Radiomics in the Diagnosis of Thyroid Nodules

Abstract

The thyroid nodules (TNs) are widespread throughout the world: according to the pathological studies, they can be found in 50–60% of adults. Currently, ultrasound, computed tomography, magnetic resonance imaging and radionuclide diagnostics, such as positron emission tomography with computed tomography, are usually used to diagnose TNs in clinic. These techniques are mainly used to diagnose the nodile benignity and malignancy, the degree of invasion into adjacent tissues and metastases to lymph nodes. Thanks to the development of artificial intelligence, machine learning and the improvement of medical imaging equipment, radiomics has become a popular area of research in recent years. It allowes to obtain various quantitative characteristics from medical images, highlighting invisible features and significantly expanding the possibilities of identifying and predicting. Radiomics has a high potential in detecting and predicting TNs. We present the information on the development and workflow of radiomics. The article summarizes the application of various imaging techniques to identify benign and malignant TNs, determine invasiveness and metastases to lymph nodes, as well as some new advances in the field of molecular level and deep learning. The disadvantages of radiomics method are also given as well as prospects for its further development.

Keywords

• thyroid nodules
• thyroid cancer
• radiomics
• computed tomography
• magnetic resonance imaging
• ultrasound
• artificial intelligence
• review