Explore the vast range of titles available.

Pulmonary embolism (PE) represents a severe, life-threatening cardiovascular condition and is notably the third leading cause of cardiovascular mortality, after myocardial infarction and stroke. This pathology occurs when blood clots obstruct the pulmonary arteries, impeding blood flow and oxygen exchange in the lungs. Prompt and accurate detection of PE is critical for appropriate clinical decision-making and patient survival. The complexity involved in interpreting medical images can often results misdiagnosis. However, recent advances in Deep Learning (DL) have substantially improved the capabilities of Computer-Aided Diagnosis (CAD) systems. Despite these advancements, existing single-model DL methods are limited when handling complex, diverse, and imbalanced medical imaging datasets. Addressing this gap, our research proposes an ensemble framework for classifying PE, capitalizing on the unique capabilities of ResNet50, DenseNet121, and Swin Transformer models. This ensemble method harnesses the complementary strengths of convolutional neural networks (CNNs) and vision transformers (ViTs), leading to improved prediction accuracy and model robustness. The proposed methodology includes a sophisticated preprocessing pipeline leveraging autoencoder (AE)-based dimensionality reduction, data augmentation to avoid overfitting, discrete wavelet transform (DWT) for multiscale feature extraction, and Sobel filtering for effective edge detection and noise reduction. The proposed model was rigorously evaluated using the public Radiological Society of North America (RSNA-STR) PE dataset, demonstrating remarkable performance metrics of 97.80% accuracy and a 0.99 for Area Under Receiver Operating Curve (AUROC). Comparative analysis demonstrated superior performance over state-of-the-art pre-trained models and recent ViT-based approaches, highlighting our method’s effectiveness in improving early PE detection and providing robust support for clinical decision-making.

Numerous medical studies have shown that Alzheimer’s disease (AD) was present decades before the clinical diagnosis of dementia. As a result of the development of these studies with the discovery of many ideal biomarkers of symptoms of Alzheimer’s disease, it became clear that early diagnosis requires a high-performance computational tool to handle such large amounts of data, as early diagnosis of Alzheimer’s disease provides us with a healthy opportunity to benefit from treatment. The main objective of this paper is to establish a complete framework that is based on deep learning approaches and convolutional neural networks (CNN). Four stages of AD, such as (I) preprocessing and data preparation, (II) data augmentation, (III) cross-validation, and (IV) classification and feature extraction based on deep learning for medical image classification, are implemented. In these stages, two methods are implemented. The first method uses a simple CNN architecture. In the second method, the VGG16 model is the pre-trained model that is trained on the ImageNet dataset but applies the same model to the different datasets. We apply transfer learning, meaning, and fine-tuning to take advantage of the pre-trained models. Seven performance metrics are used to evaluate and compare the two methods. Compared to the most recent effort, the proposed method is proficient of analyzing AD, moreover, entails less labeled training samples and minimal domain prior knowledge. A significant performance gain on classification of all diagnosis groups was achieved in our experiments. The experimental findings demonstrate that the suggested designs are appropriate for basic structures with minimal computational complexity, overfitting, memory consumption, and temporal regulation. Besides, they achieve a promising accuracy, 99.95% and 99.99% for the proposed CNN model in the classification of the AD stage. The VGG16 pre-trained model is fine-tuned and achieved an accuracy of 97.44% for AD stage classifications.

Alzheimer’s disease (AD) is a form of brain disorder that causes functions’ loss in a person’s daily activity. Due to the tremendous progress of Alzheimer’s patients and the lack of accurate diagnostic tools, early detection and classification of Alzheimer’s disease are open research areas. Accurate detection of Alzheimer’s disease in an effective way is one of the many researchers’ goals to limit or overcome the disease progression. The main objective of the current survey is to introduce a comprehensive evaluation and analysis of the most recent studies for AD early detection and classification under the state-of-the-art deep learning approach. The article provides a simplified explanation of the system stages such as imaging, preprocessing, learning, and classification. It addresses broad categories of structural, functional, and molecular imaging in AD. The included modalities are magnetic resonance imaging (MRI; both structural and functional) and positron emission tomography (PET; for assessment of both cerebral metabolism and amyloid). It reviews the process of pre-processing techniques to enhance the quality. Additionally, the most common deep learning techniques used in the classification process will be discussed. Although deep learning with preprocessing images has achieved high performance as compared to other techniques, there are some challenges. Moreover, it will also review some challenges in the classification and preprocessing image process over some articles what they introduce, and techniques used, and how they solved these problems.

