Lung Cancer was found to be one of the leading causes of death of human persons throughout the world. It spreads rapidly after it forms. The survival rate of patient is very low as the disease is identified in a very late stage. In this paper, we represent a fully automated and three-dimensional segmentation method for the early identification of cancerous pixels in thorax Computed Tomography database. The segmentation process is meant to be considered as the bottleneck in the Computer Aided Diagnosis system for lung cancer detection based on the Computed Tomography pixels’ values. We have formulated the segmentation problem as the optimization of a certain energy function. A special Classifier was designed using Hopfield Artificial Neural Network in order to classify or segment the set of pixels in the CT images of the Thorax into a set of user decided number of regions. A step function was designed, implemented and tested to ensure a high convergence speed of the classifier to local optimum that is close to the global optima. The lung contour was adequately located in 95% of the CT scans using a pre-segmentation process based on bit-planes’ features of the CT scans. The segmentation process was initially developed and tested on a large dataset of subjects, with normal and abnormal lung tissues at different stages, each of 150 CT scans giving very satisfactory results.
| Published in | Automation, Control and Intelligent Systems (Volume 3, Issue 2) |
| DOI | 10.11648/j.acis.20150302.12 |
| Page(s) | 19-25 |
| Creative Commons |
This is an Open Access article, distributed under the terms of the Creative Commons Attribution 4.0 International License (http://creativecommons.org/licenses/by/4.0/), which permits unrestricted use, distribution and reproduction in any medium or format, provided the original work is properly cited. |
| Copyright |
Copyright © The Author(s), 2015. Published by Science Publishing Group |
Chest CT Images, Lung Cancer, Segmentation
| [1] | The National Women's Health Information Center, U.S Department of Health and Human Services office on Women's Health, Lung Cancer, "http://www.4woman.gov/faq/lung.htm", 2003. |
| [2] | Muhammad Usman1, Muhammad Shoaib2, and Mohamad Rahal1, “Multi-resolution Analysis Technique for Lung Cancer Detection in Computed Tomograpic Images”, Progress In Electromagnetics Research Symposium (PIERS) Proceedings, Stockholm, Sweden, 1684-1688, Aug. , 2013. |
| [3] | Shiying Hu, Eric A. Hoffman, “Automatic Lung Segmentation for Accurate Quantitation of Volumetric X-Ray CT Images”, IEEE Transactions on Medical Imaging, Vol. 20, No. 6, June 2001. |
| [4] | Rachid sammouda, Mohammed sammouda and Jamal Abu Hasan, “ Automatic lung Region Extraction Algorithm from 3D CT-Images Based on Bit-Plane Slicing Technique”, University of Sharjah Journal of Pure and Applied Sciences, vol.3, pp. 13-32, 2006. |
| [5] | Rachid sammouda, Hassan Ben Mathkour and Ameur Tuoir, “ Effect of Bit-Planes on the Extarction of Lung Region from 3D Chest CT Images”, Journal of Advances in Computer Sciences and Engineering, vol.12, No. 2, pp. 119-128, 2014. |
| [6] | Harsha Bodhey and Dr. G. S. Sable, “Review on: Adaptive Segmentation of the Pulmonary Lobes and Tumor Identification from Chest CT Scan Images”, International Journal of Advanced Research in Computer and Communication Engineering, Vol. 2, Issue 10, pp. 4068-4071, October 2013. |
| [7] | Prashant Naresh, Dr. Rajashree Shettar, “Early Detection of Lung Cancer Using Neural Network Techniques”, Int. Journal of Engineering Research and Applications, ISSN : 2248-9622, Vol. 4, Issue 8( Version 4), August 2014, pp.78-83. |
| [8] | Kalyani. G. Kohale & Mahesh. S. Pawar, “Segmentation of Lungs Lobes and Distinction between Bening and Malignant Nodules by Use of Massive Training Artificial Neural Network for Surgical Preplanning”, ITSI Transactions on Electrical and Electronics Engineering (ITSI-TEEE), ISSN (PRINT): 2320 – 8945, Volume -1, Issue -6, 2013. |
| [9] | Rachid Sammouda “Data Dependent Weight Initialization in the Hopfield Neural Network Classifier: Application to Natural Colour Images”, Journal of Computers and Applications, Vol. 32, No.2, 2010. |
APA Style
Rachid Sammouda, Hassan Ben Mathkour. (2015). Lung Region Segmentation using Artificial Neural Network Hopfield Model for Cancer Diagnosis in Thorax CT Images. Automation, Control and Intelligent Systems, 3(2), 19-25. https://doi.org/10.11648/j.acis.20150302.12
