Hepatic Alveolar Echinococcosis: Predictive Biological Activity Based on Radiomics of MRI

• Published in: BioMed research international Vol. 2021; no. 1; p. 6681092
• Main Authors: Ren, Bo, Wang, Jian, Miao, Zhoulin, Xia, Yuwei, Liu, Wenya, Zhang, Tieliang, Aikebaier, Aierken
• Format: Journal Article
• Language: English
• Published: United States Hindawi 2021; John Wiley & Sons, Inc
• Subjects: Abdomen; Adult; Alveoli; Analysis; Area Under Curve; Biological activity; Care and treatment; Computed tomography; CT imaging; Diagnosis; Echinococcosis; Echinococcosis, Hepatic - diagnostic imaging; Echinococcosis, Hepatic - pathology; Echinococcosis, Hepatic - surgery; Emission analysis; Feature extraction; Female; Humans; Image Interpretation, Computer-Assisted - methods; Learning algorithms; Liver; Liver diseases; Liver function tests; Machine Learning; Magnetic resonance imaging; Magnetic Resonance Imaging - methods; Male; Medical imaging; Methods; Middle Aged; Model testing; Multilayer perceptrons; Oversampling; Parasitic diseases; Positron emission; Positron emission tomography; Positron Emission Tomography Computed Tomography; Radiomics; Retrospective Studies; Risk factors; Standard deviation; Support vector machines; Surgery; Tomography; Training; Young Adult; China
• ISSN: 2314-6133; 2314-6141; 2314-6141
• DOI: 10.1155/2021/6681092

Background. To evaluate the role of radiomics based on magnetic resonance imaging (MRI) in the biological activity of hepatic alveolar echinococcosis (HAE). Methods. In this study, 90 active and 46 inactive cases of HAE patients were analyzed retrospectively. All the subjects underwent MRI and positron emission tomography computed tomography (PET-CT) before surgery. A total of 1409 three-dimensional radiomics features were extracted from the T2-weighted MR images (T2WI). The inactive group in the training cohort was balanced via the synthetic minority oversampling technique (SMOTE) method. The least absolute shrinkage and selection operator (LASSO) regression method was used for feature selection. The machine learning (ML) classifiers were logistic regression (LR), multilayer perceptron (MLP), and support vector machine (SVM). We used a fivefold cross-validation strategy in the training cohorts. The classification performance of the radiomics signature was evaluated using receiver operating characteristic curve (ROC) analysis in the training and test cohorts. Results. The radiomics features were significantly associated with the biological activity, and 10 features were selected to construct the radiomics model. The best performance of the radiomics model for the biological activity prediction was obtained by MLP (AUC=0.830±0.053; accuracy=0.817; sensitivity=0.822; specificity=0.811). Conclusions. We developed and validated a radiomics model as an adjunct tool to predict the HAE biological activity by combining T2WI images, which achieved results nearly equal to the PET-CT findings.