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.

Original languageEnglish
Title of host publicationInternational Conference on Mathematics, Computational Sciences and Statistics 2020
EditorsCicik Alfiniyah, Fatmawati, Windarto
PublisherAmerican Institute of Physics Inc.
ISBN (Electronic)9780735440739
Publication statusPublished - 26 Feb 2021
EventInternational Conference on Mathematics, Computational Sciences and Statistics 2020, ICoMCoS 2020 - Surabaya, Indonesia
Duration: 29 Sept 2020 → …

Publication series

NameAIP Conference Proceedings
ISSN (Print)0094-243X
ISSN (Electronic)1551-7616


ConferenceInternational Conference on Mathematics, Computational Sciences and Statistics 2020, ICoMCoS 2020
Period29/09/20 → …


Dive into the research topics of 'Development of lung cancer classification system for computed tomography images using artificial neural network'. Together they form a unique fingerprint.

Cite this