A radiomics-based interpretable machine learning model to predict the HER2 status in bladder cancer: a multicenter study

Abstract Objective To develop a computed tomography (CT) radiomics-based interpretable machine learning (ML) model to preoperatively predict human epidermal growth factor receptor 2 (HER2) status in bladder cancer (BCa) with multicenter validation. Methods In this retrospective study, 207 patients w...

Full description

Saved in:
Bibliographic Details
Main Authors: Zongjie Wei, Xuesong Bai, Yingjie Xv, Shao-Hao Chen, Siwen Yin, Yang Li, Fajin Lv, Mingzhao Xiao, Yongpeng Xie
Format: Article
Language:English
Published: SpringerOpen 2024-10-01
Series:Insights into Imaging
Subjects:
Online Access:https://doi.org/10.1186/s13244-024-01840-3
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1850179876320968704
author Zongjie Wei
Xuesong Bai
Yingjie Xv
Shao-Hao Chen
Siwen Yin
Yang Li
Fajin Lv
Mingzhao Xiao
Yongpeng Xie
author_facet Zongjie Wei
Xuesong Bai
Yingjie Xv
Shao-Hao Chen
Siwen Yin
Yang Li
Fajin Lv
Mingzhao Xiao
Yongpeng Xie
author_sort Zongjie Wei
collection DOAJ
description Abstract Objective To develop a computed tomography (CT) radiomics-based interpretable machine learning (ML) model to preoperatively predict human epidermal growth factor receptor 2 (HER2) status in bladder cancer (BCa) with multicenter validation. Methods In this retrospective study, 207 patients with pathologically confirmed BCa were enrolled and divided into the training set (n = 154) and test set (n = 53). Least absolute shrinkage and selection operator (LASSO) regression was used to identify the most discriminative features in the training set. Five radiomics-based ML models, namely logistic regression (LR), support vector machine (SVM), k-nearest neighbors (KNN), eXtreme Gradient Boosting (XGBoost) and random forest (RF), were developed. The predictive performance of established ML models was evaluated by the area under the receiver operating characteristic curve (AUC). The Shapley additive explanation (SHAP) was used to analyze the interpretability of ML models. Results A total of 1218 radiomics features were extracted from the nephrographic phase CT images, and 11 features were filtered for constructing ML models. In the test set, the AUCs of LR, SVM, KNN, XGBoost, and RF were 0.803, 0.709, 0.679, 0.794, and 0.815, with corresponding accuracies of 71.7%, 69.8%, 60.4%, 75.5%, and 75.5%, respectively. RF was identified as the optimal classifier. SHAP analysis showed that texture features (gray level size zone matrix and gray level co-occurrence matrix) were significant predictors of HER2 status. Conclusions The radiomics-based interpretable ML model provides a noninvasive tool to predict the HER2 status of BCa with satisfactory discriminatory performance. Critical relevance statement An interpretable radiomics-based machine learning model can preoperatively predict HER2 status in bladder cancer, potentially aiding in the clinical decision-making process. Key Points The CT radiomics model could identify HER2 status in bladder cancer. The random forest model showed a more robust and accurate performance. The model demonstrated favorable interpretability through SHAP method. Graphical Abstract
format Article
id doaj-art-85431007c8e244a08305dd125c269f39
institution OA Journals
issn 1869-4101
language English
publishDate 2024-10-01
publisher SpringerOpen
record_format Article
series Insights into Imaging
spelling doaj-art-85431007c8e244a08305dd125c269f392025-08-20T02:18:24ZengSpringerOpenInsights into Imaging1869-41012024-10-0115111110.1186/s13244-024-01840-3A radiomics-based interpretable machine learning model to predict the HER2 status in bladder cancer: a multicenter studyZongjie Wei0Xuesong Bai1Yingjie Xv2Shao-Hao Chen3Siwen Yin4Yang Li5Fajin Lv6Mingzhao Xiao7Yongpeng Xie8Department of Urology, The First Affiliated Hospital of Chongqing Medical UniversityDepartment of Urology, The First Affiliated Hospital of Chongqing Medical UniversityDepartment of Urology, The First Affiliated Hospital of Chongqing Medical UniversityDepartment of Urology, Urology Research Institute, The First Affiliated Hospital of Fujian Medical UniversityDepartment of Urology, Chongqing University Fuling HospitalDepartment of Urology, Chongqing University Three Gorges HospitalDepartment of Radiology, The First Affiliated Hospital of Chongqing Medical UniversityDepartment of Urology, The First Affiliated Hospital of Chongqing Medical UniversityDepartment of Urology, The First Affiliated Hospital of Chongqing Medical UniversityAbstract Objective To develop a computed tomography (CT) radiomics-based interpretable machine learning (ML) model to preoperatively predict human epidermal growth factor receptor 2 (HER2) status in bladder cancer (BCa) with multicenter validation. Methods In this retrospective study, 207 patients with pathologically confirmed BCa were enrolled and divided into the training set (n = 154) and test set (n = 53). Least absolute shrinkage and selection operator (LASSO) regression was used to identify