ABSTRACT
Rationale: 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 18F-fluorodeoxyglucose (18F-FDG) positron emission tomography (PET) in predicting any liver fibrosis in individuals with biopsy-proven metabolic dysfunction-associated fatty liver disease (MAFLD). Methods: A total of 22 adults with biopsy-confirmed MAFLD, who underwent 18F-FDG PET/CT, were enrolled in this study. Sixty radiomics features were extracted from whole liver region of interest in 18F-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. Results: 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. Conclusion: These preliminary data suggest that 18F-FDG PET radiomics may have clinical utility in assessing early liver fibrosis in MAFLD.
Subject(s)
Fluorodeoxyglucose F18 , Liver Cirrhosis/diagnosis , Non-alcoholic Fatty Liver Disease/diagnosis , Positron Emission Tomography Computed Tomography/methods , Adult , Biopsy , China , Disease Progression , Female , Humans , Liver Cirrhosis/pathology , Male , Middle Aged , Non-alcoholic Fatty Liver Disease/pathology , Pilot Projects , Predictive Value of Tests , Prognosis , Radiometry/methodsABSTRACT
PURPOSE: Tumor boundary delineation using F-FDG PET/CT is a promising tool for radiotherapy applications, but no consensus has been established regarding the optimal delineation method. Time-phase variability of F-FDG PET/CT imaging frequently affects metabolically active volumes and treatment planning for nasopharyngeal carcinoma (NPC). This study aimed to evaluate the time-phase robustness of 8 methods commonly used for tumor volume delineation in NPC. PATIENTS AND METHODS: Twenty patients with biopsy-proven NPC were included and underwent multiple time-phase F-FDG PET/CT imaging. Gross tumor volumes (GTVs), absolute SUV, gradient-based watershed segmentation (GTV-GWT), and anatomic biologic contouring (GTV-ABC) values were determined. The volume of overlap between GTV-CT and the 8 PET-based GTVs was enclosed and the overlap fraction (OF-CT) calculated. Color matrix was used to semiquantify the time-phase differences. Gross tumor volume values obtained with different methods were recorded and compared using paired t test. Time-phase differences of GTVs and SUVmax were compared among groups by analysis of variance with Tukey honest significance tests. The coefficients of variation were computed to assess intrapatient time-phase variability. Similarity coefficient was calculated to evaluate similarity. RESULTS: Differences were observed between GTVs obtained at different time points using various delineation procedures. Nonsignificantly higher percentages were obtained for GTV-GWT (88.17%) and GTV-ABC (86.98%) compared with other methods, showing their robustness. GTV-40% (0.81-0.88) and GTV-ABC (0.82-0.88) indicated higher similarity with GTV-MRI than the other methods. CONCLUSIONS: PET/CT-based GTV-ABC between 35 and 55 minutes should be the first choice for NPC treatment planning.
