A Convolutional Neural Network Based Disease Diagnosis in Wireless Capsule Endoscopy Images
R.Sathiya1, R.KalaiMagal2

1Mrs.R.Sathiya*, Research Scholar, Computer Science, Development Centre, Bharathiyar University, Coimbatore.
2Dr.R. Kalai Magal,  Associate Professor in Computer Science, Government Arts College for Men, Nandhanam, Chennai.
Manuscript received on September 22, 2019. | Revised Manuscript received on October 20, 2019. | Manuscript published on October 30, 2019. | PP: 327-331 | Volume-9 Issue-1, October 2019 | Retrieval Number: F8515088619/2019©BEIESP | DOI: 10.35940/ijeat.F8515.109119
Open Access | Ethics and Policies | Cite | Mendeley
© The Authors. Blue Eyes Intelligence Engineering and Sciences Publication (BEIESP). This is an open access article under the CC BY-NC-ND license (http://creativecommons.org/licenses/by-nc-nd/4.0/)

Abstract: In wireless capsule endoscopy (WCE), a swallow-able miniature optical endoscope is used to transmit color images of the gastrointestinal tract. However, the number of images transmitted is large, taking a significant amount of the medical expert’s time to review the scan. In this research, we propose a technique to automate the abnormality detection in WCE images. We split the image into several patches and extract features pertaining to each block using a Convolutional neural network (CNN) to increase their generality while overcoming the drawbacks of manually crafted features. We intend to exploit the importance of color information for the task. Experiments are performed to determine the optimal color space components for feature extraction and classifier design. We obtained an area under receiver-operating-characteristic (ROC) curve of approximately 0.8 on a dataset containing multiple abnormalities.
Keywords: Gastrointestinal tract, Classification, Wireless capsule endoscopy, Convolutional neural networks.