Abstract
OBJECTIVE: This study aims to assess the value of radiomics features integrated with clinical characteristics for estimating Ki67 expression in patients with breast cancer (BC). METHODS: In total, 114 patients with BC performed (18)F-FDG PET/CT scans. Patients were randomly assigned to a training set (n = 79, 55 cases of Ki67 + and 24 cases of Ki67-) and a validation set (n = 35, 24 cases of Ki67 + and 11 cases of Ki67-). Thirteen clinical characteristics and 704 radiomics features were extracted, and 4 clinical and 8 radiomics features were selected. Three models were developed, including the clinical model, the radiomics model, and the combined model. Model performance was evaluated using the ROC curve, and clinical utility was assessed through decision curve analysis (DCA). RESULTS: The N stage, tumor morphology, SUVmax, and the longest diameter significantly differed between Ki67 + and Ki67- groups (all P < 0.05). Eight radiomics features were selected for the radiomics model. The area under the curve of the combined model in the training and test group was 0.90 (95% CI: 0.82∼0.97) and 0.81 (95% CI: 0.64∼0.99), respectively. The combined model significantly outperformed both the radiomics model and the clinical model alone (P < 0.05). The DCA curve demonstrated the superior clinical utility of the combined model compared to the clinical model and radiomics model. CONCLUSIONS: PET/CT image-based radiomics features combined with clinical features have the potential to predict Ki67 expression in BC. SUPPLEMENTARY INFORMATION: The online version contains supplementary material available at 10.1007/s13139-024-00896-9.