Identification of lung cancer stages using efficient machine learning framework

Abstract

Lung cancer is a major global health problem. Despite advances in prevention, diagnostics and therapies in the past decade, lung cancer is the leading cause of cancer-related morbidity and mortality worldwide Patients diagnosed with non-small cell lung cancer (NSCLC; ?85% of lung cancers) are most often diagnosed at late stages, associated with dismal prognoses. Convolutional Neural Networks (CNNs) models become main stream among the identification zone in light of their promising result on creating significant level image representations. A new machine learning design for learning significant level image portrayal to accomplish high order precision with low change in clinical picture order assignments is proposed. The purpose of personalized medicine is to identify the optimal treatment for each individual patient, to maximize treatment benefit and minimize adverse effects. Informative biomarkers which can reliably predict outcome are needed to achieve this goal. This manuscript proposes an Efficient Machine Learning Algorithm (EMLA) for identification of different stages of lung cancer. The proposed method is compared with the traditional methods and the results show that the proposed method is better than existing methods.