A Survey on Thyroid Nodule Detection and Classification

The prevalence of thyroid cancer (TC) and thyroid nodule disorders is increasing rapidly. Thyroid Gland (TG) can develop thyroid carcinoma which is a frequent endocrine cancer, and over-diagnosis is a factor in occurrence of TC in India. Artificial intelligence (AI) can comprehend digital images and contribute to the creation of a system that can identify thyroid nodules. As a result, several researchers are creating computer-aided-diagnostic (CAD) systems that diagnose TC using Machine Learning (ML) and Deep Learning (DL) algorithms to distinguish between benign and malignant thyroid nodules based on US imaging. ML and DL methods use a series of algorithms to retrieving features from ultrasound (US) images and classify thyroid nodules as benign and malignant nodules. So, these algorithms make radiologists to take specific decision regarding early diagnoses and over diagnoses. The paper gives an overview of current research on TC detection based on US images using ML algorithms. It also presents advancements in TC detection using DL algorithms. The information present in this paper is taken from published work of researchers in thyroid cancer with references.