Cat Swarm Optimization-Based Computer-Aided Diagnosis Model for Lung Cancer Classification in Computed Tomography Images

Lung cancer is the most significant that heavily contributes to cancer-related mortality rate, due its violent nature and late diagnosis at advanced stages. Early identification of lung essential for improving survival rate. Various imaging modalities, including X-rays computed tomography (CT) scans, are employed diagnose cancer. Computer-aided (CAD) models necessary minimizing burden upon radiologists enhancing detection efficiency. Currently, computer vision (CV) deep learning (DL) detect classify in a precise manner. In this background, current study presents cat swarm optimization-based computer-aided model classification (CSO-CADLCC) model. The proposed CHO-CADLCC technique initially pre-process data using Gabor filtering-based noise removal technique. Furthermore, feature extraction pre-processed images performed with help NASNetLarge This followed by CSO algorithm weighted extreme machine (WELM) model, which exploited nodule classification. Finally, utilized optimal parameter tuning WELM resulting an improved performance. experimental validation CSO-CADLCC was conducted against benchmark dataset, results were assessed under several aspects. outcomes established promising performance approach over recent approaches different measures.