Prediction of cervical cancer lymph node metastasis based on multisequence magnetic resonance imaging radiomics and deep learning features: a dual-center study

Abstract Cervical cancer is a leading cause of death from malignant tumors in women, and accurate evaluation of occult lymph node metastasis (OLNM) is crucial for optimal treatment. This study aimed to develop several predictive models—including Clinical model, Radiomics models (RD), Deep Learning m...

Full description

Saved in:
Bibliographic Details
Main Authors: Shigang Luo, Yan Guo, Yongqing Ye, Qinglin Mu, Wenguang Huang, Guangcai Tang
Format: Article
Language:English
Published: Nature Portfolio 2025-08-01
Series:Scientific Reports
Subjects:
Online Access:https://doi.org/10.1038/s41598-025-13781-y
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1849333006631698432
author Shigang Luo
Yan Guo
Yongqing Ye
Qinglin Mu
Wenguang Huang
Guangcai Tang
author_facet Shigang Luo
Yan Guo
Yongqing Ye
Qinglin Mu
Wenguang Huang
Guangcai Tang
author_sort Shigang Luo
collection DOAJ
description Abstract Cervical cancer is a leading cause of death from malignant tumors in women, and accurate evaluation of occult lymph node metastasis (OLNM) is crucial for optimal treatment. This study aimed to develop several predictive models—including Clinical model, Radiomics models (RD), Deep Learning models (DL), Radiomics–Deep Learning fusion models (RD-DL), and a Clinical–RD-DL combined model—for assessing the risk of OLNM in cervical cancer patients.The study included 130 patients from Center 1 (training set) and 55 from Center 2 (test set). Clinical data and imaging sequences (T1, T2, and DWI) were used to extract features for model construction. Model performance was assessed using the DeLong test, and SHAP analysis was used to examine feature contributions. Results showed that both the RD-combined (AUC = 0.803) and DL-combined (AUC = 0.818) models outperformed single-sequence models as well as the standalone Clinical model (AUC = 0.702). The RD-DL model yielded the highest performance, achieving an AUC of 0.981 in the training set and 0.903 in the test set. Notably, integrating clinical variables did not further improve predictive performance; the Clinical–RD-DL model performed comparably to the RD-DL model. SHAP analysis showed that deep learning features had the greatest impact on model predictions. Both RD and DL models effectively predict OLNM, with the RD-DL model offering superior performance. These findings provide a rapid, non-invasive clinical prediction method.
format Article
id doaj-art-02b51b7e4332498d9edb439808864c2f
institution Kabale University
issn 2045-2322
language English
publishDate 2025-08-01
publisher Nature Portfolio
record_format Article
series Scientific Reports
spelling doaj-art-02b51b7e4332498d9edb439808864c2f2025-08-20T03:46:01ZengNature PortfolioScientific Reports2045-23222025-08-0115111310.1038/s41598-025-13781-yPrediction of cervical cancer lymph node metastasis based on multisequence magnetic resonance imaging radiomics and deep learning features: a dual-center studyShigang Luo0Yan Guo1Yongqing Ye2Qinglin Mu3Wenguang Huang4Guangcai Tang5Department of Radiology, The First People’s Hospital of GuangyuanDepartment of Radiology, The First People’s Hospital of GuangyuanDepartment of Radiology, The First People’s Hospital of GuangyuanDepartment of Radiology, The First People’s Hospital of GuangyuanDepartment of Radiology, The First People’s Hospital of GuangyuanDepartment of Radiology, Affiliated Hospital of Southwest Medical UniversityAbstract Cervical cancer is a leading cause of death from malignant tumors in women, and accurate evaluation of occult lymph node metastasis (OLNM) is crucial for optimal treatment. This study aimed to develop several predictive models—including Clinical model, Radiomics models (RD), Deep Learning models (DL), Radiomics–Deep Learning fusion models (RD-DL), and a Clinical–RD-DL combined model—for assessing the risk of OLNM in cervical cancer patients.The study included 130 patients from Center 1 (training set) and 55 from Center 2 (test set). Clinical data and imaging sequences (T1, T2, and DWI) were used to extract features for model construction. Model performance was assessed using the DeLong test, and SHAP analysis was used to examine feature contributions. Results showed that both the RD-combined (AUC = 0.803) and DL-combined (AUC = 0.818) models outperformed single-sequence models as well as the standalone Clinical model (AUC = 0.702). The RD-DL model yielded the highest performance, achieving an AUC of 0.981 in the training set and 0.903 in the test set. Notably, integrating clinical variables did not further improve predictive performance; the Clinical–RD-DL model performed comparably to the RD-DL model. SHAP analysis showed that deep learning features had the greatest impact on model predictions. Both RD and DL models effectively predict OLNM, with the RD-DL model offering superior performance. These findings provide a rapid, non-invasive clinical prediction method.https://doi.org/10.1038/s41598-025-13781-yRadiomicsDeep learningOccult lymph node metastasisCervical cancer
spellingShingle Shigang Luo
Yan Guo
Yongqing Ye
Qinglin Mu
Wenguang Huang
Guangcai Tang
Prediction of cervical cancer lymph node metastasis based on multisequence magnetic resonance imaging radiomics and deep learning features: a dual-center study
Scientific Reports
Radiomics
Deep learning
Occult lymph node metastasis
Cervical cancer
title Prediction of cervical cancer lymph node metastasis based on multisequence magnetic resonance imaging radiomics and deep learning features: a dual-center study
title_full Prediction of cervical cancer lymph node metastasis based on multisequence magnetic resonance imaging radiomics and deep learning features: a dual-center study
title_fullStr Prediction of cervical cancer lymph node metastasis based on multisequence magnetic resonance imaging radiomics and deep learning features: a dual-center study
title_full_unstemmed Prediction of cervical cancer lymph node metastasis based on multisequence magnetic resonance imaging radiomics and deep learning features: a dual-center study
title_short Prediction of cervical cancer lymph node metastasis based on multisequence magnetic resonance imaging radiomics and deep learning features: a dual-center study
title_sort prediction of cervical cancer lymph node metastasis based on multisequence magnetic resonance imaging radiomics and deep learning features a dual center study
topic Radiomics
Deep learning
Occult lymph node metastasis
Cervical cancer
url https://doi.org/10.1038/s41598-025-13781-y
work_keys_str_mv AT shigangluo predictionofcervicalcancerlymphnodemetastasisbasedonmultisequencemagneticresonanceimagingradiomicsanddeeplearningfeaturesadualcenterstudy
AT yanguo predictionofcervicalcancerlymphnodemetastasisbasedonmultisequencemagneticresonanceimagingradiomicsanddeeplearningfeaturesadualcenterstudy
AT yongqingye predictionofcervicalcancerlymphnodemetastasisbasedonmultisequencemagneticresonanceimagingradiomicsanddeeplearningfeaturesadualcenterstudy
AT qinglinmu predictionofcervicalcancerlymphnodemetastasisbasedonmultisequencemagneticresonanceimagingradiomicsanddeeplearningfeaturesadualcenterstudy
AT wenguanghuang predictionofcervicalcancerlymphnodemetastasisbasedonmultisequencemagneticresonanceimagingradiomicsanddeeplearningfeaturesadualcenterstudy
AT guangcaitang predictionofcervicalcancerlymphnodemetastasisbasedonmultisequencemagneticresonanceimagingradiomicsanddeeplearningfeaturesadualcenterstudy