the most discriminative features in the training set. Five radiomics-based ML models, namely logistic regression (LR), support vector machine (SVM), k-nearest neighbors (KNN), eXtreme Gradient Boosting (XGBoost) and random forest (RF), were developed. The predictive performance of established ML models was evaluated by the area under the receiver operating characteristic curve (AUC). The Shapley additive explanation (SHAP) was used to analyze the interpretability of ML models. Results A total of 1218 radiomics features were extracted from the nephrographic phase CT images, and 11 features were filtered for constructing ML models. In the test set, the AUCs of LR, SVM, KNN, XGBoost, and RF were 0.803, 0.709, 0.679, 0.794, and 0.815, with corresponding accuracies of 71.7%, 69.8%, 60.4%, 75.5%, and 75.5%, respectively. RF was identified as the optimal classifier. SHAP analysis showed that texture features (gray level size zone matrix and gray level co-occurrence matrix) were significant predictors of HER2 status. Conclusions The radiomics-based interpretable ML model provides a noninvasive tool to predict the HER2 status of BCa with satisfactory discriminatory performance. Critical relevance statement An interpretable radiomics-based machine learning model can preoperatively predict HER2 status in bladder cancer, potentially aiding in the clinical decision-making process. Key Points The CT radiomics model could identify HER2 status in bladder cancer. The random forest model showed a more robust and accurate performance. The model demonstrated favorable interpretability through SHAP method. Graphical Abstracthttps://doi.org/10.1186/s13244-024-01840-3RadiomicsBladder cancerComputed tomographyHER2Machine learning
spellingShingle Zongjie Wei
Xuesong Bai
Yingjie Xv
Shao-Hao Chen
Siwen Yin
Yang Li
Fajin Lv
Mingzhao Xiao
Yongpeng Xie
A radiomics-based interpretable machine learning model to predict the HER2 status in bladder cancer: a multicenter study
Insights into Imaging
Radiomics
Bladder cancer
Computed tomography
HER2
Machine learning
title A radiomics-based interpretable machine learning model to predict the HER2 status in bladder cancer: a multicenter study
title_full A radiomics-based interpretable machine learning model to predict the HER2 status in bladder cancer: a multicenter study
title_fullStr A radiomics-based interpretable machine learning model to predict the HER2 status in bladder cancer: a multicenter study
title_full_unstemmed A radiomics-based interpretable machine learning model to predict the HER2 status in bladder cancer: a multicenter study
title_short A radiomics-based interpretable machine learning model to predict the HER2 status in bladder cancer: a multicenter study
title_sort radiomics based interpretable machine learning model to predict the her2 status in bladder cancer a multicenter study
topic Radiomics
Bladder cancer
Computed tomography
HER2
Machine learning
url https://doi.org/10.1186/s13244-024-01840-3
work_keys_str_mv AT zongjiewei aradiomicsbasedinterpretablemachinelearningmodeltopredicttheher2statusinbladdercanceramulticenterstudy
AT xuesongbai aradiomicsbasedinterpretablemachinelearningmodeltopredicttheher2statusinbladdercanceramulticenterstudy
AT yingjiexv aradiomicsbasedinterpretablemachinelearningmodeltopredicttheher2statusinbladdercanceramulticenterstudy
AT shaohaochen aradiomicsbasedinterpretablemachinelearningmodeltopredicttheher2statusinbladdercanceramulticenterstudy
AT siwenyin aradiomicsbasedinterpretablemachinelearningmodeltopredicttheher2statusinbladdercanceramulticenterstudy
AT yangli aradiomicsbasedinterpretablemachinelearningmodeltopredicttheher2statusinbladdercanceramulticenterstudy
AT fajinlv aradiomicsbasedinterpretablemachinelearningmodeltopredicttheher2statusinbladdercanceramulticenterstudy
AT mingzhaoxiao aradiomicsbasedinterpretablemachinelearningmodeltopredicttheher2statusinbladdercanceramulticenterstudy
AT yongpengxie aradiomicsbasedinterpretablemachinelearningmodeltopredicttheher2statusinbladdercanceramulticenterstudy
AT zongjiewei radiomicsbasedinterpretablemachinelearningmodeltopredicttheher2statusinbladdercanceramulticenterstudy
AT xuesongbai radiomicsbasedinterpretablemachinelearningmodeltopredicttheher2statusinbladdercanceramulticenterstudy
AT yingjiexv radiomicsbasedinterpretablemachinelearningmodeltopredicttheher2statusinbladdercanceramulticenterstudy
AT shaohaochen radiomicsbasedinterpretablemachinelearningmodeltopredicttheher2statusinbladdercanceramulticenterstudy
AT siwenyin radiomicsbasedinterpretablemachinelearningmodeltopredicttheher2statusinbladdercanceramulticenterstudy
AT yangli radiomicsbasedinterpretablemachinelearningmodeltopredicttheher2statusinbladdercanceramulticenterstudy
AT fajinlv radiomicsbasedinterpretablemachinelearningmodeltopredicttheher2statusinbladdercanceramulticenterstudy
AT mingzhaoxiao radiomicsbasedinterpretablemachinelearningmodeltopredicttheher2statusinbladdercanceramulticenterstudy
AT yongpengxie radiomicsbasedinterpretablemachinelearningmodeltopredicttheher2statusinbladdercanceramulticenterstudy