Adham Aleid

Improving student engagement and comprehension of complex theoretical concepts re-mains a persistent challenge in biomedical engineering education. This study proposes a smartphone-based augmented reality (AR) framework for simulating medical devices and evaluates its impact on student learning, interaction, and engagement. Unlike conventional approaches, the proposed method integrates low-cost, accessible AR models of key biomedical equipment—MRI, centrifuge, and defibrillator—developed using SolidWorks, Blender, and Unity, enabling real-time visualization in classroom settings. A cross-sectional study involving 77 biomedical engineering students at King Saud University was conducted using a structured questionnaire following an AR-based instructional session. The results demonstrate high levels of student acceptance and perceived effectiveness, with 88% of participants reporting improved understanding and motivation, 80% indicating enhanced comprehension of complex devices, and 90% supporting the larger adoption of AR across curricula. The findings highlight the potential of AR to bridge the gap between theoretical knowledge and practical visualization, particularly in resource-limited educational environments where access to physical equipment is constrained. Despite these promising outcomes, challenges related to infrastructure, accessibility, and instructor readiness re-main critical considerations. This study contributes to the growing body of research on immersive learning technologies by presenting a scalable and cost-effective AR-based educational approach, while emphasizing the need for further investigation using objective performance metrics and larger populations to validate its long-term educational impact.

This study introduces an innovative method for minimizing artifacts in electroencephalography (EEG) signals by integrating brainstorm optimization (BSO) with a variational autoencoder generative adversarial network (VAE-GAN), resulting in the BrOpt_VAGAN model. EEG signals are critical for the diagnosis of neurological disorders, for brain-computer interface (BCI) applications, and for the monitoring of neurological disabilities. However, EEG data often contains artifacts from physiological sources — such as electrooculographic (EOG), electromyographic (EMG), and electrocardiographic (ECG) signals — which can distort the accuracy of brain activity readings. Our proposed BrOpt_VAGAN model combines BSO with a VAE-GAN framework to more effectively remove these artifacts, thus improving the clarity and accuracy of EEG signals. In this model, the VAE first reduces the raw EEG signals into a lower-dimensional representation that captures the essential signal patterns while filtering out the noise. The GAN component then refines this representation via adversarial training, effectively minimizing artifacts and improving the quality of the processed EEG data. BSO optimally adjusts the encoding and decoding parameters within the VAE-GAN structure, enabling the model to handle different noise levels and helps to find different neurological disorders. Preliminary results show that BrOpt_VAGAN performs significantly better with an accuracy of 98.5 % and an error rate of 11.23 %, enabling a clearer and more precise EEG signal reconstruction.

This study introduces a novel deep-learning methodology that is customized to automatically diagnose Alzheimer’s disease (AD) through the analysis of MRI datasets. The process of diagnosing AD via the visual examination of magnetic resonance imaging (MRI) presents considerable challenges. The visual diagnosis of mild to very mild stages of AD is challenging due to the MRI similarities observed between a brain that is aging normally and one that has AD. The detection of AD with extreme precision is critical during its early stages. Deep-learning techniques have recently been shown to be significantly more effective than human detection in identifying various stages of AD, enabling early-stage diagnosis. The aim of this research is to develop a deep-learning approach that utilizes pre-trained convolutional neural networks (CNNs) to accurately detect the severity levels of AD, particularly in situations where the quantity and quality of available datasets are limited. In this approach, the AD dataset is preprocessed via a refined image processing module prior to the training phase. The proposed method was compared to two well-known deep-learning algorithms (VGG16 and ResNet50) using four Kaggle AD datasets: one for the normal stage of the disease and three for the mild, very mild, and moderate stages, respectively. This allowed us to evaluate the effectiveness of the classification results. The three models were compared using six performance metrics. The results achieved with our approach indicate an overall detection accuracy of 99.3%, which is superior to the other existing models.

Mild cognitive impairment (MCI) is the precursor to the advanced stage of Alzheimer’s disease (AD), and it is important to detect the transition to the MCI condition as early as possible. Trends in daily routines/activities provide a measurement of cognitive/functional status, particularly in older adults. In this study, activity data from longitudinal monitoring through in-home ambient sensors are leveraged in predicting the transition to the MCI stage at a future time point. The activity dataset from the Oregon Center for Aging and Technology (ORCATECH) includes measures representing various domains such as walk, sleep, etc. Each sensor-captured activity measure is constructed as a time series, and a variety of summary statistics is computed. The similarity between one individual’s activity time series and that of the remaining individuals is also computed as distance measures. The long short-term memory (LSTM) recurrent neural network is trained with time series statistics and distance measures for the prediction modeling, and performance is evaluated by classification accuracy. The model outcomes are explained using the SHapley Additive exPlanations (SHAP) framework. LSTM model trained using the time series statistics and distance measures outperforms other modeling scenarios, including baseline classifiers, with an overall prediction accuracy of 83.84%. SHAP values reveal that sleep-related features contribute the most to the prediction of the cognitive stage at the future time point, and this aligns with the findings in the literature. Findings from this study not only demonstrate that a practical, less expensive, longitudinal monitoring of older adults’ activity routines can benefit immensely in modeling AD progression but also unveil the most contributing features that are medically applicable and meaningful.