ACS Style
Rachid Sammouda; Hassan Ben Mathkour. Lung Region Segmentation using Artificial Neural Network Hopfield Model for Cancer Diagnosis in Thorax CT Images. Autom. Control Intell. Syst. 2015, 3(2), 19-25. doi: 10.11648/j.acis.20150302.12
AMA Style
Rachid Sammouda, Hassan Ben Mathkour. Lung Region Segmentation using Artificial Neural Network Hopfield Model for Cancer Diagnosis in Thorax CT Images. Autom Control Intell Syst. 2015;3(2):19-25. doi: 10.11648/j.acis.20150302.12
Share This Article
Twitter
Linked In
Facebook
Copy
Download@article{10.11648/j.acis.20150302.12,
author = {Rachid Sammouda and Hassan Ben Mathkour},
title = {Lung Region Segmentation using Artificial Neural Network Hopfield Model for Cancer Diagnosis in Thorax CT Images},
journal = {Automation, Control and Intelligent Systems},
volume = {3},
number = {2},
pages = {19-25},
doi = {10.11648/j.acis.20150302.12},
url = {https://doi.org/10.11648/j.acis.20150302.12},
eprint = {https://article.sciencepublishinggroup.com/pdf/10.11648.j.acis.20150302.12},
abstract = {Lung Cancer was found to be one of the leading causes of death of human persons throughout the world. It spreads rapidly after it forms. The survival rate of patient is very low as the disease is identified in a very late stage. In this paper, we represent a fully automated and three-dimensional segmentation method for the early identification of cancerous pixels in thorax Computed Tomography database. The segmentation process is meant to be considered as the bottleneck in the Computer Aided Diagnosis system for lung cancer detection based on the Computed Tomography pixels’ values. We have formulated the segmentation problem as the optimization of a certain energy function. A special Classifier was designed using Hopfield Artificial Neural Network in order to classify or segment the set of pixels in the CT images of the Thorax into a set of user decided number of regions. A step function was designed, implemented and tested to ensure a high convergence speed of the classifier to local optimum that is close to the global optima. The lung contour was adequately located in 95% of the CT scans using a pre-segmentation process based on bit-planes’ features of the CT scans. The segmentation process was initially developed and tested on a large dataset of subjects, with normal and abnormal lung tissues at different stages, each of 150 CT scans giving very satisfactory results.},
year = {2015}
}
TY - JOUR T1 - Lung Region Segmentation using Artificial Neural Network Hopfield Model for Cancer Diagnosis in Thorax CT Images AU - Rachid Sammouda AU - Hassan Ben Mathkour Y1 - 2015/03/21 PY - 2015 N1 - https://doi.org/10.11648/j.acis.20150302.12 DO - 10.11648/j.acis.20150302.12 T2 - Automation, Control and Intelligent Systems JF - Automation, Control and Intelligent Systems JO - Automation, Control and Intelligent Systems SP - 19 EP - 25 PB - Science Publishing Group SN - 2328-5591 UR - https://doi.org/10.11648/j.acis.20150302.12 AB - Lung Cancer was found to be one of the leading causes of death of human persons throughout the world. It spreads rapidly after it forms. The survival rate of patient is very low as the disease is identified in a very late stage. In this paper, we represent a fully automated and three-dimensional segmentation method for the early identification of cancerous pixels in thorax Computed Tomography database. The segmentation process is meant to be considered as the bottleneck in the Computer Aided Diagnosis system for lung cancer detection based on the Computed Tomography pixels’ values. We have formulated the segmentation problem as the optimization of a certain energy function. A special Classifier was designed using Hopfield Artificial Neural Network in order to classify or segment the set of pixels in the CT images of the Thorax into a set of user decided number of regions. A step function was designed, implemented and tested to ensure a high convergence speed of the classifier to local optimum that is close to the global optima. The lung contour was adequately located in 95% of the CT scans using a pre-segmentation process based on bit-planes’ features of the CT scans. The segmentation process was initially developed and tested on a large dataset of subjects, with normal and abnormal lung tissues at different stages, each of 150 CT scans giving very satisfactory results. VL - 3 IS - 2 ER -
Email: