Application of Artificial Intelligence in Ultrasonic Intelligent Diagnosis of Thyroid Nodule
XIAO Bingxin1,2, WU Guozhu2
1. Graduate School, Baotou Medical College, Inner Mongolia University of Science and Technology, Baotou Inner Mongolia 014040,
China; 2. Department of Ultrasound, Inner Mongolia Autonomous Region People’s Hospital, Hohhot Inner Mongolia 010017, China
Abstract:With the rapid development of high-frequency ultrasound and the wide application of new techniques, the ultrasonic
detection rate of thyroid noduleis improved correspondingly. However, the influence of subjective factors such as doctors’ experience
and technology, different doctors may have different results in discriminating benign and malignant of the same nodule. With the
improvement of the requirement for accurate and non-invasive discrimination of benign and malignant thyroid nodules, it is urgent to
explore a fast, accurate and objective imaging diagnosis method. In recent years, with the rapid development of artificial intelligence
(AI), more and more AI-based computational models have realized the accurate discrimination and segmentation of thyroid nodules,
as well as the accurate discrimination of benign and malignant nodules and lymph node metastasis, which reduced the subjective
diagnosis of physicians. This paper reviewed the application of AI in ultrasonic intelligent diagnosis of thyroid nodules, which can
help the clinic to better formulate the treatment policies and evaluate the prognosis of patients.