Multiparameter MRI-based model integrating radiomics and deep learning for preoperative staging of laryngeal squamous cell carcinoma

Abstract The accurate preoperative staging of laryngeal squamous cell carcinoma (LSCC) provides valuable guidance for clinical decision-making. The objective of this study was to establish a multiparametric MRI model using radiomics and deep learning (DL) to preoperatively distinguish between Stages...

Full description

Saved in:
Bibliographic Details
Main Authors: Kai Xie, Huan Jiang, Xinwei Chen, Youquan Ning, Qiang Yu, Fajin Lv, Rui Liu, Yuan Zhou, Lin Xu, Qiang Yue, Juan Peng
Format: Article
Language:English
Published: Nature Portfolio 2025-05-01
Series:Scientific Reports
Subjects:
Online Access:https://doi.org/10.1038/s41598-025-01270-1
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1849728227900129280
author Kai Xie
Huan Jiang
Xinwei Chen
Youquan Ning
Qiang Yu
Fajin Lv
Rui Liu
Yuan Zhou
Lin Xu
Qiang Yue
Juan Peng
author_facet Kai Xie
Huan Jiang
Xinwei Chen
Youquan Ning
Qiang Yu
Fajin Lv
Rui Liu
Yuan Zhou
Lin Xu
Qiang Yue
Juan Peng
author_sort Kai Xie
collection DOAJ
description Abstract The accurate preoperative staging of laryngeal squamous cell carcinoma (LSCC) provides valuable guidance for clinical decision-making. The objective of this study was to establish a multiparametric MRI model using radiomics and deep learning (DL) to preoperatively distinguish between Stages I–II and III–IV of LSCC. Data from 401 histologically confirmed LSCC patients were collected from two centers (training set: 213; internal test set: 91; external test set: 97). Radiomics features were extracted from the MRI images, and seven radiomics models based on single and combined sequences were developed via random forest (RF). A DL model was constructed via ResNet 18, where DL features were extracted from its final fully connected layer. These features were fused with crucial radiomics features to create a combined model. The performance of the models was assessed using the area under the receiver operating characteristic (ROC) curve (AUC) and compared with the radiologist performances. The predictive capability of the combined model for Progression-Free Survival (PFS) was evaluated via Kaplan–Meier survival analysis and the Harrell’s Concordance Index (C-index). In the external test set, the combined model had an AUC of 0.877 (95% CI 0.807–0.946), outperforming the DL model (AUC: 0.811) and the optimal radiomics model (AUC: 0.835). The combined model significantly outperformed both the DL (p = 0.017) and the optimal radiomics models (p = 0.039), and the radiologists (both p < 0.050). Moreover, the combined model demonstrated great prognostic predictive value in patients with LSCC, achieving a C-index of 0.624 for PFS. This combined model enhances preoperative LSCC staging, aiding in making more informed clinical decisions.
format Article
id doaj-art-99056f22d79a492f9ffcd0fb90ab604f
institution DOAJ
issn 2045-2322
language English
publishDate 2025-05-01
publisher Nature Portfolio
record_format Article
series Scientific Reports
spelling doaj-art-99056f22d79a492f9ffcd0fb90ab604f2025-08-20T03:09:35ZengNature PortfolioScientific Reports2045-23222025-05-0115111310.1038/s41598-025-01270-1Multiparameter MRI-based model integrating radiomics and deep learning for preoperative staging of laryngeal squamous cell carcinomaKai Xie0Huan Jiang1Xinwei Chen2Youquan Ning3Qiang Yu4Fajin Lv5Rui Liu6Yuan Zhou7Lin Xu8Qiang Yue9Juan Peng10Department of Radiology, The First Affiliated Hospital of Chongqing Medical UniversityDepartment of Radiology, The First Affiliated Hospital of Chongqing Medical UniversityDepartment of Radiology, The First Affiliated Hospital of Chongqing Medical UniversityDepartment of Radiology, The First Affiliated Hospital of Chongqing Medical UniversityDepartment of Radiology, The First Affiliated Hospital of Chongqing Medical UniversityDepartment of Radiology, The First Affiliated Hospital of Chongqing Medical UniversityDepartment of Radiology, The First Affiliated Hospital of Chongqing Medical UniversityDepartment of Radiology, The First Affiliated Hospital of Chongqing Medical UniversitySchool of Intelligent Medicine, Chengdu University of TCMDepartment of Radiology, West China Hospital of Sichuan UniversityDepartment of Radiology, The First Affiliated Hospital of Chongqing Medical UniversityAbstract The accurate preoperative staging of laryngeal squamous cell carcinoma (LSCC) provides valuable guidance for clinical decision-making. The objective