Radiomics based on fluoro-deoxyglucose positron emission tomography predicts liver fibrosis in biopsy-proven MAFLD: a pilot study

• Published in: International journal of medical sciences Vol. 18; no. 16; pp. 3624 - 3630
• Main Authors: Chen, Zhong-Wei, Tang, Kun, Zhao, You-Fan, Chen, Yang-Zong, Tang, Liang-Jie, Li, Gang, Huang, Ou-Yang, Wang, Xiao-Dong, Targher, Giovanni, Byrne, Christopher D., Zheng, Xiang-Wu, Zheng, Ming-Hua
• Format: Journal Article
• Language: English
• Published: Australia Ivyspring International Publisher Pty Ltd 01.01.2021; Ivyspring International Publisher
• Subjects: Adult; Biopsy; Blood pressure; China; Cholesterol; Diabetes; Discriminant analysis; Disease Progression; Drug dosages; Fatty liver; Female; Fluorodeoxyglucose F18; Glucose; Histology; Humans; Liver Cirrhosis - diagnosis; Liver Cirrhosis - pathology; Liver diseases; Male; Medical imaging; Metabolism; Middle Aged; Non-alcoholic Fatty Liver Disease - diagnosis; Non-alcoholic Fatty Liver Disease - pathology; Performance evaluation; Pilot Projects; Positron Emission Tomography Computed Tomography - methods; Predictive Value of Tests; Prognosis; Radiometry - methods; Radiomics; Research Paper; Software; Tomography; Variables; China; 18F-FDG PET/CT; Metabolic dysfunction-associated fatty liver disease; Fibrosis; Radiomics
• ISSN: 1449-1907; 1449-1907
• DOI: 10.7150/ijms.64458

Since non-invasive tests for prediction of liver fibrosis have a poor diagnostic performance for detecting low levels of fibrosis, it is important to explore the diagnostic capabilities of other non-invasive tests to diagnose low levels of fibrosis. We aimed to evaluate the performance of radiomics based on F-fluorodeoxyglucose ( F-FDG) positron emission tomography (PET) in predicting any liver fibrosis in individuals with biopsy-proven metabolic dysfunction-associated fatty liver disease (MAFLD). A total of 22 adults with biopsy-confirmed MAFLD, who underwent F-FDG PET/CT, were enrolled in this study. Sixty radiomics features were extracted from whole liver region of interest in F-FDG PET images. Subsequently, the minimum redundancy maximum relevance (mRMR) method was performed and a subset of two features mostly related to the output classes and low redundancy between them were selected according to an event per variable of 5. Logistic regression, Support Vector Machine, Naive Bayes, 5-Nearest Neighbor and linear discriminant analysis models were built based on selected features. The predictive performances were assessed by the receiver operator characteristic (ROC) curve analysis. The mean (SD) age of the subjects was 38.5 (10.4) years and 17 subjects were men. 12 subjects had histological evidence of any liver fibrosis. The coarseness of neighborhood grey-level difference matrix (NGLDM) and long-run emphasis (LRE) of grey-level run length matrix (GLRLM) were selected to predict fibrosis. The logistic regression model performed best with an AUROC of 0.817 [95% confidence intervals, 0.595-0.947] for prediction of liver fibrosis. These preliminary data suggest that F-FDG PET radiomics may have clinical utility in assessing early liver fibrosis in MAFLD.