Segmentation and classification of lungs CT-scan for detecting COVID-19 abnormalities by deep learning technique: U-Net model.

Background: Artificial intelligence (AI) techniques have been ascertained useful in the analysis and description of infectious areas in radiological images promptly. Our aim in this study was to design a web-based application for detecting and labeling infected tissues on CT (computed tomography) lung images of patients based on the deep learning (DL) method as a type of AI. Materials and Methods: The U-Net architecture, one of the DL networks, is used as a hybrid model with pre-trained densely connected convolutional network 121 (DenseNet121) architecture for the segmentation process. The proposed model was constructed on 1031 persons' CT-scan images from Ibn Sina Hospital of Iran in 2021 and some publicly available datasets. The network was trained using 6000 slices, validated on 1000 slices images, and tested against the 150 slices. Accuracy, sensitivity, specificity, and area under the receiver operating characteristics (ROC) curve (AUC) were calculated to evaluate model performance. Results: The results indicate the acceptable ability of the U-Net-DenseNet121 model in detecting COVID-19 abnormality (accuracy = 0.88 and AUC = 0.96 for thresholds of 0.13 and accuracy = 0.88 and AUC = 0.90 for thresholds of 0.2). Based on this model, we developed the "Imaging-Tech" web-based application for use at hospitals and clinics to make our project's output more practical and attractive in the market. Conclusion: We designed a DL-based model for the segmentation of COVID-19 CT scan images and, based on this model, constructed a web-based application that, according to the results, is a reliable detector for infected tissue in lung CT-scans. The availability of such tools would aid in automating, prioritizing, fastening, and broadening the treatment of COVID-19 patients globally.

The effect of disease-modifying antirheumatic drugs (DMARDs) on bone homeostasis in rheumatoid arthritis (RA) patients.

The autoimmune disease known as rheumatoid arthritis (RA) has been linked to the deterioration of bone. Bone erosion is a hallmark of RA and is linked to the severity of the disease as well as a poor functional result. Erosion of periarticular cortical bone is a common feature seen on plain radiographs of patients with RA. This characteristic feature is the result of excessive bone resorption and inadequate formation of bone. It has been determined that there is a complex interaction between the inflammatory condition seen in RA and bone destruction. Increased knowledge of the pathways and other mechanisms involved in osteoclastogenesis has resulted from advances in both animal and clinical investigations. Also, Biological and targeted medicines have modified RA's bone metabolism. Here, we provide a narrative overview of the literature on the pathomechanisms of bone structure involved in biological and targeted treatments for RA and also, the clinical implications of disease-modifying antirheumatic drugs (DMARDs) are discussed. In light of the fact that these newer treatments present patients with RA with new possibilities for disease improvement and symptom control, it is imperative that additional rigorous evidence be gathered to provide a clinical reference for both patients and their treating physicians.

Analyzing Survival Rate of Leukemia Patients Applying Long Term Exponential Model.

BACKGROUND: Making progressin treatment of all branches of cancers has increasedthe percent of patients that never experience the event of interest. These cases are called immune or cure and models for handling the data included cure fraction rate, are referred to as cure model or long-term survival models. METHODS: The data for this historical cohort study, were collected from leukemia patients diagnosed between 2007 to 2014 and followed up until 2016 in Taleghani hospital and received BMT (Bone Marrow Transplant). Some data had to be excluded because of incomplete information. Using recorded files mostly and phone calls rarely, were made to confirm whether the patients were still alive or not. Death due to leukemia was regarded as interested event. Analysis were performed by R version 3.4.1and Stata version 14. RESULTS: Number of recurrents after receiving BMT, pre-transplant Hb and age at diagnosis were found as significant prognostics of survival time. HD patients had the highest 5-years overall survival in category of diagnosis type with 81.3%. Cure fraction was estimated to be 64.1%. CONCLUSION: According to high percentage of censoring, using long-term model had better fit.

Short-term memory impairment in patients undergoing general anesthesia and its contributing factors.

BACKGROUND: Short-term memory disorder following surgery and anesthesia is a common complication of anesthesia and a common complaint of the patients. AIMS: This study was designed to assess memory impairment in patients undergoing elective surgery, investigate the effect of general anesthesia (GA) on memory, and identify the factors contributing to it, as well as the specific effect of anesthesia on each of the memory domains. SETTING AND DESIGN: This cross-sectional study was performed in a university hospital. METHODS AND MATERIALS: Patients with the American Society of Anesthesiologists (ASA) Class I, II, and III who were candidates for elective abdominal surgery were enrolled. Patients answered several questions based on the Wechsler Memory Scale-Revised V (WMS-R-V), a standardized questionnaire, minutes before entering the operating room (OR) and again after 24 h postoperation, and the differences were recorded. STATISTICAL ANALYSIS: Analysis was performed using T-independent and Chi-square tests with Pearson's coefficient and Fischer's exact test and Man-Whitney test. Data were analyzed using the Statistical Package for the Social Sciences (SPSS) software. RESULTS: Four hundred patients (198 females and 202 males) with a mean age of 50.75 years were enrolled in our study. Our study results showed that short-term memory after GA was significantly decreased compared with preanesthesia (P < 0.05). There was no significant relationship between memory disorder following GA and gender (P = 0.18) or comorbidities (P = 0.138). However, older age was found to be a contributing factor to memory loss following GA (P < 0.001). The highest and lowest effect of GA were found on the number repeat (45.2%) and personal information (16.2%) domain of the memory. CONCLUSION: GA significantly reduces the patient's short-term memory after the surgery.