Background: Gray-scale sonography is generally
considered as a first-line diagnostic tool for patient with
suspected acute cholecystitis. It is suggested by gallstones,
Murphy's sign, thickening of the gallbladder wall and bile
sludging, but the specificity of these sonographic findings
are not as high as their sensitivity. Blood flow of the
gallbladder wall is increased in acute inflammation.
Objective: To evaluate the sensitivity and specificity of
power Doppler sonography and compared with conventional
color Doppler and gray-scale sonography in diagnosing
patients with acute cholecystitis.
Type of the study: This was a cross sectional study.
Patients and methods: The study was conducted t

Background: Menstrual problems with all manifestations ranging from life-threatening bleeding to amen- orrhea are considered patterns of abnormal uterine bleeding (AUB), which is until now a popular reason for referral to the gynaecologic clinic and requires a special diagnostic tool. Objective: To assess the accuracy of hysteroscopy in diagnosing endometrial pathologies and to compare it with sonographic and histopathologic reports. Patients and Methods: A prospective study conducted in the Baghdad Teaching Hospital on 60 Iraqi females having varying complaints from abnormal uterine bleeding in pre- and post-menopausal women, infertility, and chronic pelvic pain with normal or abnormal ultrasound findings. Office hysteroscopy was done and

Background: Langerhans' cell histiocytosis (LCH) is a group of conditions affecting the reticuloendothelial system. It includes Letterer-Siwe disease, Hand-Schuller-Christian disease and eosinophilic granuloma and most often presents in childhood. Materials and methods: Twenty-five cases of LCH were diagnosed histologically and confirmed by CD1a antibody and assessed immunohistochemically using anti-RANKL and anti-RANK antibodies to evaluate osteoclastogenic mechanism. Results: Regarding jaw cases, there was a significant correlation between CD1a and RANK (P=0.016). While in the skull, highly significant correlation existed between RANK and RANKL (p=0.001). Among the sites, there was no statistically significant difference found for each

Axial spondyloarthritis (axSpA) is a chronic rheumatic inflammatory disease affecting mainly the spine and sacroiliac joints. Since the copper-to-zinc ratio (Cu/Zn) indicates an inflammatory response, the change in ratio is expected to correlate with axSpA. This study compared levels of Cu/Zn in the serum of axSpA patients. Serum samples were obtained from 53 patients with axSpA divided according to biological treatment into cohorts A and B, and 28 healthy control as cohort C. Serum levels of Cu and Zn were determined first by a fully automated chemistry analyzer TC-Matrix Plus, then the ratio was obtained. The elevated serum Cu concentration means of cohort B (189.32 ± 13.808 µg/dL) compared to cohort A (168.85 ± 7.244 µg/dL) a

Background: Trauma is one of the most common
clinical problems that confront the maxillofacial
surgeon and radiologist alike. Middle third facial
fractures are diagnosed primarily on the bases of
clinical examination and plain radiographs than can
result in much preoperative speculation.
Objective: To assess the advantages of spiral
computerized tomography over conventional
radiography in the pre-surgical evaluation of middle
third facial fractures.
Methods: Thirty patients with thirty-eight facial
fractures were studied, all patients were examined
clinically, by plain radiography and then by spiral CT.
Results: Of the 38 middle-third fractures, 16
(42.1%) were zygomatic fractures, 8 (21.1%) were

     Deep learning (DL) plays a significant role in several tasks, especially classification and prediction. Classification tasks can be efficiently achieved via convolutional neural networks (CNN) with a huge dataset, while recurrent neural networks (RNN) can perform prediction tasks due to their ability to remember time series data. In this paper, three models have been proposed to certify the evaluation track for classification and prediction tasks associated with four datasets (two for each task). These models are CNN and RNN, which include two models (Long Short Term Memory (LSTM)) and GRU (Gated Recurrent Unit). Each model is employed to work consequently over the two mentioned tasks to draw a road map of deep learning mod