6Enhanced Intersection Particle Swarm Optimization (EIPSO) Algorithm and Image Processing Techniques for Lung Cancer Detection

Image processing techniques are now broadly used in several medical sectors for primary identification and therapy phases. Pre-processing, extraction of features, and segmentation strategies like thresholding or K-means clustering are deliberated as part of the dispensation processes.. By using picture improvement and segmentation algorithms in MATLAB software, the goal is to obtain more accurate findings. CT used to detect lung cancer is one of the most accepted imaging techniques in medicine. We proposed a method for identifying lung cancer based on different pertinent techniques and picture segmentation, one of the intermediate phases in image processing.The goal is to create a quick image segmentation technique for medical imaging, which will decrease how frequently clinicians examine computer tomography (CT) scan images to look for lung cancer.. Large images formed by current medical imaging technologies are mainly difficult to estimate and improve manually. This is worrisome because of its importance in efficiently detecting and starting therapy effectively. Recent image processing techniques are very important to study as they are frequently used in a variety of medical issues. To extract the tumour from the lung picture in this study, we applied and assessed the performance of optimization techniques such as k-means clustering, the optimization of particle swarms, and the enhanced intersecting particle swarm optimization technique (EIPSO).. After reviewing the outcomes of the median, adaptive median, and average filters in the first preliminary step, it was determined that the adaptive median filter was the most suitable for usage with medical CT scans. Based on the outcomes of our studies, we concluded that our method was effective. The preprocessed image with good quality is susceptible to multiple algorithms in studies using 20 lung scans as samples, with the EIPSO technique having the best accuracy (96.19%)