Browsing by Subject "Ultrasound imaging"

Now showing 1 - 2 of 2
  • Thumbnail Image
    Item
    Assessment of Deep Learning Methods for Differentiating Autoimmune Disorders in Ultrasound Images
    (Medical University Publishing House Craiova, 2021) Vasile, Corina Maria; Udriştoiu, Anca Loredana; Ghenea, Alice Elena; Padureanu, Vlad; Udriştoiu, Ştefan; Gruionu, Lucian Gheorghe; Gruionu, Gabriel; Iacob, Andreea Valentina; Popescu, Mihaela; Medicine, School of Medicine
    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.
  • Thumbnail Image
    Item
    Prenatal and Postnatal Sonographic Confirmation of Congenital Absence of the Ductus Venosus in a Child with Noonan Syndrome
    (hindawi publishing corporation, 2017) Newman, Christopher L.; Wanner, Matthew R.; Brown, Brandon P.; Radiology and Imaging Sciences, School of Medicine
    The ductus venosus serves as an important vascular pathway for intrauterine circulation. This case presents a description of an absent ductus venosus in a female patient with Noonan syndrome, including both prenatal and postnatal imaging of the anomaly. In the setting of the anomalous vascular connection, the umbilical vein courses inferiorly to the iliac vein in parallel configuration with the umbilical artery. This finding was suspected based on prenatal imaging and the case was brought to attention when placement of an umbilical catheter was thought to be malpositioned given its appearance on radiography. Ultrasound imaging confirmed the anomalous course. This is in keeping with prior descriptions in the literature of an association between Noonan syndrome and aberrant umbilical venous drainage. This case illustrates the need for awareness of this condition by the radiologist, allowing for identification on radiographs and the recommendation for further confirmatory imaging. Further, the case illustrates the value of paying particular attention to the fetal course of the umbilical vessels in patients with suspected Noonan syndrome, as this population is particularly at risk for anomalous vasculature.