Breast cancer ranks among the leading causes of death for women globally, making it imperative to swiftly and precisely detect the condition to ensure timely treatment and enhanced chances of recovery. This study focuses on transfer learning with 3D U-Net models to classify ductal carcinoma, the most frequent subtype of breast cancer, in histopathology imaging. In this research work, a dataset of 162 microscopic images of breast cancer specimens is utilized for breast histopathology analysis. Preprocessing the original image data includes shrinking the images, standardizing the intensities, and extracting patches of size 50 × 50 pixels. The retrieved patches were employed to construct a basic 3D U-Net model and a refined 3D U-Net model that had been previously trained on an extensive medical image segmentation dataset. The findings revealed that the fine-tuned 3D U-Net model (97%) outperformed the simple 3D U-Net model (87%) in identifying ductal cancer in breast histopathology imaging. The fine-tuned model exhibited a smaller loss (0.003) on the testing data (0.041) in comparison to the simple model. The disparity in the training and testing accuracy reveals that the fine-tuned model may have overfitted to the training data indicating that there is room for improvement. To progress in computer-aided diagnosis, the research study also adopted various data augmentation methodologies. The experimental approach that was put forward achieved state-of-the-art performance, surpassing the benchmark techniques used in previous studies in the same field, and exhibiting greater accuracy. The presented scheme has promising potential for better cancer detection and diagnosis in practical applications of mammography.

Artificial intelligence (AI) is one of the most promising approaches to health innovation. The use of AI in image recognition considerably extends findings beyond the constraints of human sight. The application of AI in medical imaging, which relies on picture interpretation, is beneficial for automatic diagnosis. Diagnostic radiology is evolving from a subjective perceptual talent to a more objective science thanks to AI. Automatic object detection in medical images is an essential AI technology in medicine. The problem of detecting brain tumors at an early stage is well advanced with convolutional neural network (CNN) and deep learning algorithms (DLA). The problem is that those algorithms require a training phase with a big database of more than 500 images and time-consuming with a complex computational and expensive infrastructure. This study proposes a classical automatic segmentation method for detecting brain tumors in the early stage using MRI images. It is based on a multilevel thresholding technique on a harmony search algorithm (HSO); the algorithm was developed to suit MRI brain segmentation, and parameters selection was optimized for the purpose. Multiple thresholds, based on the variance and entropy functions, break the histogram into multiple portions, and different colors are associated with each portion. To eliminate the tiny arias supposed as noise and detect brain tumors, morphological operations followed by a connected component analysis are utilized after segmentation. The brain tumor detection performance is judged using performance parameters such as Accuracy, Dice Coefficient, and Jaccard index. The results are compared to those acquired manually by experts in the field. The results were further compared with different CNN and DLA approaches using Brain Images dataset called the “BraTS 2017 challenge”. The average Dice Index was used as a performance measure for the comparison. The results of the proposed approach were found to be competitive in accuracy to those obtained by CNN and DLA methods and much better in terms of execution time, computational complexity, and data management.

Speech-in-noise tests are used to assess the ability of the human auditory system to perceive speech in a noisy environment. Early diagnosis of hearing deficits helps health professionals to plan for the most appropriate management. However, hospitals and auditory clinics have a shortage of reliable Arabic versions of speech-in-noise tests. Additionally, access to specialized healthcare facilities is associated with socioeconomic status. Hence, individuals with compromised socioeconomic status do not have proper access to healthcare. Thus, In the current study, a mobile and cost-effective Arabic speech-in-noise test was developed and tested on 30 normal-hearing subjects, and their ability to perceive words-in-noise was evaluated. Moreover, a comparison between two different background noises was explored (multi-talker babble noise and white noise). The results revealed a significant difference in the thresholds between the two types of background noises. The percent-correct scores ranged from 100% to 54.17% for the white background noise and 91.57% to 50% for the multi-talker babble background noise. The proposed Arabic word-in-noise screening tool has the potential to be used effectively to screen for deteriorated speech perception abilities, particularly in low-resource settings.

Due to their interesting size-dependent magnetic characteristics and relative biocompatibility, magnetic superparamagnetic iron oxide (SPIO) nanoparticles have been widely exploited as probes for cell and subcellular structure identification, as well as medication and gene delivery. A thorough understanding of the mechanics of the interaction between nanoparticles and macrophages is vital in managing dynamic processes in nanomedicine. In this study, the interaction behavior and uptake of SPIO nanoparticles by M1- and M2-type macrophages were investigated. Mice monocytes were differentiated into M1 and M2 macrophages, and the uptake of SPIO nanoparticles was studied using a TEM microscope. A high resolution image of 1 nm resolution, an image processing technique, was developed to extract the SPIO-NPs from tomographic TEM microscopic images. Lysosomes appear to be the zones of high concentrations of SPIO inside macrophages. Lysosomes were first selected in each image, and then segmentation by the Otsu thresholding method was used to extract the SPIO-NPs. The Otsu threshold method is a global thresholding technique used to automatically differentiate SPIOs from the background. The SPIO-NPs appear in red colors, and the other pixels in the image are considered background. Then, an estimation of the SPIO-NP uptakes by lysosomes is produced. Higher uptake of all-sized nanoparticles was observed in M1- and M2-type macrophages. An accurate estimation of the number of SPIO-NPs was obtained. This result will help in controlling targeted drug delivery and assessing the safety impact of the use of SPIO-NPs in nanomedicine for humans.