×
The submission system is temporarily under maintenance. Please send your manuscripts to
Go to Editorial ManagerCone-beam computed tomography (CBCT) is an indispensable method that reconstructs three dimensional (3D) images. CBCT employs a mathematical technique of reconstruction, which reveals the anatomy of the patient’s body through the measurements of projections. The mathematical techniques employed in the reconstruction process are classified as; analytical, and iterative. The iterative reconstruction methods have been proven to be superior over the analytical methods, but due to their prolonged reconstruction time those methods are excluded from routine use in clinical applications. The aim of this research is to accelerate the iterative methods by performing the reconstruction process using a graphical processing unit (GPU). This method is tested on two iterative-reconstruction algorithms (IR), the algebraic reconstruction technique (ART), and the multiplicative algebraic reconstruction technique (MART). The results are compared against the traditional ART, and MART. A 3D test head phantom image is used in this research to demonstrate results of the proposed method on the reconstruction algorithms. The simulation results are executed using MATLAB (version R2018b) programming language and computer system with the following specifications: CPU core i7 (2.40 GHz) for the processing, with a NIVDIA GEFORCE GPU. Experimental results indicate, that this method reduces the reconstruction time for the iterative algorithms.
This study evaluates the performance and efficiency of four deep learning models—VGG-16, ResNet-50, Inception-V3, and DenseNet-121—in detecting pneumonia from chest X-rays, addressing the critical need for balanced accuracy and computational efficiency in clinical diagnostics. Methods: A dataset of 5,234 chest X-rays (3,875 pneumonia, 1,341 normal) was augmented via rotation, flipping, and zooming to mitigate class imbalance. Models were trained on an RTX 2060 GPU for 40 epochs, with performance assessed using accuracy, F1 score, sensitivity, specificity, precision, and computational metrics (training time, memory usage). Statistical significance was validated via paired t-tests (p < 0.05). Results: DenseNet-121 achieved the highest accuracy (95.2% ± 0.8), F1 score (95.1% ± 0.7), and throughput (400 images/sec) with minimal memory usage (33MB). ResNet-50 and Inception-V3 showed moderate performance, while VGG-16 exhibited overfitting tendencies. In conclusion, DenseNet-121 showed strong performance compared to other models, both in terms of accuracy and processing speed, which is essential for use in real-time clinical settings. However, the small size of the validation set and limited population diversity are important limitations that should be addressed in future studies. Moreover, more testing on larger datasets is needed to confirm the stability of the model and see how the model will work in different settings. Future work should address ethical considerations in AI-driven diagnostics and validate findings across multi-institutional datasets.
As a result of the tremendous development taking place in modern systems and technologies in the field of electronic monitoring. Intelligent monitoring, decision making, and automated response systems have become common subjects at this time, especially after the development of machines responsible for these processes. Traffic surveillance is a trend goal nowadays using different techniques and equipment. In this article, real-time Object detection and tracking techniques were proposed for traffic surveillance using image processing techniques. A state was specifically examined for its ability to detect and count passing motorcycles on a highway in a specific area. The results showed good reliability, with a frame processing time of approximately about (30 ms) and the achievement of real-time performance. The main contribution of this article is reaching the best result implemented by the performance the real-time process using image process technique and tracking the object by depending on the sequencing of frames and can stands with rationally not so powerful machines. Several tools have been used for different types of necessary tasks that will be part of the required application such as Python 3.7; which was used to build the basic algorithms,Visual studio code (VSC) as an Integrated Development Environment (IDE), and Anaconda navigator for downloading many useful libraries. The specifications of the used device were Intel(R) Core (TM) i7- 10750H CPU @ 2.60GHz 2.59 GHz, RAM 16.0 GB, NVIDIA GeForce GTX 1650 GPU, 64-bit operating system, x64-based processor.