Combined Feature Learning And CNN For Polyp Detection In Wireless Capsule Endoscopy Images

Combined Feature Learning And CNN For Polyp Detection In Wireless Capsule Endoscopy Images
  IJETT-book-cover           
  
© 2021 by IJETT Journal
Volume-69 Issue-6
Year of Publication : 2021
Authors : S.Sunitha, Dr.S.S. Sujatha
DOI :  10.14445/22315381/IJETT-V69I6P230

How to Cite?

S.Sunitha, Dr.S.S. Sujatha, "Combined Feature Learning And CNN For Polyp Detection In Wireless Capsule Endoscopy Images," International Journal of Engineering Trends and Technology, vol. 69, no. 6, pp. 206-215, 2021. Crossref, https://doi.org/10.14445/22315381/IJETT-V69I6P230

Abstract
There is a high probability for the polyps of the small intestine to turn into a malignant tumor. So, it is mandatory to identify these polyps in the early stage and remove them. This would increase the patient`s survival rate many times. With the tremendous growth of the technology, Wireless Capsule Endoscopy (WCE) is viewed as an achievement in the medical field. WCE makes it easy, painless, and inexpensive to view an internal body that humans cannot see. However, the primary disadvantage of wireless capsule endoscopy is the poor image quality. Additionally, the shape, color, and texture of the human gastrointestinal (GI) tract resemble polyps. Hence, certain types of polyps cannot be identified even by a well-trained doctor. For this reason, a computer-aided polyp segmentation remains a problem to be solved. In this proposed research, the Combined Feature Learning (CFL) and Convolutional Neural Network (CNN) has been used to develop an automated polyp detection system. WCE images have been augmented to improve the training efficiency of the proposed CFL-CNN model. Furthermore, high and low level feature learning has been used in this proposed method to reduce the False Positive (FP) rate. The experimental results demonstrate that high-level features and image augmentation significantly reduce the FP intensity. This shows a significant improvement in overall performance in terms of precision, sensitivity, specificity, and recall. Additionally, the experiment results indicate that training the proposed CFL-CNN model requires a small amount of time and computational resources.

Keywords
Wireless Capsule Endoscopy, Image Segmentation, Image Pre-Processing, CNN, Polyp Detection, Deep Learning.

