Benign Malignant Classification of Lung Nodules using Machine Learning

Lung disease has been the deadliest among every single kind of tumor. Early discovery of tumor is needed to increment the survival rate for patients from disease. Our motivation is for building up an effective Computer Aided Diagnosis (CAD) system for lung nodules (knobs) discovery from pre notion district of lung and group the knobs into two categories Malignant (carcinogenic) or Benign (non-destructive). Computer-aided detection supported location frameworks can help radiologists to distinguish aspiratory knobs at a beginning time. In this research, a novel CAD system is developed for the order of aspiratory (pulmonary) knob as carcinogenic and non-destructive. This CAD framework utilizing various classifiers, gives an accurate idea to radiologists at the finding procedure of the infection, high grouping execution.