Insights into Imaging · 2024 · 22 citations · 19 references
MedicineOncologyRadiologyDiagnostic ImagingDiagnostic RadiologyMachine LearningBladder CancerCancer DiagnosisComputer-aided DiagnosisExplainable Machine LearningFeature SelectionTumor ClassificationExtreme Gradient BoostingInterpretabilityMulticenter ValidationPredictive Model PerformancePredictive PerformanceRadiomicsRadiomics PrognosisShapley Value Explanations
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.
19
Radiomics: Images Are More than Pictures, They Are Data
Robert J. Gillies, Paul E. Kinahan, Hedvig Hricak · Radiology · 2015 · 8.3K citations
Mahul B. Amin, Frederick L. Greene, Stephen B. Edge et al. · CA A Cancer Journal for Clinicians · 2017 · 6.5K citations · Full text
Medicine, Cancer Biology, Oncology +17
Gary S. Collins, Johannes B. Reitsma, Douglas G. Altman et al. · Annals of Internal Medicine · 2015 · 2.9K citations · Full text
Antonio C. Wolff, M. Elizabeth Hammond, Kimberly H. Allison et al. · Journal of Clinical Oncology · 2018 · 2.5K citations · Full text
Advances in diagnosis and treatment of bladder cancer
Antonio López-Beltrán, Michael S. Cookson, Brendan J. Guercio et al. · BMJ · 2024 · 448 citations · Full text