Intracranial blood vessels segmentation from computed tomography angiography (CTA) volumes is a promising biomarker for diagnosis and therapeutic treatment in cerebrovascular diseases. These segmentation outputs are a fundamental requirement in the development of automated decision support systems for preoperative assessment or intraoperative guidance in neuropathology. The state-of-the-art in medical image segmentation methods are reliant on deep learning architectures based on convolutional neural networks. However, despite their popularity, there is a research gap in the current deep learning architectures optimized to address the technical challenges in blood vessel segmentation. These challenges include: (i) the extraction of concrete brain vessels close to the skull; and (ii) the precise marking of the vessel locations. We propose an Optimally Fused Fully end-to-end Network (OFF-eNET) for automatic segmentation of the volumetric 3D intracranial vascular structures. OFF-eNET comprises of three modules. In the first module, we exploit the up-skip connections to enhance information flow, and dilated convolution for detailed preservation of spatial feature map that are designed for thin blood vessels. In the second module, we employ residual mapping along with inception module for speedy network convergence and richer visual representation. For the third module, we make use of the transferred knowledge in the form of cascaded training strategy to gradually optimize the three segmentation stages (basic, complete, and enhanced) to segment thin vessels located close to the skull. All these modules are designed to be computationally efficient. Our OFF-eNET, evaluated using 70 CTA image volumes, resulted in 90.75% performance in the segmentation of intracranial blood vessels and outperformed the state-of-the-art counterparts.

Background: A critical component of disaster preparedness in hospitals is experiential education and training of health care professionals. A live drill is a well-established, effective training approach, but cost restraints and logistic constraints make clinical implementation challenging, and training opportunities with live drills may be severely limited. Virtual reality simulation (VRS) technology may offer a viable training alternative with its inherent features of reproducibility, just-in-time training, and repeatability. Objective: This integrated review examines the scientific evidence pertaining to the effectiveness of VRS and its practical usefulness in training health care professionals for in-hospital disaster preparedness. Methods: A well-known 4-stage methodology was used for the integrated review process. It consisted of problem identification, a literature search and inclusion criteria determination, 2-stage validation and analysis of searched studies, and presentation of findings. A search of diverse publication repositories was performed. They included Web of Science (WOS), PubMed (PMD), and Embase (EMB). Results: The integrated review process resulted in 12 studies being included. Principle findings identified 3 major capabilities of VRS: (1) to realistically simulate the clinical environment and medical practices related to different disaster scenarios, (2) to develop learning effects on increased confidence and enhanced knowledge acquisition, and (3) to enable cost-effective implementation of training programs. Conclusions: The findings from the integrated review suggested that VRS could be a competitive, cost-effective adjunct to existing training approaches. Although the findings demonstrated the applicability of VRS to different training scenarios, these do not entirely cover all disaster scenarios that could happen in hospitals. This integrated review expects that the recent advances of VR technologies can be 1 of the catalysts to enable the wider adoption of VRS training on challenging clinical scenarios that require sophisticated modeling and environment depiction.

Worldwide, coronary heart disease (CHD) is a leading cause of mortality, and its early prediction remains a critical challenge in clinical data analysis. Machine learning (ML) offers valuable diagnostic support by leveraging healthcare data to enhance decision-making and prediction accuracy. Although numerous studies have applied ML classifiers for heart disease prediction, their contributions often lack clarity in addressing key challenges. In this paper, we present a comprehensive ML framework that systematically tackles these issues. First, we employ mutual information (MI) for effective feature selection to isolate the most informative predictors. Second, we address the significant class imbalance in the dataset using the Synthetic Minority Oversampling Technique (SMOTE), which substantially improves model training. Third, we propose a novel hybrid model that integrates particle swarm optimization (PSO) with an artificial neural network (ANN) to optimize feature weighting and bias training. Additionally, we conduct a comparative analysis with traditional classifiers, including Logistic Regression and Random Forest, using the National Health and Nutritional Examination Survey dataset. Our results demonstrate that while conventional classifiers achieve an accuracy of 95.8%, the proposed PSO-ANN model attains an enhanced accuracy of up to 97% in predicting CHD. This work clearly defines its contributions by improving feature selection, handling data imbalance, and introducing an innovative hybrid model for superior prediction performance.

Denoising is one of the most important processes in digital image processing to recover visual quality and structural integrity in images. Traditional methods often suffer from limitations like computational complexity, over-smoothing, and the inability to preserve critical details, particularly edges. This paper introduces a hybrid denoising algorithm combining Adaptive Median Filter (AMF) and Modified Decision-Based Median Filter (MDBMF) to address these challenges. The AMF adjusts the window sizes dynamically to precisely detect noisy pixels, and MDBMF selectively recovers corrupted pixels without affecting intact regions, effectively reducing noise while preserving edges. The subjective analysis is supplemented with objective analyses in which visual quality proves that hybrid approach performance considerably outperforms existing state-of-the-art methods. The test is conducted on nine benchmark images standard and medical dataset, namely, Chest and Liver images with different noise densities in the range from 10 to 90%. Quantitative evaluations PSNR, MSE, IEF, SSIM, FOM and VIF clearly show the performance superiority of the hybrid approach when compared to the state-of-the-art approaches. The improvement in PSNR was up to 2.34 dB, IEF improvement was more than 20%, and the improvement in MSE was up to 15% improvement over other methods like BPDF, AT2FF, and SVMMF. Improvement in the values of SSIM is up to 0.07, which confirms improved structural similarity. Furthermore, the FOM and VIF metrics demonstrate the remarkable performance of the hybrid approach: both the FOM and VIF exceeded all other denoising techniques evaluated, reaching 0.68 and 0.61, respectively.