Abstract. The thyroid is arguably one of the most important parts of your body. As part of the endocrine system, this small gland in your neck secretes thyroid hormone, which is responsible for directing all your metabolic functions— that means controlling everything from digestion to mood to energy. When the thyroid malfunctions, it can affect every facet of your health. Both researchers and doctors are facing the challenges of fighting with thyroid diseases. In that thyroid disease is a major cause of formation in medical diagnosis and in the prediction, onset to which it is a difficult the medical research. Thyroid gland is one of the most important organs in our body. The secretions of thyroid hormones are culpable in controlling the metabolism. Hyperthyroidism and hypothyroidism are one of the two common diseases of the thyroid that releases thyroid hormones in regulating the rate of body’s metabolism. Early detection of thyroid diseases is the top priority for saving the livesof many. Typically, visual examination and manual techniques are used for these types of a thyroid disease’s diagnosis. This manual interpretation of medical images demands high time consumption and is highly prone to mistakes. Thus, In this paper we develop and apply a novel deep learning architecture to effectively detect and identify the presence of different thyroid diseases such as Hyperthyroidism,Hypothyroidism, Thyroid cancer, Thyroid nodules .Thisleads to earlier prediction of the presence of the disease and allows us to take prior actions immediately to avoid further consequences in an effective and cheap manner avoiding human error rate. A web application will also be developed in which an input scanned image will give the output of the type of thyroid disease saving a lot of time and money invested by the patients.

Keywords: Deep Learning, Thyroid Disease, Hyperthyroidism, Thyroid cancer

| DOI: 10.17148/IARJSET.2022.9207