ABSTRACT
At present, deep learning becomes an important tool in medical image analysis, with good performance in diagnosing, pattern detection, and segmentation. Ultrasound imaging offers an easy and rapid method to detect and diagnose thyroid disorders. With the help of a computer-aided diagnosis (CAD) system based on deep learning, we have the possibility of real-time and non-invasive diagnosing of thyroidal US images. This paper proposed a study based on deep learning with transfer learning for differentiating the thyroidal ultrasound images using image pixels and diagnosis labels as inputs. We trained, assessed, and compared two pre-trained models (VGG-19 and Inception v3) using a dataset of ultrasound images consisting of 2 types of thyroid ultrasound images: autoimmune and normal. The training dataset consisted of 615 thyroid ultrasound images, from which 415 images were diagnosed as autoimmune, and 200 images as normal. The models were assessed using a dataset of 120 images, from which 80 images were diagnosed as autoimmune, and 40 images diagnosed as normal. The two deep learning models obtained very good results, as follows: the pre-trained VGG-19 model obtained 98.60% for the overall test accuracy with an overall specificity of 98.94% and overall sensitivity of 97.97%, while the Inception v3 model obtained 96.4% for the overall test accuracy with an overall specificity of 95.58% and overall sensitivity of 95.58.
ABSTRACT
Thyroid hormones are critical regulators of growth, myelination of the nervous system, metabolism, and organ function. The most prevalent endocrinopathies in childhood are related to thyroid disorders. Thyroid problems in children and adolescents have a significantly different etiology and clinical presentation than in adults. Thus, pediatric medical care involves an understanding of the unique features of thyroid function and dysfunction during childhood and adolescence. The etiology and clinical manifestations of thyroid disorders in children and adolescents are vastly different from those in adults. The particular aspects of thyroid function and malfunction in childhood and adolescence are hence part of pediatric medical therapy. To prevent persistent nervous system damage and developmental problems, it is vital to recognize and treat thyroid dysfunction in neonates as early as possible. The purpose of the research was to understand more how children's thyroid problems function, structure, and prevalence. The research examined 30 children under the age of 16 years who had symptoms that were linked to thyroid problems. In addition to demographic and family information, thyroid ultrasounds and blood samples for the detection of T3, T4, and TSH were obtained. Females surpassed males by a small majority (2.33:1 ratio).Out of the total children included in the study, 14(46.7%) cases for autoimmune thyroiditis, 2(6.67%) cases for congenital hypothyroidism, 1(3.33%) case for hyperthyroidism, 1(3.33%) case for hyperthyroidism-Graves disease, 8(26.7%) cases for hypothyroidism and 4(13.3%) cases for subclinical hypothyroidism.
