Application of Machine Learning Techniques for the Diagnosis of Lung Cancer with ANT Colony Optimization

Abstract

Lung cancer is the leading cause of cancer-related death in the worldwide. The prognosis is poor, with less than 15% of patients surviving 5 years after diagnosis. The poor prognosis is attributable to lack of efficient diagnostic methods for early detection and lack of successful treatment metastatic disease. However, persons with early lung cancer have lower lung cancer-related mortality than those with extensive disease, suggesting early detection and treatment of lung cancer might be beneficial. Computer Tomography is a clinical recommended imaging tool for the detection, diagnosis and follows up of many cancers. The most essential and challenging task for physicians is detection of lesions. Detection of lesions is found to be most difficult because of low contrast of an image or sometimes their residual. This paper is aimed to design computer aided diagnosis (CAD) system which has four different phases for detection of cancerous nodules from lung CT (Computer Tomography) images and they are preprocessing, feature extraction, feature selection and classification. Ant colony optimization as feature selection technique is being used to get more accurate result. Two kinds of machine learning techniques, viz., SVM (Support Vector Machine) and ANN (Artificial Neural Network) have been presented which classify the abnormal or normal lung image. ANN has proved that it gives the best accuracy as compared to SVM. The system accuracy using SVM is 93.2% and ANN is 98.40%. In this study, our methods are validated via a series of experimentation conducted with a data set of 250 lung CT images and the procedure is implemented using MATLAB tool.

Prediction of Lung Cancer Using Machine Learning Classifier

“…Z. Zubi et al (2014) extracted features from chest x ray images and used concept of back propagation neural network method to improve the accuracy [ 31 ]. Rashmee Kohad et al (2015) used ant colony optimization with ANN and SVM to predict the accuracy of 98% and 93.2% respectively on 250 lung cancer CT images [ 16 ]. Kourou et al (2015) outlined a review of various machine learning approach on several cancer data and concluded that application of integration of feature selection and classifier will provide a promising result in analysis of cancer data [ 17 ].…”

Performance evaluation of machine learning techniques in lung cancer classification from PET/CT images

“…ANN based lung cancer detection system has been established and utilized first order texture features extracted from CT images [11]. Significant texture features yielded a better accuracy of 98.4% using ANN compared to 93.2 % by SVM [12]. Classification using Hop field neural network achieved 98% accuracy in detecting lung cancer [13].…”

An Ensemble Model With Feature Selection Technique for Classification of Lung Cancer Disease

“…There are various doctors and researchers have done in the field of lung cancer diagnosis and achieved better solution to find out better results. According to the World Health Organization (WHO) [1] approximately 14 million new cases and 8.2 million cancers related death in 2012. According to American Lung Association, deaths due to Lung cancer is more than the next most common cancers combined (colon, breast and pancreatic).…”

“…S. P. Tidke, et al [3] have suggested SVM algorithm to diagnosis of lung cancer disease and achieved satisfactory accuracy. R. Kohad et al [1] have used classifiers like SVM and ANN and proposed ACO_ANN. The proposed algorithm gives better accuracy which higher than the accuracy compare to others.…”