PurposeThe aim of this study was to investigate the diagnostic efficacy of Acoustic Radiation Force Impulse (ARFI) for benign and malignant thyroid nodules in the presence and absence of non-papillary thyroid cancer (NPTC) and to determine the cut-off values of Shear Wave Velocity (SWV) for the highest diagnostic efficacy of Virtual Touch Quantification (VTQ) and Virtual Touch Tissue Imaging and Quantification (VTIQ).MethodsThe diagnostic accuracy of ARFI for benign and malignant thyroid nodules was assessed by pooling sensitivity, specificity and area under the curve (AUC) in each group in the presence and absence of both non-papillary thyroid glands, using histology and cytology as the gold standard. All included studies were divided into two groups according to VTQ and VTIQ, and each group was ranked according to the magnitude of the SWV cutoff value to determine the SWV cutoff interval with the highest diagnostic efficacy for VTQ and VTIQ.ResultsA total of 57 studies were collected on the evaluation of ARFI for the diagnosis of benign and malignant thyroid nodules. The results showed that the presence of non-papillary thyroid carcinoma led to differences in the specificity of VTIQ for the identification of benign and malignant thyroid nodules, and the differences were statistically significant. In addition, the diagnostic efficacy of VTQ was best when the cutoff value of SWV was in the interval of 2.48-2.55 m/s, and the diagnostic efficacy of VTIQ was best when the cutoff value of SWV was in the interval of 3.01-3.15 m/s.ConclusionVTQ and VTIQ have a high diagnostic value for benign and malignant thyroid nodules; however, when the malignant nodules in the study contain non-papillary thyroid carcinoma occupying the thyroid gland, the findings should be viewed in a comprehensive manner.

Artificial intelligence (AI), especially deep learning, is gaining extensive attention for its excellent performance in medical image analysis. It can automatically make a quantitative assessment of complex medical images and help doctors to make more accurate diagnoses. In recent years, AI based on ultrasound has been shown to be very helpful in diffuse liver diseases and focal liver lesions, such as analyzing the severity of nonalcoholic fatty liver and the stage of liver fibrosis, identifying benign and malignant liver lesions, predicting the microvascular invasion of hepatocellular carcinoma, curative transarterial chemoembolization effect, and prognoses after thermal ablation. Moreover, AI based on endoscopic ultrasonography has been applied in some gastrointestinal diseases, such as distinguishing gastric mesenchymal tumors, detection of pancreatic cancer and intraductal papillary mucinous neoplasms, and predicting the preoperative tumor deposits in rectal cancer. This review focused on the basic technical knowledge about AI and the clinical application of AI in ultrasound of liver and gastroenterology diseases. Lastly, we discuss the challenges and future perspectives of AI.

No abstract

ObjectiveThe aim of this study was to evaluate the accuracy of deep learning using the convolutional neural network VGGNet model in distinguishing benign and malignant thyroid nodules based on ultrasound images.MethodsRelevant studies were selected from PubMed, Embase, Cochrane Library, China National Knowledge Infrastructure (CNKI), and Wanfang databases, which used the deep learning-related convolutional neural network VGGNet model to classify benign and malignant thyroid nodules based on ultrasound images. Cytology and pathology were used as gold standards. Furthermore, reported eligibility and risk bias were assessed using the QUADAS-2 tool, and the diagnostic accuracy of deep learning VGGNet was analyzed with pooled sensitivity, pooled specificity, diagnostic odds ratio, and the area under the curve.ResultsA total of 11 studies were included in this meta-analysis. The overall estimates of sensitivity and specificity were 0.87 [95% CI (0.83, 0.91)] and 0.85 [95% CI (0.79, 0.90)], respectively. The diagnostic odds ratio was 38.79 [95% CI (22.49, 66.91)]. The area under the curve was 0.93 [95% CI (0.90, 0.95)]. No obvious publication bias was found.ConclusionDeep learning using the convolutional neural network VGGNet model based on ultrasound images performed good diagnostic efficacy in distinguishing benign and malignant thyroid nodules.Systematic Review Registrationhttps://www.crd.york.ac.nk/prospero, identifier CRD42022336701.