Radiomics nomogram based on optimal VOI of multi-sequence MRI for predicting microvascular invasion in intrahepatic cholangiocarcinoma

• Published in: Radiologia medica Vol. 128; no. 11; pp. 1296 - 1309
• Main Authors: Ma, Xijuan, Qian, Xianling, Wang, Qing, Zhang, Yunfei, Zong, Ruilong, Zhang, Jia, Qian, Baoxin, Yang, Chun, Lu, Xin, Shi, Yibing
• Format: Journal Article
• Language: English
• Published: Milan Springer Milan 01.11.2023; Springer Nature B.V
• Subjects: Abdominal Radiology; Algorithms; Bile Duct Neoplasms - diagnostic imaging; Bile Duct Neoplasms - surgery; Bile Ducts, Intrahepatic - diagnostic imaging; Cholangiocarcinoma; Cholangiocarcinoma - diagnostic imaging; Cholangiocarcinoma - surgery; Diagnostic Radiology; Humans; Imaging; Interventional Radiology; Magnetic resonance imaging; Magnetic Resonance Imaging - methods; Medical imaging; Medicine; Medicine & Public Health; Multivariate analysis; Neoplasm Invasiveness; Neuroradiology; Nomograms; Performance evaluation; Performance prediction; Radiology; Radiomics; Retrospective Studies; Tumors; Ultrasound; Magnetic resonance imaging; Microvascular invasion; Nomogram; Intrahepatic cholangiocarcinoma
• ISSN: 1826-6983; 0033-8362; 1826-6983
• DOI: 10.1007/s11547-023-01704-8

Objective Microvascular invasion (MVI) is a significant adverse prognostic indicator of intrahepatic cholangiocarcinoma (ICC) and affects the selection of individualized treatment regimens. This study sought to establish a radiomics nomogram based on the optimal VOI of multi-sequence MRI for predicting MVI in ICC tumors. Methods 160 single ICC lesions with MRI scanning confirmed by postoperative pathology were randomly separated into training and validation cohorts (TC and VC). Multivariate analysis identified independent clinical and imaging MVI predictors. Radiomics features were obtained from images of 6 MRI sequences at 4 different VOIs. The least absolute shrinkage and selection operator algorithm was performed to enable the derivation of robust and effective radiomics features. Then, the best three sequences and the optimal VOI were obtained through comparison. The MVI prediction nomogram combined the independent predictors and optimal radiomics features, and its performance was evaluated via the receiver operating characteristics, calibration, and decision curves. Results Tumor size and intrahepatic ductal dilatation are independent MVI predictors. Radiomics features extracted from the best three sequences (T1WI-D, T1WI, DWI) with VOI 10mm (including tumor and 10 mm peritumoral region) showed the best predictive performance, with AUC TC  = 0.987 and AUC VC  = 0.859. The MVI prediction nomogram obtained excellent prediction efficacy in both TC (AUC = 0.995, 95%CI 0.987–1.000) and VC (AUC = 0.867, 95%CI 0.798–0.921) and its clinical significance was further confirmed by the decision curves. Conclusion A nomogram combining tumor size, intrahepatic ductal dilatation, and the radiomics model of MRI multi-sequence fusion at VOI 10mm may be a predictor of preoperative MVI status in ICC patients.