Steffensencompton9356

The obtained results are in the range of human inter-rater performance for all structures. Moreover, we investigate the method's robustness against noise and demonstrate the generalization capability for varying ratios of labeled data and on other challenging tasks, namely the hippocampus and skin lesion segmentation. UATS achieved superiority segmentation quality compared to the supervised baseline, particularly for minimal amounts of labeled data.The segmentation and analysis of coronary arteries from intravascular optical coherence tomography (IVOCT) is an important aspect of diagnosing and managing coronary artery disease. Current image processing methods are hindered by the time needed to generate expert-labelled datasets and the potential for bias during the analysis. Therefore, automated, robust, unbiased and timely geometry extraction from IVOCT, using image processing, would be beneficial to clinicians. With clinical application in mind, we aim to develop a model with a small memory footprint that is fast at inference time without sacrificing segmentation quality. Using a large IVOCT dataset of 12,011 expert-labelled images from 22 patients, we construct a new deep learning method based on capsules which automatically produces lumen segmentations. Our dataset contains images with both blood and light artefacts (22.8 %), as well as metallic (23.1 %) and bioresorbable stents (2.5 %). We split the dataset into a training (70 %), validation (20 %) and test (10 %) set and rigorously investigate design variations with respect to upsampling regimes and input selection. We show that our developments lead to a model, DeepCap, that is on par with state-of-the-art machine learning methods in terms of segmentation quality and robustness, while using as little as 12 % of the parameters. This enables DeepCap to have per image inference times up to 70 % faster on GPU and up to 95 % faster on CPU compared to other state-of-the-art models. DeepCap is a robust automated segmentation tool that can aid clinicians to extract unbiased geometrical data from IVOCT.Bronchopulmonary dysplasia (BPD) has the main manifestations of pulmonary edema in the early stage and characteristic alveolar obstruction and microvascular dysplasia in the late stage, which may be caused by structural and functional destruction of the lung epithelial barrier. The Claudin family is the main component of tight junction and plays an important role in regulating the permeability of paracellular ions and solutes. Claudin-18 is the only known tight junction protein solely expressed in the lung. The lack of Claudin-18 can lead to barrier dysfunction and impaired alveolar development, and the knockout of Claudin-18 can cause characteristic histopathological changes of BPD. This article elaborates on the important role of Claudin-18 in the development and progression of BPD from the aspects of lung epithelial permeability, alveolar development, and progenitor cell homeostasis, so as to provide new ideas for the pathogenesis and clinical treatment of BPD.Neonatal hypoxic-ischemic brain damage (HIBD) remains an important cause of neonatal death and disability in infants and young children, but it has a complex mechanism and lacks specific treatment methods. As a new type of programmed cell death, ferroptosis has gradually attracted more and more attention as a new therapeutic target. This article reviews the research advances in abnormal iron metabolism, glutamate antiporter dysfunction, and abnormal lipid peroxide regulation which are closely associated with ferroptosis and HIBD.Coronavirus disease 2019 (COVID-19) has become a worldwide pandemic and can occur at any age, including children. Children with COVID-19 can develop the clinical symptoms of multiple systems, among which symptoms of the nervous system have been reported increasingly, and thus it is particularly important to understand COVID-19-associated neurological damage in children. find more This article reviews the mechanisms and types of COVID-19-associated neurological damage in children.A boy, aged 3 years and 8 months, had recurrent thrombocytopenia with hemolytic anemia for more than 3 years. The physical examination showed no enlargement of the liver, spleen, and lymph nodes or finger deformities. Laboratory results showed a negative result of the direct antiglobulin test, normal coagulation function, and increases in bilirubin, lactate dehydrogenase and reticulocytes. The results of von Willebrand factor-cleaving protease ADAMTS13 activity assay showed extreme deficiency, and antibody assay showed negative ADAMTS13 inhibitory autoantibodies. Next-generation sequence showed compound heterozygous mutation in the ADAMTS13 gene. The boy was diagnosed with congenital thrombotic thrombocytopenic purpura. This disease may be easily misdiagnosed as Evans syndrome and is difficult to diagnose in clinical practice. The child had developed the disease since birth, but it took 3 years to make a confirmed diagnosis. Therefore, congenital thrombotic thrombocytopenic purpura should be considered for children with jaundice at birth, recurrent thrombocytopenia with hemolytic anemia, and negative results of the direct antiglobulin test. The detection of ADAMTS13 activity and ADAMTS13 inhibitory autoantibodies should be performed as soon as possible for a definite diagnosis, and gene detection should be performed to make a confirmed diagnosis when necessary.Rapid-onset obesity with hypothalamic dysfunction, hypoventilation, and autonomic dysregulation syndrome (ROHHADS) is a rare multi-system disease, and delayed diagnosis and treatment may lead to catastrophic cardiopulmonary complications. As far as we know, no patient with ROHHADS has been reported in China, and this article reports a child with ROHHADS to improve the awareness of this disease among clinicians. A girl, aged 3 years, had the clinical manifestations of rapid weight gain, fever, disturbance of consciousness, and convulsion. The physical examination showed a body weight of 20 kg, somnolence, irregular breathing, and stiff neck. She had increased blood levels of prolactin and follicle-stimulating hormone and hyponatremia. The lumbar puncture showed an increased intracranial pressure. The brain MRI and magnetic resonance venography showed symmetrical lesions in the periventricular region and venous thrombosis in the right transverse sinus and the superior sagittal sinus. The sleep monitoring showed hypopnea.