Artificial intelligence (AI), especially deep learning, is gaining extensive attentionfor its excellent performance in medical image analysis. It can automatically makea quantitative assessment of complex medical imag...Artificial intelligence (AI), especially deep learning, is gaining extensive attentionfor its excellent performance in medical image analysis. It can automatically makea quantitative assessment of complex medical images and help doctors to makemore accurate diagnoses. In recent years, AI based on ultrasound has been shownto be very helpful in diffuse liver diseases and focal liver lesions, such asanalyzing the severity of nonalcoholic fatty liver and the stage of liver fibrosis,identifying benign and malignant liver lesions, predicting the microvascularinvasion of hepatocellular carcinoma, curative transarterial chemoembolizationeffect, and prognoses after thermal ablation. Moreover, AI based on endoscopicultrasonography has been applied in some gastrointestinal diseases, such asdistinguishing gastric mesenchymal tumors, detection of pancreatic cancer andintraductal papillary mucinous neoplasms, and predicting the preoperative tumordeposits in rectal cancer. This review focused on the basic technical knowledgeabout AI and the clinical application of AI in ultrasound of liver and gastroenterologydiseases. Lastly, we discuss the challenges and future perspectives of AI.展开更多
基金the National Natural Science Foundation of China,No.82071953Medical Youth Top-notch Talent Project of Hubei Province
文摘Artificial intelligence (AI), especially deep learning, is gaining extensive attentionfor its excellent performance in medical image analysis. It can automatically makea quantitative assessment of complex medical images and help doctors to makemore accurate diagnoses. In recent years, AI based on ultrasound has been shownto be very helpful in diffuse liver diseases and focal liver lesions, such asanalyzing the severity of nonalcoholic fatty liver and the stage of liver fibrosis,identifying benign and malignant liver lesions, predicting the microvascularinvasion of hepatocellular carcinoma, curative transarterial chemoembolizationeffect, and prognoses after thermal ablation. Moreover, AI based on endoscopicultrasonography has been applied in some gastrointestinal diseases, such asdistinguishing gastric mesenchymal tumors, detection of pancreatic cancer andintraductal papillary mucinous neoplasms, and predicting the preoperative tumordeposits in rectal cancer. This review focused on the basic technical knowledgeabout AI and the clinical application of AI in ultrasound of liver and gastroenterologydiseases. Lastly, we discuss the challenges and future perspectives of AI.