Multiparametric Ultrasound Approach Using a Tree-Based Decision Classifier for Inconclusive Focal Liver Lesions Evaluated by Contrast Enhanced Ultrasound

• Published in: Journal of personalized medicine Vol. 11; no. 12; p. 1388
• Main Authors: Moga, Tudor Voicu, David, Ciprian, Popescu, Alina, Lupusoru, Raluca, Heredea, Darius, Ghiuchici, Ana M, Foncea, Camelia, Burdan, Adrian, Sirli, Roxana, Danilă, Mirela, Ratiu, Iulia, Bizerea-Moga, Teofana, Sporea, Ioan
• Format: Journal Article
• Language: English
• Published: Switzerland MDPI AG 20.12.2021; MDPI
• Subjects: Algorithms; contrast-enhanced ultrasound; Decision making; Decision trees; focal liver lesions; Lesions; Liver; Liver cirrhosis; liver fibrosis; Metastasis; multiparametric ultrasound; Patients; Precision medicine; Software; Ultrasonic imaging; Ultrasound; liver fibrosis; focal liver lesions; multiparametric ultrasound; contrast-enhanced ultrasound
• ISSN: 2075-4426; 2075-4426
• DOI: 10.3390/jpm11121388

Multiparametric ultrasound (MPUS) is a concept whereby the examiner is encouraged to use the latest features of an ultrasound machine. The aim of this study was to reanalyze inconclusive focal liver lesions (FLLs) that had been analyzed via contrast enhanced ultrasound (CEUS) using the MPUS approach with the help of a tree-based decision classifier. We retrospectively analyzed FLLs that were inconclusive upon CEUS examination in our department, focusing our attention on samples taken over a period of two years (2017-2018). MPUS reanalysis followed a three-step algorithm, taking into account the liver stiffness measurement (LSM), time-intensity curve analysis (TIC), and parametric imaging (PI). After processing all steps of the algorithm, a binary decision tree classifier (BDTC) was used to achieve a software-assisted decision. Area was the only TIC-CEUS parameter that showed a significant difference between malign and benign lesions with a cutoff of >-19.3 dB for washout phenomena (AUROC = 0.58, Se = 74.0%, Sp = 45.7%). Using the binary decision tree classifier (BDTC) algorithm, we correctly classified 71 out of 91 lesions according to their malignant or benignant status, with an accuracy of 78.0% (sensitivity = 62%, specificity = 45%, and precision = 80%). By reevaluating inconclusive FLLs that had been analyzed via CEUS using MPUS, we managed to determine that 78% of the lesions were malignant and, in 28% of them, we established the lesion type.