Published August 23, 2020
| Version Version 1
Journal article
Open
THE EFFECT OF EPOCH ON THE ACCURACY OF DETECTION OF LUNG CANCER
- 1. Department of Physics, Faculty of Sciences and Mathematics, Diponegoro University, Indonesia
- 2. Department of Physics, Faculty of Sciences and Mathematics, Diponegoro University, Indonesia
Description
The purpose of this study was to detect lung cancer from CT-Scan images using the deep learning (DL) method, namely Convolutional Neural Network (CNN). Convolutional Neural Network (CNN) is a deep learning neural network that has mimicked the network functions of the human brain. CNN is one of the deep learning algorithms which is a multi layer perceptron (MLP) development which is designed to process data, so that it can be used to detect and recognize an object in an image. The study was conducted by training the model on 2000 CT-Scan images by varying the epoch three times and giving a learning rate of 0.0001 for each variation. It can be seen that the greater the epoch given, the higher the accuracy obtained but it takes a long time. So that the best results given by the model are found in variation III with an accuracy value of 98.50%.
Notes
Lung cancer is the most feared type of cancer with a very high mortality rate among all other types of cancer. The main problem is the difficulty in diagnosing and the time needed to identify it, thereby reducing the level of life after being diagnosed. Patient survival rates can increase from 15% to 49% if cancer is detected at an early stage [1]. Smoking is a major cause of lung cancer, where cigarette smoke contains more than 4,000 chemicals of which 63 types are carcinogens and toxic [2]. Lung cancer is divided into two major parts, namely non-small cell lung cancer (NSCLC) and small cell lung cancer (SCLC) [3]. NSCLC is a more common type of lung cancer and this research is based on the classification of NSCLC type lung cancer. There are various modalities that can be used to diagnose lung cancer one of which is to use Computed Tomography Scan (CT-Scan). CT-Scan is a diagnostic support modality that has a systematic imaging that uses a combination of X-rays and computer technology to produce images. CT-Scan modalities are more effective than plain chest x-rays in detecting and diagnosing lung cancer because they are able to provide good and clear images in this case have good contrast and can provide precise anatomical information [4]. The images obtained from CT-Scan can be analyzed later using digital image processing techniques on a personal computer.
Files
04.AUAE10084.pdf
Files
(1.1 MB)
| Name | Size | Download all |
|---|---|---|
|
md5:684282818c2b72521c6bbf872dfa28a6
|
1.1 MB | Preview Download |
Additional details
Related works
- Cites
- Journal article: 10.26562/ijirae.2020.v0708.004 (DOI)
- Is cited by
- Journal article: http://www.ijirae.com/volumes/Vol7/iss-8/04.AUAE10084.pdf (URL)
References
- 1. Mahalakshmi, S., Rajalakshmi, K., & Varadarajan, M. K. M. (2016). An Expert System for Detecting Stages in Lung Cancer. An International Journal of Advance Computer Technology, 221–225.
- 2. Panpaliya, N., Tadas, N., Bobade, S., Aglawe, R., & Gudadhe, A. (2015). A Survey on Early Detection and Prediction of Lung Cancer. International Journal of Computer Science and Mobile Computing, 4(1), 175–184.
- 3. Varalakshmi, K. (2013). Classification of Lung Cancer Nodules Using a Hybrid Approach. Journal of Emerging Trends in Computing and Information Sciences Vol. 4, No. 1 Jan 2013 ISSN 2079-8407, 4(1), 63–68.
- 4. Bushberg, J. T., Seibert, J.A., Leidholft, E. M., dan Boone, J. M. 2002. The Essential Physics of Medical Imaging: Second Edition. Lippincott Williams and Wilkins,Philadelphia
- 5. He, K., Zhang, X., Ren, S., & Sun, J. (2016). Deep Residual Learning for Image Recognition Kaiming. Indian Journal of Chemistry - Section B Organic and Medicinal Chemistry, 45(8), 1951–1954
- 6. Anthimopoulos, M., Christodoulidis, S., Ebner, L., Christe, A., & Mougiakakou, S. (2016). Lung Pattern Classification for Interstitial Lung Diseases Using a Deep Convolutional Neural Network. IEEE Transactions on Medical Imaging, 35(5), 1207–1216.
- 7. Gao, M., Xu, Z., & Mollura, daniel J. (2017). Combining Deep Learning and Structured Prediction. Interstitial Lung Diseases via Deep Convolutional Neural Networks: Segmentation Label Propagation, Unordered Pooling and Cross-Dataset Learning, March 2019, 225–240.
- 8. Matsuyama, E., & Tsai, D.-Y. (2018). Automated Classification of Lung Diseases in Computed Tomography Images Using a Wavelet Based Convolutional Neural Network. Journal of Biomedical Science and Engineering, 11(10), 263–274.