Development of lung cancer classification system for computed tomography images using Artificial Neural Network
An automatic digital classification system for lung cancer detection of Computed Tomography Images using Artificial Neural Network (ANN) and Self Organizing Map (SOM) method is presented. The image samples used in this study are CT Thorax images showing lungs that are healthy and those infected with...
Saved in:
Main Authors: | , , , |
---|---|
Format: | Conference or Workshop Item |
Published: |
2021
|
Subjects: | |
Online Access: | http://eprints.um.edu.my/35396/ |
Tags: |
Add Tag
No Tags, Be the first to tag this record!
|
id |
my.um.eprints.35396 |
---|---|
record_format |
eprints |
spelling |
my.um.eprints.353962023-10-20T05:05:02Z http://eprints.um.edu.my/35396/ Development of lung cancer classification system for computed tomography images using Artificial Neural Network Apsari, R. Aditya, Yudha Noor Purwanti, Endah Arof, Hamzah RC0254 Neoplasms. Tumors. Oncology (including Cancer) T Technology (General) An automatic digital classification system for lung cancer detection of Computed Tomography Images using Artificial Neural Network (ANN) and Self Organizing Map (SOM) method is presented. The image samples used in this study are CT Thorax images showing lungs that are healthy and those infected with cancer stage I and II. Before feature extraction, the images are subjected to segmentation by thresholding to obtain the lung and cancer areas. This is followed by morphological operations such as erosion and dilation. Three features extracted are area, perimeter, and shape and they are fed into the ANN classifier. SOM training showed 87% accuracy, where 29 out of 31 images that were used had been successfully identified. Results of a program validation test obtained by data testing showed accuracy levels as high as 100% for healthy lung, 80% for stage I lung cancer, and 100% for stage II lung cancer. Based on these results, a system designed by using a Self-Organizing Map (SOM) can identify lung cancer stages. This prediction system is useful for the doctors to take an appropriate decision based on patient's condition. 2021-02 Conference or Workshop Item PeerReviewed Apsari, R. and Aditya, Yudha Noor and Purwanti, Endah and Arof, Hamzah (2021) Development of lung cancer classification system for computed tomography images using Artificial Neural Network. In: International Conference on Mathematics, Computational Sciences and Statistics 2020, ICoMCoS 2020, 29 September 2020, Surabaya. |
institution |
Universiti Malaya |
building |
UM Library |
collection |
Institutional Repository |
continent |
Asia |
country |
Malaysia |
content_provider |
Universiti Malaya |
content_source |
UM Research Repository |
url_provider |
http://eprints.um.edu.my/ |
topic |
RC0254 Neoplasms. Tumors. Oncology (including Cancer) T Technology (General) |
spellingShingle |
RC0254 Neoplasms. Tumors. Oncology (including Cancer) T Technology (General) Apsari, R. Aditya, Yudha Noor Purwanti, Endah Arof, Hamzah Development of lung cancer classification system for computed tomography images using Artificial Neural Network |
description |
An automatic digital classification system for lung cancer detection of Computed Tomography Images using Artificial Neural Network (ANN) and Self Organizing Map (SOM) method is presented. The image samples used in this study are CT Thorax images showing lungs that are healthy and those infected with cancer stage I and II. Before feature extraction, the images are subjected to segmentation by thresholding to obtain the lung and cancer areas. This is followed by morphological operations such as erosion and dilation. Three features extracted are area, perimeter, and shape and they are fed into the ANN classifier. SOM training showed 87% accuracy, where 29 out of 31 images that were used had been successfully identified. Results of a program validation test obtained by data testing showed accuracy levels as high as 100% for healthy lung, 80% for stage I lung cancer, and 100% for stage II lung cancer. Based on these results, a system designed by using a Self-Organizing Map (SOM) can identify lung cancer stages. This prediction system is useful for the doctors to take an appropriate decision based on patient's condition. |
format |
Conference or Workshop Item |
author |
Apsari, R. Aditya, Yudha Noor Purwanti, Endah Arof, Hamzah |
author_facet |
Apsari, R. Aditya, Yudha Noor Purwanti, Endah Arof, Hamzah |
author_sort |
Apsari, R. |
title |
Development of lung cancer classification system for computed tomography images using Artificial Neural Network |
title_short |
Development of lung cancer classification system for computed tomography images using Artificial Neural Network |
title_full |
Development of lung cancer classification system for computed tomography images using Artificial Neural Network |
title_fullStr |
Development of lung cancer classification system for computed tomography images using Artificial Neural Network |
title_full_unstemmed |
Development of lung cancer classification system for computed tomography images using Artificial Neural Network |
title_sort |
development of lung cancer classification system for computed tomography images using artificial neural network |
publishDate |
2021 |
url |
http://eprints.um.edu.my/35396/ |
_version_ |
1781704463274213376 |
score |
13.19449 |