Early Online (Volume - 4 | Issue - 8) at IgMin Research

The present paper demonstrates kidney disease recognition in computed tomography (CT) images using deep neural networks, including convolutional neural networks (CNNs), the visual geometry group (VGG) network, and the deep residual network (ResNet-50). The kidney disease dataset consists of images among four categories, i.e cyst, normal, stone, and tumor. The class “cyst” consists of 3,709 images, the class “normal” consists of 5,077 images, the class “stone” consists of 1,377 images, and finally the class &l...dquo;tumor” consists of 2,283 images. In total, the dataset has 12,446 images. This dataset was passed through the deep CNN, VGG19, and ResNet-50 models to obtain the results. The major novelty of this work compared to previous works is that the algorithms of the CNN and ResNet-50 models have been modified, compared to existing works. The results, such as error/positive-predictive-value (PPV), error/probability of detection (POD), and error/area under the curve (AUC) curves, are shown for the confirmation of the work. Further, the error matrix, specificity/POD, and PPV/POD curves are also shown for the justification of the work. Finally, the performance metrics such as accuracy, PPV, POD, and F1-score values obtained from the error matrix are also shown for the justification of the work. The CNN model has achieved an accuracy of 0.95 for class “cyst”, 0.82 for class “normal”, 0.89 for class “stone”, and 0.87 for class “tumor”. The VGG19 neural network model has achieved an accuracy of 0.95 for class “cyst”, 0.79 for class “normal”, 0.84 for class “stone”, and 0.89 for class “tumor”. The ResNet-50 neural network model has achieved an accuracy of 0.92 for class “cyst”, 0.82 for class “normal”, 0.84 for class “stone”, and 0.92 for class “tumor”. The deep CNN model has achieved an area under the curve (AUC) value of 0.98 for class “cyst”, 0.87 for class “normal”, 0.92 for class “stone”, and 0.91 for class “tumor”. The deep CNN model has the highest AUC value for class “cyst” compared to other classes. The VGG19 model has an AUC value of 0.99 for class “cyst”, 0.92 for class “normal”, 1.00 for class “stone”, and 0.96 for class “tumor”. The VGG19 model has the highest AUC value for class “stone” compared to other classes. The ResNet-50 model has AUC values of 0.96 for class “cyst”, 0.92 for class “normal”, 0.92 for class “stone”, and 0.86 for class “tumor”. The ResNet-50 model has the highest AUC value for class “cyst” compared to the other classes.Read more

High-voltage direct-current (HVDC) transmission schemes are designed for high transfer capability and long-distance delivery. Still, their reliability can be significantly affected by lightning, as even relatively infrequent lightning faults can interrupt large power transfers. This study examines the lightning performance of the positive and negative poles of the Inga–Kolwezi ±500 kV HVDC scheme in the Democratic Republic of Congo, with particular attention to the unusual configuration in which the two poles are implemented as ind...ependent monopolar lines. The supplied technical record describes a 517 km section of the approximately 1,700 km scheme and provides system, fault, lightning-exposure and lightning-detection information. The methodology combines a review of the line configuration and insulation parameters, analysis of operational fault records, and interpretation of Fault Analysis and Lightning Location System (FALLS) Small Area Exposure (SAE) data over ten years from 1 April 2010 to 1 April 2020 within a 1 km buffer around each line. The theoretical interpretation is based on electro-geometric and leader-progression concepts and on the polarity-dependent interaction between the DC operating voltage and negative downward lightning. The source record reports lightning-related faults between 2015 and 2023, including ten shielding-failure events and five back-flashovers, with shielding-failure events associated with comparatively low peak currents, including 15 and 35 kA, while back-flashovers are associated with much higher reported amplitudes of 105 and 135 kA. The supplied material further indicates that a positive 500 kV pole can have a substantially increased shielding-failure rate under a negative downward leader, whereas the negative pole is more susceptible to direct negative-stroke flashover and the positive pole to back-flashover. These results support the conclusion that lightning performance cannot be evaluated from shielding geometry alone; pole polarity, conductor position, insulation coordination, grounding and the quality of lightning-location data must be considered jointly. The principal recommendation is therefore to complete the comparative assessment with pole-specific exposure and outage denominators and to use the resulting dataset to calibrate protection and maintenance priorities along the two independent lines.Read more

Background: Helicobacter pylori infection is a major cause of gastroduodenal diseases and is strongly associated with gastric carcinogenesis. Endoscopy plays a key role in identifying mucosal lesions related to this infection. However, data on the endoscopic aspects of H. pylori–associated lesions remain scarce in Cameroon. This study aimed to describe the endoscopic features of lesions associated with Helicobacter pylori infection in two hospitals in Douala over a three-year period.Methods: This analytical cross-sectional study included ...842 patients who underwent upper gastrointestinal endoscopy with gastric biopsies. The diagnosis of H. pylori infection was established using histology (reference method), rapid urease testing, and bacterial culture. Histological lesions, including mononuclear and polymorphonuclear infiltration, glandular atrophy, and intestinal metaplasia, were assessed according to the updated Sydney classification and compared according to H. pylori infection status.Results: The prevalence of H. pylori infection was 73.2% by histology, 67.7% by rapid urease test, and 42.9% by bacterial culture. The most common endoscopic lesions were superficial gastritis (28.4%) and erosive gastritis (22.3%), followed by duodenal ulcers (16.8%) and gastric ulcers (10%). The prevalence of H. pylori infection was particularly high in duodenal ulcers (91.9%), gastric ulcers (82.1%), and gastric cancer (100%). High positivity rates were also observed in superficial gastritis (70.7%), erosive gastritis (64.9%), and patients with normal endoscopic findings (63.6%). H. pylori infection was significantly associated (p < 0.01) with severe mononuclear and polymorphonuclear infiltration, glandular atrophy, and intestinal metaplasia.Conclusion: This study confirms the high prevalence of H. pylori infection and its significant association with inflammatory, ulcerative, and precancerous gastric lesions. These findings support the major role of H. pylori in the pathophysiological cascade leading to gastric cancer and highlight the importance of early detection and eradication strategies.Read more