MRI-based radiomics nomogram for preoperatively differentiating intrahepatic cholangiocarcinoma from colorectal liver metastases Abstract

A total of 133 patients in training cohort (64 IMCC and 69 CRLM) and 57 patients in validation cohort (29 IMCC and 28 CRLM) were included. Radiomics features were extracted from the DCE-MR images and selected by the least absolute shrinkage and selection operator algorithm to establish the radiomics model. The radiomics nomogram was constructed combining the radiomics model and clinical model. The radiomics nomogram combining radiomics signatures based on DCE-MRI with clinical factors (serum CEA level and tumor diameter) may provide a reliable and noninvasive tool to discriminate IMCC from CRLM, which could help guide treatment strategies and prognosis prediction preoperatively.