Artificial intelligence assists identifying malignant versus benign liver lesions using contrast‐enhanced ultrasound

Abstract

Background and Aim: This study aims to construct a strategy that uses assistance from artificial intelligence (AI) to assist radiologists in the identification of malignant versus benign focal liver lesions (FLLs) using contrast-enhanced ultrasound (CEUS). Methods: A training set (patients = 363) and a testing set (patients = 211) were collected from our institute. On four-phase CEUS images in the training set, a composite deep learning architecture was trained and tuned for differentiating malignant and benign FLLs. In the test dataset, AI performance was evaluated by comparison with radiologists with varied levels of experience. Based on the comparison, an AI assistance strategy was constructed, and its usefulness in reducing CEUS interobserver heterogeneity was further tested. Results: In the test set, to identify malignant versus benign FLLs, AI achieved an area under the curve of 0.934 (95% CI 0.890-0.978) with an accuracy of 91.0%. Comparing with radiologists reviewing videos along with complementary patient information, AI outperformed residents (82.9-84.4%, P = 0.038) and matched the performance of experts (87.2-88.2%, P = 0.438). Due to the higher positive predictive value (PPV) (AI: 95.6% vs residents: 88.6-89.7%, P = 0.056), an AI strategy was defined to improve the malignant diagnosis. With the assistance of AI, radiologists exhibited a sensitivity improvement of 97.0-99.4% (P < 0.05) and an accuracy of 91.0-92.9% (P = 0.008-0.189), which was comparable with that of the experts (P = 0.904). Conclusions:The CEUS-based AI strategy improved the performance of residents and reduced CEUS's interobserver heterogeneity in the differentiation of benign and malignant FLLs.

Conventional, functional and radiomics assessment for intrahepatic cholangiocarcinoma

“…Ultrasound (US) is an imaging tool inexpensive, non-aggressive, non based on X-rays suorces and so repeatable [ 30 – 40 ]. The possibility of injecting a contrast medium (Contrast-Enhanced Ultrasound (CEUS)) determines a technical evolution [ 30 ].…”

Predicting the Initial Treatment Response to Transarterial Chemoembolization in Intermediate-Stage Hepatocellular Carcinoma by the Integration of Radiomics and Deep Learning

“…In addition to clinical variables, the predictive performance of the radiomics model in the study was similar to that of our linear and logistic models but was lower than that of the SVM, RF, and GBM models, which revealed that the optimal feature selection is important for building a precise model. Unlike the engineered features model, the DL model as a novel method for image classification has been widely used in liver cancers (37)(38)(39). A DL model based on CT and gadoxetic acid-enhanced magnetic resonance imaging (EOB-MRI) seemed efficient for predicting microvascular invasion in HCC (40).…”

“…Unlike the engineered features model, the DL model as a novel method for image classification has been widely used in liver cancers ( 37 – 39 ). A DL model based on CT and gadoxetic acid-enhanced magnetic resonance imaging (EOB-MRI) seemed efficient for predicting microvascular invasion in HCC ( 40 ).…”

Diagnostic evaluation and ablation treatments assessment in hepatocellular carcinoma

“…The contrast agent spreads through the human body, emphasizing the vessel structure in the region of interest [22]. This technology leads to the highlighting of both large vessel flows, as well as of the microcirculation, being firstly implemented for hepatic tumor pathology, for abdominal emergencies and in order to recognize various tumor types [26][27][28][29][30][31][32][33][34][35][36]. The microbubbles of the contrast agent produce harmonic echoes, which are detected by the transducer.…”