of this study was to establish a multiparametric MRI model using radiomics and deep learning (DL) to preoperatively distinguish between Stages I–II and III–IV of LSCC. Data from 401 histologically confirmed LSCC patients were collected from two centers (training set: 213; internal test set: 91; external test set: 97). Radiomics features were extracted from the MRI images, and seven radiomics models based on single and combined sequences were developed via random forest (RF). A DL model was constructed via ResNet 18, where DL features were extracted from its final fully connected layer. These features were fused with crucial radiomics features to create a combined model. The performance of the models was assessed using the area under the receiver operating characteristic (ROC) curve (AUC) and compared with the radiologist performances. The predictive capability of the combined model for Progression-Free Survival (PFS) was evaluated via Kaplan–Meier survival analysis and the Harrell’s Concordance Index (C-index). In the external test set, the combined model had an AUC of 0.877 (95% CI 0.807–0.946), outperforming the DL model (AUC: 0.811) and the optimal radiomics model (AUC: 0.835). The combined model significantly outperformed both the DL (p = 0.017) and the optimal radiomics models (p = 0.039), and the radiologists (both p < 0.050). Moreover, the combined model demonstrated great prognostic predictive value in patients with LSCC, achieving a C-index of 0.624 for PFS. This combined model enhances preoperative LSCC staging, aiding in making more informed clinical decisions.https://doi.org/10.1038/s41598-025-01270-1Multiparametric MRILaryngeal squamous cell carcinomaCancer stagingRadiomicsDeep learning
spellingShingle Kai Xie
Huan Jiang
Xinwei Chen
Youquan Ning
Qiang Yu
Fajin Lv
Rui Liu
Yuan Zhou
Lin Xu
Qiang Yue
Juan Peng
Multiparameter MRI-based model integrating radiomics and deep learning for preoperative staging of laryngeal squamous cell carcinoma
Scientific Reports
Multiparametric MRI
Laryngeal squamous cell carcinoma
Cancer staging
Radiomics
Deep learning
title Multiparameter MRI-based model integrating radiomics and deep learning for preoperative staging of laryngeal squamous cell carcinoma
title_full Multiparameter MRI-based model integrating radiomics and deep learning for preoperative staging of laryngeal squamous cell carcinoma
title_fullStr Multiparameter MRI-based model integrating radiomics and deep learning for preoperative staging of laryngeal squamous cell carcinoma
title_full_unstemmed Multiparameter MRI-based model integrating radiomics and deep learning for preoperative staging of laryngeal squamous cell carcinoma
title_short Multiparameter MRI-based model integrating radiomics and deep learning for preoperative staging of laryngeal squamous cell carcinoma
title_sort multiparameter mri based model integrating radiomics and deep learning for preoperative staging of laryngeal squamous cell carcinoma
topic Multiparametric MRI
Laryngeal squamous cell carcinoma
Cancer staging
Radiomics
Deep learning
url https://doi.org/10.1038/s41598-025-01270-1
work_keys_str_mv AT kaixie multiparametermribasedmodelintegratingradiomicsanddeeplearningforpreoperativestagingoflaryngealsquamouscellcarcinoma
AT huanjiang multiparametermribasedmodelintegratingradiomicsanddeeplearningforpreoperativestagingoflaryngealsquamouscellcarcinoma
AT xinweichen multiparametermribasedmodelintegratingradiomicsanddeeplearningforpreoperativestagingoflaryngealsquamouscellcarcinoma
AT youquanning multiparametermribasedmodelintegratingradiomicsanddeeplearningforpreoperativestagingoflaryngealsquamouscellcarcinoma
AT qiangyu multiparametermribasedmodelintegratingradiomicsanddeeplearningforpreoperativestagingoflaryngealsquamouscellcarcinoma
AT fajinlv multiparametermribasedmodelintegratingradiomicsanddeeplearningforpreoperativestagingoflaryngealsquamouscellcarcinoma
AT ruiliu multiparametermribasedmodelintegratingradiomicsanddeeplearningforpreoperativestagingoflaryngealsquamouscellcarcinoma
AT yuanzhou multiparametermribasedmodelintegratingradiomicsanddeeplearningforpreoperativestagingoflaryngealsquamouscellcarcinoma
AT linxu multiparametermribasedmodelintegratingradiomicsanddeeplearningforpreoperativestagingoflaryngealsquamouscellcarcinoma
AT qiangyue multiparametermribasedmodelintegratingradiomicsanddeeplearningforpreoperativestagingoflaryngealsquamouscellcarcinoma
AT juanpeng multiparametermribasedmodelintegratingradiomicsanddeeplearningforpreoperativestagingoflaryngealsquamouscellcarcinoma