NORMA eResearch @NCI Library

Lung Cancer Detection Using Classification Algorithms

Jadhav, Sumit (2020) Lung Cancer Detection Using Classification Algorithms. Masters thesis, Dublin, National College of Ireland.

[thumbnail of Master of Science]
Preview
PDF (Master of Science)
Download (1MB) | Preview
[thumbnail of Configuration manual]
Preview
PDF (Configuration manual)
Download (1MB) | Preview

Abstract

Diagnosing lung cancer with high accuracy is most critical to make a significant change in survival rate. For diagnosing lung cancer different imaging techniques are used by radiologists such as Magnetic Resonance Imaging (MRI), Computer tomography (CT) and X-ray. These techniques help to detect the benign or malignant nodules present in the lungs but with certain limitations to the human eye. This study proposes to build a classification system that can identify the benign and malignant nodules and provide better accuracy for lung cancer detection. A Kaggle dataset of 6691 images of CT scans is used in this research. In preprocessing, these images were split into individual file and then resized in 64x64 resolution for data consistency along with antialiasing to smooth the edges of the nodules for better detection. In this study five classification models were applied { Convolution Neural Network (CNN), Random Forest classification algorithm (RF), Support Vector Machine (SVM) and boosting techniques such as Xtreme Gradient Boost (XGBoost) and Adaptive Boost (ADABoost) to classify the malignant and benign lung nodules and finally all the obtained results were compared. This study finds the accuracy of all the applied classifier models. From all these algorithms CNN outperforms with an accuracy of 89%. Support Vector Machine classifier accuracy was observed to be improved with RBF kernel. Random forest accuracy was observed to be 83%. This approach is successful for identifying the malignant and benign lung nodules with a greater number of images than previous studies.

Item Type: Thesis (Masters)
Subjects: Q Science > QA Mathematics > Electronic computers. Computer science
T Technology > T Technology (General) > Information Technology > Electronic computers. Computer science
Q Science > QA Mathematics > Computer software
T Technology > T Technology (General) > Information Technology > Computer software
R Medicine > R Medicine (General)
Divisions: School of Computing > Master of Science in Data Analytics
Depositing User: Dan English
Date Deposited: 11 Jun 2020 10:43
Last Modified: 11 Jun 2020 10:43
URI: https://norma.ncirl.ie/id/eprint/4271

Actions (login required)

View Item View Item