A convolutional neural network approach for abnormality detection in Wireless Capsule Endoscopy

Sekuboyina, A K and Devarakonda, S T and Seelamantula, C S (2017) A convolutional neural network approach for abnormality detection in Wireless Capsule Endoscopy. In: IEEE International Symposium on Biomedical Imaging, ISBI, 18-21 April 2017, Melbourne Convention and Exhibition Centre, Melbourne; Australia.

Full text not available from this repository. (Request a copy)

Abstract

In wireless capsule endoscopy (WCE), a swallowable 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 paper, 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.

[error in script]
IITH Creators:
IITH CreatorsORCiD
Item Type: Conference or Workshop Item (Paper)
Uncontrolled Keywords: Classification; Convolutional neural networks; Gastrointestinal tract; Wireless capsule endoscopy
Subjects: Electrical Engineering > Wireless Communication
Electrical Engineering > Instruments and Instrumentation
Divisions: Department of Electrical Engineering
Depositing User: Team Library
Date Deposited: 08 Aug 2017 09:31
Last Modified: 08 Aug 2017 09:31
URI: http://raiith.iith.ac.in/id/eprint/3472
Publisher URL: https://doi.org/10.1109/ISBI.2017.7950698
Related URLs:

Actions (login required)

View Item View Item
Statistics for RAIITH ePrint 3472 Statistics for this ePrint Item