Radiomics-Based Differentiation of Primary Central Nervous System Lymphoma and Solitary Brain Metastasis Using Contrast-Enhanced T1-Weighted Imaging: A Retrospective Machine Learning Study.
Authors
Affiliations (5)
Affiliations (5)
- Division of Head & Neck Tumor Multimodality Treatment, Cancer Center, West China Hospital, Sichuan University, Chengdu, China (X.X., Q.G.).
- Division of Head & Neck Tumor Multimodality Treatment and West China Biomedical Big Data Center, West China Hospital, Sichuan University, Chengdu, China (J.Q.).
- Radiotherapy Physics and Technology Center, Cancer Center, West China Hospital, Sichuan University, Chengdu, China (Q.T.).
- Department of Targeting Therapy & Immunology, Cancer Center, West China Hospital, Sichuan University, Chengdu, China (W.D.).
- Division of Head & Neck Tumor Multimodality Treatment, Cancer Center, West China Hospital, Sichuan University, Chengdu, China (X.X., Q.G.). Electronic address: [email protected].
Abstract
To develop and evaluate radiomics-based models using contrast-enhanced T1-weighted imaging (CE-T1WI) for the non-invasive differentiation of primary central nervous system lymphoma (PCNSL) and solitary brain metastasis (SBM), aiming to improve diagnostic accuracy and support clinical decision-making. This retrospective study included a cohort of 324 patients pathologically diagnosed with PCNSL (n=115) or SBM (n=209) between January 2014 and December 2024. Tumor regions were manually segmented on CE-T1WI, and a comprehensive set of 1561 radiomic features was extracted. To identify the most important features, a two-step approach for feature selection was utilized, which involved the use of least absolute shrinkage and selection operator (LASSO) regression. Multiple machine learning classifiers were trained and validated to assess diagnostic performance. Model performance was evaluated using area under the curve (AUC), accuracy, sensitivity, and specificity. The effectiveness of the radiomics-based models was further assessed using decision curve analysis, which incorporated a risk threshold of 0.5 to balance both false positives and false negatives. 23 features were identified through LASSO regression. All classifiers demonstrated robust performance in terms of area under the curve (AUC) and accuracy, with 15 out of 20 classifiers achieving AUC values exceeding 0.9. In the 10-fold cross-validation, the artificial neural network (ANN) classifier achieved the highest AUC of 0.9305, followed by the support vector machine with polynomial kernels (SVMPOLY) classifier at 0.9226. Notably, the independent test revealed that the support vector machine with radial basis function (SVMRBF) classifier performed best, with an AUC of 0.9310 and the highest accuracy of 0.8780. The selected models-SVMRBF, SVMPOLY, ensemble learning with LDA (ELDA), ANN, random forest (RF), and grading boost with random undersampling boosting (GBRUSB)-all showed significant clinical utility, with their standardized net benefits (sNBs) surpassing 0.6. These results underline the potential of the radiomics-based models in reliably distinguishing PCNSL from SBM. The application of radiomic-driven models based on CE-T1WI has demonstrated encouraging potential for accurately distinguishing between PCNSL and SBM. The SVMRBF classifier showed the greatest diagnostic efficacy of all the classifiers tested, indicating its potential clinical utility in differential diagnosis.