Lung cancer diagnosis through CT images using principal component analysis (PCA) and error correcting output codes (ECOC)

Abstract

Lung cancer has been a leading cause of cancer-related mortality in recent years, and early detection can increase patients’ chances of recovery. Machine learning and image processing may be used to analyze Computed Tomography (CT) scans for signs of lung cancer; by integrating several machine learning models, the accuracy of lung cancer diagnoses can be increased. In this paper, we propose a method that introduces a segmentation algorithm based on Social Spider Optimization (SSO) to detect suspicious regions in the CT image. The proposed method uses a combination of Error Correcting Output Codes (ECOC) and Support Vector Machine (SVM) to classify suspicious regions and diagnose lung cancer. The efficiency has been evaluated and compared with previous works. The results show that the proposed method can diagnose lung cancer with an average accuracy of 96.67% and can be used as an efficient tool for assisting specialists in diagnosing lung cancer.