Impact of harmonization and oversampling methods on radiomics analysis of multi-center imbalanced datasets: application to PET-based prediction of lung cancer subtypes

作者：Dongyang Du, Isaac Shiri, Fereshteh Yousefirizi, Mohammad R. Salmanpour, Jieqin Lv, Huiqin Wu, Wentao Zhu, Habib Zaidi, Lijun Lu, Arman Rahmim · 发表于：EJNMMI Physics · 年份：2025 · DOI：10.1186/s40658-025-00750-7 · 被引用次数：5 · 研究领域：Radiomics and Machine Learning in Medical Imaging、Lung Cancer Diagnosis and Treatment、Cancer Immunotherapy and Biomarkers

BACKGROUND: Medical imaging data frequently encounter image-generation heterogeneity and class imbalance properties, challenging strong generalized predictive performances with data-driven machine-learning methods. The purpose of this study was to investigate the impact of harmonization and oversampling methods on multi-center imbalanced datasets, with specific application to PET-based radiomics modeling for histologic subtype prediction in non-small cell lung cancer (NSCLC). METHODS: The retrospective study included 245 patients with adenocarcinoma (ADC) and 78 patients with squamous cell carcinoma (SCC) from 4 centers. Utilizing 1502 radiomics features per patient, we trained, validated, and tested 4 machine-learning classifiers, to investigate the effect of no harmonization (NoH) or 4 feature harmonization methods, paired with no oversampling (NoO) or 5 oversampling methods on subtype prediction. Model performance was evaluated using the average area under the ROC curve (AUROC) and G-mean via 5 times 5-fold cross-validations. Statistical comparisons of the combined models against baseline (NoH + NoO) were performed for each fold of cross-validation using the DeLong test. RESULTS: The number of cross-combinations with both AUROC and G-mean outperforming baseline in validation and testing was 15, 4, 2, and 7 (out of 29) for random forest (RF), linear discriminant analysis (LDA), logistic regression (LR), and support vector machine (SVM), respectively. ComBat harmonization co...