Medical imaging is an essential and valuable tool in modern medicine for providing essential details on the internal structures and functioning of the human body. Although very useful, the raw images obtained from medical imaging systems usually contain different types of artifacts and noise that might hide some essential diagnostic information. In this paper, the author details the conventional and non-conventional methods as well as sophisticated deep learning research methods used in improving the quality of healthcare images. The paper also delves into strategies designed to elevate the visual quality and interpretability in medical diagnostics. The paper includes some latest case studie... More >

Understanding the dynamic interaction between the amygdala and the ventromedial prefrontal cortex (vmPFC) is essential for unraveling the neural mechanisms underlying emotion regulation. This study introduces a multidimensional analytical framework that integrates functional connectivity, time-lagged correlation, Granger causality analysis (GCA), and entropy-based complexity metrics to explore the amygdala–vmPFC relationship during emotionally aversive tasks using intracranial EEG (iEEG) data. Our findings reveal a significant negative functional correlation (r = -0.009, p < 0.05) between the amygdala and vmPFC, indicating an inhibitory relationship. Time-lagged correlation analysis furthe... More >

Diabetic Retinopathy occurs when elevated blood sugar levels damage retinal blood vessels, potentially leading to vision impairment. In this paper, we have tested the performance of CNN, ViT and their hybrid models. The dataset used is publicly available on Kaggle and the dataset contained around 35,000 retinal images which were divided into 5 classes namely No DR, Mild DR, Moderate DR, Severe DR and Proliferative DR. In CNN we tested 4 different architectures in which we achieved the best accuracy of 75.4% with Resnet50 architecture and with ViT model we achieved an accuracy of 83.9% and from the hybrid model we achieved an accuracy of 88.4% from the Resnet50 + ViT. The results shown by the... More >

The COVID-19 pandemic exerted immense pressure on healthcare systems globally, including in Morocco, where the demand for intensive care unit (ICU) beds frequently surpassed available capacity—at times doubling it. This crisis underscored the critical need for accurate prediction of ICU length of stay (LOS) to optimize resource allocation, enhance patient care, and reduce healthcare costs. This study aims to leverage artificial intelligence (AI) to predict and optimize ICU resource allocation during the COVID-19 crisis, ensuring efficient patient triage and resource management. By integrating Random Forest (RF) and Deep Neural Networks (DNN), the research demonstrates improved accuracy in... More >

Healthcare decision support framework(HDSF), a comprehensive web application framework designed to revolutionize healthcare accessibility and efficiency. HDSF integrates various facilities including online appointment booking, virtual doctor consultations, symptom detection, detailed prescription management, home nursing appointment scheduling, and updates on local health camps with Google Maps integration for navigation. The application employs a robust architecture with a front end developed using HTML, CSS, and Bootstrap, while the back-end leverages Java and Java Servlet technologies. Data management is facilitated by MySQL, and the application is developed within the Eclipse IDE and XAM... More >