Predicting Microvascular Invasion in Hepatocellular Carcinoma Using CT-based Radiomics Model
Tian-Yi Xia1, Zheng-Hao Zhou1, Xiang-Pan Meng1
1From the Jiangsu Key Laboratory of Molecular and Functional Imaging, Department of Radiology, Zhongda Hospital, School of Medicine, Southeast University, 87 Ding Jia Qiao Road, Nanjing, China 210009 (T.Y.X., X.P.M., J.H.Z., Q.Y., W.L.W., Y.C.W., T.Y.T., S.H.J.); Institute for AI in Medicine, School of Artificial Intelligence, Nanjing University of Information Science and Technology, Nanjing, China (Z.H.Z., J.X.); MR Scientific Marketing, Siemens Healthineers, Shanghai, China (Y.S.); Department of Radiology, The Third Affiliated Hospital of Nantong University, Nantong, China (T.Z.); Department of Radiology, The Xiangya Hospital of Central South University, Changsha, China (X.Y.L.); Department of Radiology, Department of Hepatobiliary Surgery, The First Affiliated Hospital of Kunming Medical University, Kunming, China (Y.L.); and Department of Radiology, The First Affiliated Hospital of Zhejiang University School of Medicine, Hangzhou, China (W.B.X.).
A new hybrid radiomics model accurately predicts microvascular invasion (MVI) in hepatocellular carcinoma (HCC) using CT scans. This model also helps predict patient survival and identifies MVI-related genes involved in glucose metabolism.
Area of Science:
- Radiology
- Oncology
- Medical Imaging
Background:
- Microvascular invasion (MVI) prediction is crucial for hepatocellular carcinoma (HCC) treatment.
- Radiomics offers a non-invasive method to assess MVI status.
Purpose of the Study:
- Develop a radiomics approach to predict MVI in HCC using preoperative CT images.
- Identify genes associated with MVI for further understanding of HCC progression.
Main Methods:
- Retrospective analysis of 773 HCC patients from four centers.
- Radiomics feature extraction from CT images.
- Development and validation of radiomics and hybrid models.
- Gene expression analysis using RNA sequencing data.
Main Results:
- The hybrid model achieved high predictive performance (AUCs of 0.86 and 0.84 in internal and external test sets).
- The hybrid model effectively categorized early recurrence-free and overall survival.
- MVI-associated differentially expressed genes were linked to glucose metabolism.
Conclusions:
- The hybrid radiomics model demonstrates superior performance in predicting MVI in HCC.
- This approach can aid in treatment strategy determination and patient prognostication.
- Identified gene expression patterns provide insights into MVI mechanisms.
