Lung cancer classification with Convolutional Neural Network Architectures

One of the most common malignant tumors in the world today is lung cancer, and it is the primary cause of death from cancer. With the continuous advancement of urbanization and industrialization, the problem of air pollution has become more and more serious. The best treatment period for lung cance...

Full description

Saved in:
Bibliographic Details
Main Authors: Shivan H. M. Mohammed, Ahmet Çinar
Format: Article
Language:English
Published: Qubahan 2021-02-01
Series:Qubahan Academic Journal
Subjects:
Online Access:https://journal.qubahan.com/index.php/qaj/article/view/33
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1832544471744512000
author Shivan H. M. Mohammed
Ahmet Çinar
author_facet Shivan H. M. Mohammed
Ahmet Çinar
author_sort Shivan H. M. Mohammed
collection DOAJ
description One of the most common malignant tumors in the world today is lung cancer, and it is the primary cause of death from cancer. With the continuous advancement of urbanization and industrialization, the problem of air pollution has become more and more serious. The best treatment period for lung cancer is the early stage. However, the early stage of lung cancer often does not have any clinical symptoms and is difficult to be found. In this paper, lung nodule classification has been performed; the data have used of CT image is SPIE AAPM-Lung. In recent years, deep learning (DL) was a popular approach to the classification process. One of the DL approaches that have used is Transfer Learning (TL) to eliminate training costs from scratch and to train for deep learning with small training data. Nowadays, researchers have been trying various deep learning techniques to improve the efficiency of CAD (computer-aided system) with computed tomography in lung cancer screening. In this work, we implemented pre-trained CNN include: AlexNet, ResNet18, Googlenet, and ResNet50 models. These networks are used for training the network and CT image classification. CNN and TL are used to achieve high performance resulting and specify lung cancer detection on CT images. The evaluation of models is calculated by some matrices such as confusion matrix, precision, recall, specificity, and f1-score.
format Article
id doaj-art-3c8bd43391d94a7e9a4c4e5f2aaf457c
institution Kabale University
issn 2709-8206
language English
publishDate 2021-02-01
publisher Qubahan
record_format Article
series Qubahan Academic Journal
spelling doaj-art-3c8bd43391d94a7e9a4c4e5f2aaf457c2025-02-03T10:12:58ZengQubahanQubahan Academic Journal2709-82062021-02-011110.48161/qaj.v1n1a3333Lung cancer classification with Convolutional Neural Network ArchitecturesShivan H. M. Mohammed0Ahmet Çinar1Department of Computer Science, Duhok University, Duhok, IraqDepartment of Computer Engineering, Firat University, Elazig, Turkey One of the most common malignant tumors in the world today is lung cancer, and it is the primary cause of death from cancer. With the continuous advancement of urbanization and industrialization, the problem of air pollution has become more and more serious. The best treatment period for lung cancer is the early stage. However, the early stage of lung cancer often does not have any clinical symptoms and is difficult to be found. In this paper, lung nodule classification has been performed; the data have used of CT image is SPIE AAPM-Lung. In recent years, deep learning (DL) was a popular approach to the classification process. One of the DL approaches that have used is Transfer Learning (TL) to eliminate training costs from scratch and to train for deep learning with small training data. Nowadays, researchers have been trying various deep learning techniques to improve the efficiency of CAD (computer-aided system) with computed tomography in lung cancer screening. In this work, we implemented pre-trained CNN include: AlexNet, ResNet18, Googlenet, and ResNet50 models. These networks are used for training the network and CT image classification. CNN and TL are used to achieve high performance resulting and specify lung cancer detection on CT images. The evaluation of models is calculated by some matrices such as confusion matrix, precision, recall, specificity, and f1-score. https://journal.qubahan.com/index.php/qaj/article/view/33Deep learning; Transfer learning; Lung cancer; pre-trained network.
spellingShingle Shivan H. M. Mohammed
Ahmet Çinar
Lung cancer classification with Convolutional Neural Network Architectures
Qubahan Academic Journal
Deep learning; Transfer learning; Lung cancer; pre-trained network.
title Lung cancer classification with Convolutional Neural Network Architectures
title_full Lung cancer classification with Convolutional Neural Network Architectures
title_fullStr Lung cancer classification with Convolutional Neural Network Architectures
title_full_unstemmed Lung cancer classification with Convolutional Neural Network Architectures
title_short Lung cancer classification with Convolutional Neural Network Architectures
title_sort lung cancer classification with convolutional neural network architectures
topic Deep learning; Transfer learning; Lung cancer; pre-trained network.
url https://journal.qubahan.com/index.php/qaj/article/view/33
work_keys_str_mv AT shivanhmmohammed lungcancerclassificationwithconvolutionalneuralnetworkarchitectures
AT ahmetcinar lungcancerclassificationwithconvolutionalneuralnetworkarchitectures