Multiple sclerosis (MS) is a chronic disease that affects different body parts including the brain. Detection and classification of MS brain lesions is of immense importance to physicians for the administration of appropriate treatment. Thus, this study investigates an automated framework for the diagnoses and classification of MS lesions in brain using magnetic resonance imaging (MRI). First, the MRI images format converted from dicom images of each patient into TIF format as MS lesion appears in white matter (WM) obviously. This is followed by a brain tissue segmentation using a k-nearest neighbor classifier. Then, cumulative empirical distributions or cumulative histograms (CH) of the segmented lesions are estimated along with other texture/statistical features that work on the difference between the intensity of MS lesions and its surrounding tissues. Finally, these CDFs are fused with and the statistical features for the classification of MS using K mean classifiers. Experiments are conducted, using transverse T2-weighted MR brain scans from 20 patients that are highly sensitive in detecting MS plaques, with gold standard classification obtained by an experienced MS. By comparing the evaluated performance with statistical features, our proposed fusion scored the highest accuracy with 98% and a false-positive rate of 1%.

This paper proposes a robust optimization of eight chaotic maps: Logistics, Sine, Gauss, Circle, Tent, Chebyshev, Singer, and Piecewise Maps, for superior image encryption. The proposed model consists of two main processes: chaotic confusion and pixel diffusion. In the chaotic confusion process, the positions of the image’s pixels are permuted with the chaotic maps, where the initial condition and the control parameters represent the confusion key. Firstly, the confusion process was performed using the eight chaotic maps without optimization. Then nine metaheuristic optimizers, which are the genetic algorithm, particle swarm optimizations, whale optimization algorithm, dragonfly algorithm, grey wolf optimizer, moth-flame optimizer, sine cosine algorithm, multi-verse optimizer, and ant-lion optimizer, have been used to fine-tune the control parameters of the eight chaotic maps. Then the image’s pixel values are changed using the diffusion function in the pixel diffusion process. Multiple performance metrics, such as entropy, histogram, cross-correlation, computation time analysis, the number of pixels change rate (NPCR), unified average changing intensity (UACI), noise attack, data loss, and key analysis metrics, are utilized to evaluate the proposed model. The results demonstrate that the encryption algorithms based on the eight optimized chaotic maps are more resistant to differential attacks than those without optimization. Furthermore, the optimized Gauss chaotic map is the most computationally efficient, while the chaotic circle map has the most robust key. The careful adjustment of initial conditions and control parameters empowers the chaotic maps to create encryption keys with greater randomness and complexity, thereby increasing the security level of the encryption scheme. Experimental analysis indicates that the correlation coefficient values of images encrypted with the proposed scheme are nearly zero, the histogram of the encrypted images is uniform, the execution time of 0.1556 s, the key space of 10^80, NPCR of 99.63%, UACI of 32.92%, and entropy of 7.997. Moreover, the analysis of noise and cropping attacks, along with the comparison with other algorithms, demonstrate the efficiency and robustness of the proposed algorithm.

Stroke is among the leading causes of death, especially among old adults. Thus, the mortality rate and severe cerebral disability can be avoided when stroke is diagnosed at its early stages, followed by subsequent treatment. There is no doubt that healthcare specialists can find the necessary solutions more effectively and instantly with the help of artificial intelligence (AI) and machine learning (ML). In this study, we used ML classifiers and explainable artificial intelligence (XAI) to predict stroke. Six different ML classifiers that trained on available datasets for stroke patients. Six feature selection methodologies were used to extract essential features from the dataset. The XAI methods applied (Shapley Additive Values (SHAP), ELI5, and Local Interpretable Model-agnostic Explanations (LIME)). This study provides preliminary insights that may support the development of future tools to assist medical practitioners in managing patients, pending further clinical validation and real-world testing.

