Detection and Classification of Lung Cancer through Integrated Image Processing and Machine Learning Approaches

Since lung cancer has few symptoms and it might be difficult to spot lung nodules in medical imaging, prompt detection is essential to improving the survival rate of patients. Innovative, non-invasive alternatives are needed because traditional diagnostic techniques are frequently intrusive and expensive. The objective of this research is to improve the effectiveness and precision of diagnosis by examining current machine learning models and creating a new strategy. It uses a methodical approach that includes gathering images, preprocessing them, extracting features, and integrating AXS-LCNet with a Multiclass SVM Classifier using the large Lung Image Database Consortium (LIDC) dataset. Simplifying diagnostic workflows, minimizing invasive procedures, lowering healthcare costs, and improving accessibility are the main goals to facilitate early treatments and improved patient outcomes.