Reference
[1] Mustain Billah, Sajjad Waheed, Mohammad Motiur Rahman, An Automatic Gastrointestinal Polyp Detection System in Video Endoscopy Using Fusion of Color Wavelet and Convolutional Neural Network Features, International Journal of Biomedical Imaging, vol. 2017, Article ID 9545920, 9 pages, 2017. https://doi.org/10.1155/2017/9545920.
[2] X. Yang, Q. Wei, C. Zhang, K. Zhou, L. Kong and W. Jiang, "Colon Polyp Detection and Segmentation Based on Improved MRCNN," in IEEE Transactions on Instrumentation and Measurement, 70 (2021) 1-10, Art no. 4501710, doi: 10.1109/TIM.2020.3038011.
[3] Md. Mahmodul Hasan, Nazrul Islam, Mohammad Motiur Rahman, Gastrointestinal polyp detection through a fusion of contourlet transform and Neural features, Journal of King Saud University - Computer and Information Sciences, 2020.
[4] Mostafiz, R., Rahman, M.M. & Uddin, M.S. Gastrointestinal polyp classification through empirical mode decomposition and neural features. SN Appl. Sci. 2, 1143 (2020). https://doi.org/10.1007/s42452-020-2944-4.
[5] Y. Shin, H. A. Qadir and I. Balasingham, Abnormal Colon Polyp Image Synthesis Using Conditional Adversarial Networks for Improved Detection Performance, in IEEE Access, vol. 6, pp. 56007-56017, 2018, doi: 10.1109/ACCESS.2018.2872717.
[6] Collins JT, Nguyen A, Badireddy M. Anatomy, Abdomen and Pelvis, Small Intestine. [Updated 2020 Aug 10]. In: StatPearls [Internet]. Treasure Island (FL): StatPearls Publishing; 2021 Jan.
[7] Cheng LK, O`Grady G, Du P, Egbuji JU, Windsor JA, Pullan AJ. Gastrointestinal system. Wiley Interdiscip Rev Syst Biol Med. 2010;2(1):65-79. doi:10.1002/wsbm.19
[8] Bauer, R.L., Palmer, M.L., Bauer, A.M. et al. Adenocarcinoma of the small intestine: 21-Year review of diagnosis, treatment, and prognosis. Annals of Surgical Oncology 1, 183–188 (1994). https://doi.org/10.1007/BF02303522.
[9] Boland CR, Luciani MG, Gasche C, Goel A. Infection, inflammation, and gastrointestinal cancer. Gut. 2005;54(9):1321-1331. doi:10.1136/gut.2004.060079.
[10] Bull MJ, Plummer NT. Part 1: The Human Gut Microbiome in Health and Disease. Integr Med (Encinitas). 2014;13(6):17-22.
[11] Marônek M, Link R, Monteleone G, Gardlík R, Stolfi C. Viruses in Cancers of the Digestive System: Active Contributors or Idle Bystanders?. Int J Mol Sci. 2020;21(21):8133. Published 2020 Oct 30. doi:10.3390/ijms21218133.
[12] Shussman N, Wexner SD. Colorectal polyps and polyposis syndromes. Gastroenterol Rep (Oxf). 2014;2(1):1-15. doi:10.1093/gastro/got041.
[13] Guobing Pan, Litong Wang, "Swallowable Wireless Capsule Endoscopy: Progress and Technical Challenges", Gastroenterology Research and Practice, vol. 2012, Article ID 841691, 9 pages, 2012. https://doi.org/10.1155/2012/841691.
[14] Redondo-Cerezo E, Sánchez-Capilla AD, De La Torre-Rubio P, De Teresa J. Wireless capsule endoscopy: perspectives beyond gastrointestinal bleeding. World J Gastroenterol. 2014;20(42):15664-15673. doi:10.3748/wjg.v20.i42.15664.
[15] M. R. Basar, F. Malek, Khairudi M. Juni, M. Shaharom Idris, M. Iskandar M. Saleh, "Ingestible Wireless Capsule Technology: A Review of Development and Future Indication", International Journal of Antennas and Propagation, vol. 2012, Article ID 807165, 14 pages, 2012. https://doi.org/10.1155/2012/807165.
[16] Alzubaidi, L., Zhang, J., Humaidi, A.J. et al. Review of deep learning: concepts, CNN architectures, challenges, applications, future directions. J Big Data 8, 53 (2021). https://doi.org/10.1186/s40537-021-00444-8.
[17] Yim J., Ju J., Jung H., Kim J. (2015) Image Classification Using Convolutional Neural Networks With Multi-stage Feature. In: Kim JH., Yang W., Jo J., Sincak P., Myung H. (eds) Robot Intelligence Technology and Applications 3. Advances in Intelligent Systems and Computing, vol 345. Springer, Cham. https://doi.org/10.1007/978-3-319-16841-8_52.
[18] P. Vasuki, J. Kanimozhi and M. B. Devi, "A survey on image preprocessing techniques for diverse fields of medical imagery," 2017 IEEE International Conference on Electrical, Instrumentation and Communication Engineering (ICEICE), 2017, pp. 1-6, doi: 10.1109/ICEICE.2017.8192443.
[19] J. A. Talingdan, Performance Comparison of Different Classification Algorithms for Household Poverty Classification, 2019 4th International Conference on Information Systems Engineering (ICISE), 2019, 11-15, doi: 10.1109/ICISE.2019.00010.
[20] Gopalakrishnan.S, Dr.Ebenezer Abishek.B, Dr. A. Vijayalakshmi, Dr. V. Rajendran Analysis And Diagnosis Using Deep -Learning Algorithm On Erythemato-Squamous Disease, International Journal of Engineering Trends and Technology 69(3) (2021) 52-57.