Objectives:Epilepsy is one of the most common chronic neurologic disorders in childhood and it affects 0.5-1% of children. The purpose of the study was to determine the prevalence and types of structural abnormalities in the epileptic children.Methods:The study was performed in Near East University and Dr. Suat Gunsel University in North Cyprus. It was conducted at pediatric neurology outpatient clinic of the hospital. The records of 1 to 18 years old epileptic children in whom Magnetic Resonance Imaging (MRI) performed within 6 months after diagnosis were enrolled to the study between the dates of October 2011 and June 2017.Results:Among 220 children; 131 (59.55%) had no abnormality and 89 (45.45%) had at least one abnormality in the MRI. Most commonly documented lesions were generally encephalomalacia, hydrocephaly and brain atrophy with a percent of 5.90 (13 cases), 5.45 (12 cases) and 4.55 (10 cases) respectively. Sixty nine (31.06%) of the patients had one abnormality whereas 20 (9.09%) had two or more lesion.Conclusion:Abnormality in MRI examination in newly diagnosed epileptic children was high. These high rates may be due to enrollment of children with new emerging epilepsy on a chronical neurologic disorder. Additionally 20 (9.09%) of patients had a concomitant lesion. Secondary lesions were detected in cases with corpus callosum abnormality, atrophy, encephalomalacia and hydrocephaly. Primarily formed lesions are unknown; further studies are needed to confirm these findings.

The aim of this study is to determine the prevalence of pathologic findings in asymptomatic knees of Kangoo Jumpers by using a 3T MRI and to compare them with age and sex-matched controls who do not regularly participate in any impact sports. Methods: Both knees of 18 Kangoo Jumpers were examined by 3T MRIs in a total of 36 MRI scans. The control group was comprised of 20 volunteers from the same age group and with similar weights who did not participate in any competitive sports, in a total of 40 MRI scans. Two orthopedists and one radiologist independently assessed all images for the presence or absence of any abnormalities. Results: In 32 (88.9%) of the 36 Kangoo Jumpers' knees, one or more abnormalities were observed. The most prevalent abnormality was bone marrow edema, which was detected in 32 knees (88.9%). The other significant findings were quadriceps tendinopathy (80.6%), patellar tendinopathy (63.9%), gastrocnemius tendinopathy (63.9%), infrapatellar fat pad edema (75%), suprapatellar fat pad edema (63.9%), meniscal signal change (72.2%) and cartilage damage in the patellofemoral joint (72.2%). There were no statistically significant differences in terms of joint effusion (8.3%), ganglion cysts (8.3%) or tibiofemoral joint cartilage injury (0%). Conclusion: This study reveals many types of knee MRI findings of asymptomatic Kangoo Jumpers compared to the control group. These MRI findings may be associated with acute knee injuries or chronic joint problems such as osteoarthritis, which may develop in long-term follow-up studies.

Introduction: Epilepsy is one of the most frequently diagnosed chronic neurological disorders in children. Diagnosis is often based on seizure history and electroencephalography (EEG) assessment. Magnetic resonance imaging (MRI) is recommended for etiologic workup and intervention requirements. We aimed to detect by MRI if focal structural abnormalities are present in the brain in relation to interictal epileptiform discharges (IED). Material and Methods: The study was designed retrospectively. The data were collected from patients admitted to Near East University, Department of Pediatric Neurology, who were aged between 3 months and 18 years and who were diagnosed with epilepsy. The cases considered in the current study, however, were patients that had an EEG record prior to initiating treatment and an MRI within the first six months following diagnosis. Results: Among 222 patients, 212 (95.5%) had IED, and 92 (41.4%) had abnormal MRI results. The most frequently seen abnormalities detected by MRI were encephalomalacia, hydrocephaly, and atrophy. Among patients who had IED, the ones with multifocal IED were documented to have a statistically significant higher rate of abnormalities in MRI scans. In other patients, IED had no significant correlation with structural lesions detected by MRI. Conclusion: IED can be unrelated to MRI findings. Focal IED were not statistically concordant with the structural lesions detected by MRI. However, for the cases with multifocal discharges revealed by interictal EEG, the rate of abnormalities detected using MRI was 68%. Therefore, the likelihood of detecting abnormalities using MRI in patients with multifocal IED does support the necessity of the use of MRI in early diagnosis stages.

Healthcare is one of the crucial aspects of the Internet of things. Connected machine learning-based systems provide faster healthcare services. Doctors and radiologists can also use these systems for collaboration to provide better help to patients. The recently emerged Coronavirus (COVID-19) is known to have strong infectious ability. Reverse transcription-polymerase chain reaction (RT-PCR) is recognised as being one of the primary diagnostic tools. However, RT-PCR tests might not be accurate. In contrast, doctors can employ artificial intelligence techniques on X-ray and CT scans for analysis. Artificial intelligent methods need a large number of images; however, this might not be possible during a pandemic. In this paper, a novel data-efficient deep network is proposed for the identification of COVID-19 on CT images. This method increases the small number of available CT scans by generating synthetic versions of CT scans using the generative adversarial network (GAN). Then, we estimate the parameters of convolutional and fully connected layers of the deep networks using synthetic and augmented data. The method shows that the GAN-based deep learning model provides higher performance than classic deep learning models for COVID-19 detection. The performance evaluation is performed on COVID19-CT and Mosmed datasets. The best performing models are ResNet-18 and MobileNetV2 on COVID19-CT and Mosmed, respectively. The area under curve values of ResNet-18 and MobileNetV2 are 0.89% and 0.84%, respectively.

No abstract