Research progress of deep learning in ultrasound diagnosis of thyroid nodules
Thyroid nodules are common in the population,and their evaluation is mainly based on thyroid Imaging reporting and data system.The accuracy of thyroid nodule diagnosis in ultrasound examination is closely related to the examination skills,clinical experience and thinking and analysis ability of sonographers.In recent years,the incidence of thyroid cancer has increased rapidly.How to improve the ability of preoperative diagnosis of thyroid nodules quickly and effectively in our country has become an urgent problem to be solved.As a new technology in the field of artificial intelligence,deep learning has been gradually applied in the field of medical imaging,and has attracted much attention in thyroid ultrasound diagnosis.This paper will introduce the research progress and application value of deep learning in ultrasound diagnosis of thyroid nodules from the aspects of ultrasound image segmentation of thyroid nodules,differentiation of benign and malignant nodules,histopathological prediction of nodules,and intelligent evaluation of cervical lymph nodes.The purpose of this review is to summarize the previous relevant studies to assist physicians to deeply understand the development status of this field and explore new research directions,so as to provide more accurate and comprehensive reference information for the clinical diagnosis and treatment of thyroid nodules in the future.
deep learningultrasoundthyroid nodulesartificial intelligence
万方数据
维普
