Detection of early clinical keratoconus (KCN) is a challenging task, even for expert clinicians. In this study, we propose a deep learning (DL) model to address this challenge. We first used Xception and InceptionResNetV2 DL architectures to extract features from three different corneal maps collected from 1371 eyes examined in an eye clinic in Egypt. We then fused features using Xception and InceptionResNetV2 to detect subclinical forms of KCN more accurately and robustly. We obtained an area under the receiver operating characteristic curves (AUC) of 0.99 and an accuracy range of 97–100% to distinguish normal eyes from eyes with subclinical and established KCN. We further validated the model based on an independent dataset with

Deep learning convolution neural network has been widely used to recognize or classify voice. Various techniques have been used together with convolution neural network to prepare voice data before the training process in developing the classification model. However, not all model can produce good classification accuracy as there are many types of voice or speech. Classification of Arabic alphabet pronunciation is a one of the types of voice and accurate pronunciation is required in the learning of the Qur’an reading. Thus, the technique to process the pronunciation and training of the processed data requires specific approach. To overcome this issue, a method based on padding and deep learning convolution neural network is proposed to

ABSTRACT The present study was conducted to determine the mode of presentation of hypothyroidism in pediatric patients and the effects of timing of diagnosis and therapy on the patient’s outcome. The study involved review and evaluation of the medical records of 41 registered patients in the Endocrine clinic of Children Welfare Teaching Hospital in Baghdad during the period from January 1991 to July 2007. Forty one patients included in this study. Twenty four (58.5%) were males and17 (41.4%) were females with a male to female ratio of 1.4:1, their age range is 40 days to12.3 years. The majority of the studied patients were infants 19(47%). The most commonly observed presenting features were growth retardation and short stature. The best t

KE Sharquie, AA Noaimi, AH Muhammad Ali, 2008 - Cited by 3

Abstract: The present study aimed to evaluate calcium, potassium, albumin, protein, creatinine, urea, uric acid levels, and the level of total sialic acid in the sera of patients with chronic renal failure who had been infected with Hepatitis C virus and in the sera of patients with chronic renal failure, and compare them with healthy volunteers. A total of 90 subjects with age 25-55 years, were divided into three groups. G1 represents 30 patients with chronic renal failure who had treated by dialysis and infected with chronic Hepatitis C virus (positive group). G2 represents 30 patients with chronic failure who had been treated by dialysis (negative group), while G3 represents 30 healthy volunteers (control group). The results showed

Background: Epilepsy is a common neurological disorder of incidence rate 1-2%. Genetic, congenital, developmental, tumors, head trauma and central nervous system infections maybe the cause of epilepsy. This study aimed to determine the prevalence of stomatitis, xerostomia and taste disorder among patients taking carbamazepine or sodium valproate and to make salivary analysis for IgA, cystatin c and salivary flow rate. Material and method:This study performed in al- Yarmuk teaching hospital in Baghdad, Samples consist of (70) epileptics half of them treated with carbamazepine and other half treated with sodium valproate, and (18) healthy control group of both genders and with different ages to detect the prevalence of oral manifestations, s

Background: Endometrial Cancer (EC) is the malignant tumor originating from endometrium cell (lining of the uterus). EC incidence and mortality have increased in recent years. Routinely used methods for EC diagnosis and treatment are histopathological tissue culture after surgery and postoperative radiotherapy, however there is still not enough efficient treatment for recurrence or progression of this disease. So, there is a critical need for further EC identification by new biological ways for the prognostic diagnosis of it. Objective: This study aimed to look for ways by which could help in diagnosis of EC before the hysterectomy. Materials and Methods: 55 patients with EC and 57 healthy women were involved in this study (up to 45 years)

Bedside clinical teaching is a fundamental part of the medical education that offers invaluable opportunities for the students to build and improve their clinical and communication skills. However, there is a growing concern about the increasing refusal of patients to participate in clinical sessions, especially in certain settings where there are sensitive cultural traditions and decreased trust in institutions.