Search

In computer vision segmentation field, super pixel identity has become an important index in the recently segmentation algorithms especially in medical images. Simple Linear Iterative Clustering (SLIC) algorithm is one of the most popular super pixel methods as it has a great robustness, less sensitive to the image type and benefit to the boundary recall in different kinds of image processing. Recently, COVID-19 severity increased with the lack of an effective treatment or vaccine. As the Corona virus spreads in an unknown manner, th-ere is a strong need for segmenting the lungs infected regions for fast tracking and early detection, no matter how small. This may consider difficult to be achieved with traditional segmentation techniques. From this perspective, this paper presents an efficient modified central force optimization (MCFO)-based SLIC segmentation algorithm to discuss chest CT images for detecting the positive COVID-19 cases. The proposed MCFO-based SLIC segmentation algorithm performance is evaluated and compared with the thresholding segmentation algorithm using different evaluation metrics such as accuracy, boundary recall, F-measure, similarity index, MCC, Dice, and Jaccard. The outcomes demonstrated that the proposed MCFO-based SLIC segmentation algorithm has achieved better detection for the small infected regions in CT lung scans than the thresholding segmentation. [ABSTRACT FROM AUTHOR]

For proper homoeopathic identification of the medical image, image fusion has been proposed as a mandatory solution to obtain high-spectral and high-spectral spatial data. This article presents a complete fusion system for several types of medical images according to their multi-resolution, multi-scale transforms and the Modified Central Force Optimization (MCFO) technique. Four main techniques have been proposed for this purpose; Optimized Discrete Wavelet and Dual-Tree based fusion techniques as a multi-resolution transform. Besides, the optimized Non-Sub-Sampled Contourlet and Non-Sub-Sampled Shearlet as multi-scale fusion techniques. The perfect matching between input images and minimum artifacts after image registration can be achieved through four stages in the proposed fusion algorithms. First, the input medical image is initially decomposed into their coefficients, and the MCFO method establishes the optimal gain parameter values of the resulted coefficients. Finally, the adaptive histogram equalization and the histogram matching are applied for higher clearness and better visualization of information details. The proposed algorithms are evaluated using various datasets for different medical and surveillance applications through some quality metrics. The Experimental test outcomes indicate that the proposed fusion algorithms achieve good performance with high image quality and appreciated estimation metrics principles. Moreover, it provides better image visualization and minimum processing time, which helps diagnose diseases. [ABSTRACT FROM AUTHOR]