Efficient differential privacy enabled federated learning model for detecting COVID-19 disease using chest X-ray images.

The rapid spread of COVID-19 pandemic across the world has not only disturbed the global economy but also raised the demand for accurate disease detection models. Although many studies have proposed effective solutions for the early detection and prediction of COVID-19 with Machine Learning (ML) and Deep learning (DL) based techniques, but these models remain vulnerable to data privacy and security breaches. To overcome the challenges of existing systems, we introduced Adaptive Differential Privacy-based Federated Learning (DPFL) model for predicting COVID-19 disease from chest X-ray images which introduces an innovative adaptive mechanism that dynamically adjusts privacy levels based on real-time data sensitivity analysis, improving the practical applicability of Federated Learning (FL) in diverse healthcare environments. We compared and analyzed the performance of this distributed learning model with a traditional centralized model. Moreover, we enhance the model by integrating a FL approach with an early stopping mechanism to achieve efficient COVID-19 prediction with minimal communication overhead. To ensure privacy without compromising model utility and accuracy, we evaluated the proposed model under various noise scales. Finally, we discussed strategies for increasing the model's accuracy while maintaining robustness as well as privacy.

Morphometric Analysis of the Mandibular Canal, Anterior Loop, and Mental Foramen: A Cone-Beam Computed Tomography Evaluation.

This study investigated the cone-beam computed tomography (CBCT)-based features of the mandibular canal, mental foramen, anterior loop, and accessory mental foramina with respect to age and sex. A total of 306 CBCT mandibular images were included in this retrospective study to measure the mandibular canal location and extension, the mental foramen position, the presence of the anterior loop, and the accessory mental foramina. The measurements were obtained in sagittal, coronal, and axial views. Descriptive statistics are presented. Sex-related differences, correlations, and comparisons were calculated using SPSS at 5% significance level. The mandibular canal was located more coronal and medial in male patients. The majority of cases had the mental foramen located just apical to the mandibular second premolar with a mean height of 2.94 mm and a mean length of 3.28 mm. Age affected the size of the mental foramen. The mental canal in all cases tended to show a coronal direction. Mesial extension of the anterior loop was found in 66.01% of the images while accessory mental foramina were detected in 2.6%. The complexity of the mandibular canal, mental foramen, anterior loop, and accessory mental foramina among Sudanese patients with respect to age and sex was confirmed.

Prevalence of Theileria annulata in dairy cattle in Nyala, South Darfur State, Sudan.

AIM: This study was conducted in dairy cattle in Nyala, South Darfur State, during the period from June to September 2015, to study the prevalence of bovine tropical theileriosis. MATERIALS AND METHODS: Apparently, healthy cattle of different age groups, different breeds, and from both sexes were randomly selected from seven locations. Three age groups of cattle were selected, group one <1 year old, group two 1-3 years old, and group three older than 3 years. These cattle were indigenous and cross (Friesian X zebu). A total of 150 blood samples were collected for blood smears, blood in EDTA tubes, and serum samples as well as ticks infesting cattle. Three diagnostic techniques were used such as blood smear, indirect fluorescent antibody test (IFAT), and polymerase chain reaction (PCR). RESULTS: Of 150 samples, 11 (7.3%, 95% confidence interval [CI]: 9.1-5.5) were positive for Theileria spp. piroplasms in the blood smears, 70 (46.7%, 95% CI: 35.7-57.7) were positive for Theileriaannulata antibodies in the IFAT, and of 100 samples, 39 (39%, 95% CI: 46.6-31.4) were positive for T. annulata using PCR. The prevalence of T. annulata was higher in indigenous breed than cross cattle by the three diagnostic techniques. The highest prevalence of T. annulata was recorded among cattle older than 3 years old. There were three genera and ten species of ticks found feeding on cattle. These were Rhipicephalus evertsi evertsi, Rhipicephalus decoloratus, Rhipicephalus annulatus, Hyalomma dromedrii, Hyalomma impeltatum, Hyalomma rufipes, Hyalomma anatolicum, Hyalomma truncatum, Amblyomma variegatum, and Amblyomma lepidum. CONCLUSION: The study concluded that tropical theileriosis is prevalent among dairy cattle in Nyala. H. anatolicum was found in very low numbers, suggesting other ticks may play a role in the transmission of the disease. Molecular characterization of T. annulata is recommended for accurate mapping of the disease and evaluates the magnitude problem of tropical theileriosis in South Darfur region.