Obesity, currently the fifth leading cause of death worldwide, has seen a significant increase in prevalence over the past four decades. Timely identification of obesity risk facilitates proactive measures against associated factors. In this paper, we proposed a new machine learning framework for predicting susceptibility to obesity called ObeRisk. The proposed model consists of three main parts, preprocessing stage (PS), feature stage (FS), and obesity risk prediction (OPR). In PS, the used dataset was preprocessed through several processes; filling null values, feature encoding, removing outliers, and normalization. Then, the preprocessed data passed to FS where the most useful features were selected. In this paper, we introduced a new feature selection methodology called entropy-controlled quantum Bat algorithm (EC-QBA), which incorporated two variations to the traditional Bat algorithm (BA): (i) control BA parameters using Shannon entropy and (ii) update BA positions in local search using quantum mechanisms. Then, these selected features fed into several machine learning (ML) algorithms, including LR, LGBM, XGB, AdaBoost, MLP, KNN, and SVM. The final decision was obtained based on the majority voting. Experiment results demonstrated that the proposed EC-QBA outperformed the most recent feature selection methodology in terms of accuracy, precision, sensitivity, and F-measure. It introduced 96% accuracy, 96% precision, 96.5% sensitivity, and 96.25% F-measure. Additionally, experimental results indicated that the EC-QBA with the proposed OPR model delivered the best performance, surpassing modern strategies for predicting obesity by achieving maximum accuracy.

Acute ischemic stroke (AIS) remains a leading cause of mortality and disability worldwide, demanding diagnostic tools that are both accurate and fast for timely intervention. This study presents a comparative evaluation of three state-of-the-art object detection models-YOLOv12, YOLOv11, and YOLO-NAS-for multi-class AIS detection in magnetic resonance imaging (MRI). The dataset, comprising four categories (Normal, PD-Patient, Acute Ischemic Stroke, and Control), was preprocessed with normalization, resizing, and augmentation, then split into training (70%), validation (20%), and testing (10%). Models were trained and evaluated on identical data, with performance measured by precision, recall, mean average precision at IoU 0.5 (mAP@50), and inference speed. YOLOv11 achieved the highest mAP@50 (98.5%) and balanced precision (95.4%) and recall (96.6%), making it the most reliable across classes. YOLOv12 performed comparably (mAP@50 98.3%, precision 95.2%, recall 96.0%) with slightly slower inference, while YOLO-NAS offered the fastest speed (154 FPS) but lower precision (76.3%. Results highlight the trade-offs between detection accuracy and processing speed, providing guidance for selecting YOLO-based architectures suited to specific clinical workflows such as emergency stroke care. The real-time implementation, accessible via Roboflow, demonstrates the feasibility of deploying these models for rapid, automated AIS detection in clinical settings.

Myocardial infarctions, also known as heart attacks, are a leading cause of death globally, highlighting the need for prompt and precise diagnoses to improve patient outcomes. Recently, many machine learning (ML) and artificial intelligence (AI) techniques have been used for diagnosing heart attack diseases, but these techniques still cannot provide the most accurate results. Thus, it is important to improve these approaches to provide better results than current methods do. In this paper, a new hybrid diagnostic approach for heart attack diagnosis called the ensemble heart attack diagnosis model (EHAD), which is based on the ensemble classification technique (ECT), is introduced. ECT integrates three primary classifiers, namely, the support vector machine (SVM), long short-term memory (LSTM), and artificial neural network (ANN), which are combined with the majority voting (MV) technique to make accurate and fast final decisions. The simulation proved that the Ensemble Heart Attack Diagnosis (EHAD) outperforms other models related to many metrics, such as recall, precision, F1 score, accuracy, and many other statistical analysis measurements.

One-third of all cancer diagnoses worldwide are skin malignancies. One of the most common tumors, skin cancer can develop from a variety of dermatological conditions and is subdivided into different categories based on its textile, color, body, and other morphological characteristics. The most effective strategy to lower the mortality rate of melanoma is early identification because skin cancer incidence has been on the rise recently. In order to categorize dermoscopy images into the four diagnosis classifications of melanoma, benign, malignant, and human against machine (HAM) not melanoma, this research suggests a computer-aided diagnosis (CAD) system. Experimental results show that the suggested approach enabled 97.25% classification accuracy. In order to automate the identification of skin cancer and expedite the diagnosis process in order to save a life, the proposed technique offers a less complex and cutting-edge framework.