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

Tudor Voicu Moga,Roxana Sirli,Camelia Foncea,Mirela Danilă,Ciprian David,Ioan Sporea,Adrian Burdan,Raluca Lupusoru,Teofana Bizerea-Moga,Alina Popescu,Iulia Ratiu,Ana M Ghiuchici,Darius Heredea

doi:10.3390/jpm11121388

Abstract

Background: 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. Materials and methods: 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. Results: 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%). Conclusions: 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.

Highlights

The aim of our study was to reassess inconclusive focal liver lesions (FLL) that had been evaluated by contrast enhanced ultrasound (CEUS) with the help of the Multiparametric ultrasound (MPUS) concept, using a binary decision tree classifier in order to highlight the malignancy of the lesions as the first endpoint, and later on to identify the lesion type as the second endpoint
All of the lesions included in the study had a second line imaging method—contrast-enhanced computer tomography (CE-CT), with contrast-enhanced magnetic resonance imaging (CEMRI) or biopsy—that was considered as the reference method
The steps consisted of liver stiffness measurement (LSM), time–intensity curve analysis (TIC), and parametric imaging (PI), hereinafter referred to as multiparametric ultrasound (MPUS) evaluation (Figure 1)

Summary

Introduction

Ultrasound (US) is a widely used method for diagnosis. It is easy to use, non-invasive, and does not irradiate the patient, and can be repeated as many times as necessary. Because all US machines have grayscale imaging (B-mode) and Doppler, these modes are used as the first line of imaging diagnosis. With the evolution of ultrasound engineering, multiple other options have emerged, increasing the utility of US. New ultrasound devices have the ability to perform multiple elastographic methods, enabling us to assess fibrosis. With the introduction of contrast medium (contrast-enhanced ultrasound (CEUS)), the paradigm of ultrasound indication has changed, especially for focal liver lesions (FLLs)

Objectives

Methods

Results

Conclusion