Assessment of Primary Colorectal Cancer CT Radiomics to Predict Metachronous Liver Metastasis.

Objectives: To establish and validate a machine learning-based CT radiomics model to predict metachronous liver metastasis (MLM) in patients with colorectal cancer. Methods: In total, 323 patients were retrospectively recruited from two independent institutions to develop and evaluate the CT radiomics model. Then, 1288 radiomics features were extracted to decode the imaging phenotypes of colorectal cancer on CT images. The optimal radiomics features were selected using a recursive feature elimination selector configured by a support vector machine. To reduce the bias caused by an unbalanced dataset, the synthetic minority oversampling technique was applied to resample the minority samples in the datasets. Then, both radiomics and clinical features were used to train the multilayer perceptron classifier to develop two classification models. Finally, a score-level fusion model was developed to further improve the model performance. Results: The area under the curve (AUC) was 0.78 ± 0.07 for the tumour feature model and 0.79 ± 0.08 for the clinical feature model. The fusion model achieved the best performance, with AUCs of 0.79 ± 0.08 and 0.72 ± 0.07 in the internal and external validation cohorts. Conclusions: Radiomics models based on baseline colorectal contrast-enhanced CT have high potential for MLM prediction. The fusion model combining radiomics and clinical features can provide valuable biomarkers to identify patients with a high risk of colorectal liver metastases.