by extreme gradient boosting modeling for recurrence prediction.

Main Results:

The multimodal segmentation model achieved moderate Dice similarity coefficients, reflecting the infiltrative nature of NPC.
The multimodal fusion model demonstrated superior performance in external validation, achieving an AUC of 0.910, accuracy of 0.908, sensitivity of 0.805, and specificity of 0.946.
The fully automatic segmentation approach yielded comparable results to expert-reviewed regions of interest, supporting end-to-end deployment feasibility.

Conclusions:

The developed multimodal MRI radiomics model shows promising multicenter performance for NPC recurrence risk evaluation.
The fusion of multimodal features enhances prediction accuracy over single-modality models.
This framework supports post-treatment surveillance planning and personalized patient management.