A Survey on Diagnosis of US Image Thyroid Nodules and Automated Classification

Different types of human diseases are detected by medical image analysis which plays an important role. Studies that are developed for automated thyroid cancer classification is reviewed in this paper, especially to analyze the benign and malignant thyroid nodules features and comparisons. Hypothyroidism, hyperthyroidism, goitre and thyroid nodules (benign/malignant) are thyroid disorders. Ultrasound imaging, CT, MR imaging, nuclear medicine (NM) with positron emission tomography (PET), single photon emission computed tomography (SPECT) are the different medical techniques used to identify and classify thyroid gland abnormalities. In order to enhance the diagnosis of thyroid disease, various image processing techniques applied to thyroid ultra sound images are reviewed here. Studies based on non-clinical features for thyroid nodules classification is also discussed and reviewed.