An Approach on Stage Classification of Lung Cancer Using Fuzzy Inference System

Lung cancer stands as the second most prevalent global fatality attributed to cancer. Prior diagnosis and timely identification are utmost important for effective treatment and to enhance survival outcomes. In recent years, machine learning techniques have exhibited immense potential in the early detection and diagnosis of lung cancer. This model proposes an approach for lung cancer stage classification using a fuzzy interface system (FIS). The proposed system integrates different techniques, including image processing, feature selection, and FIS, to achieve the classification of lung cancer stages. The tumor images were pre-processed using binarization techniques, and the clinical data were pre-processed using various scaling techniques. The proposed system for malignant and benign data achieved mean accuracy of 91.03%, demonstrating its potential as an effective tool for lung cancer diagnosis and treatment. The proposed approach had a mean accuracy of 93.89 and 93.51% for stage T1 and stage T2 malignant data, respectively. Overall, this proposed model adds a significant improvement to the field of lung cancer diagnosis, treatment, and has the potential to improve patient outcomes.