Application of Convolutional Neural Networks for Automated Ulcer Detection in Wireless Capsule Endoscopy Images.

Haya Alaskar,Panos Liatsis,Abir Hussain,Nourah Al-Aseem,Dhiya Al-Jumeily

doi:10.3390/s19061265

Abstract

Detection of abnormalities in wireless capsule endoscopy (WCE) images is a challenging task. Typically, these images suffer from low contrast, complex background, variations in lesion shape and color, which affect the accuracy of their segmentation and subsequent classification. This research proposes an automated system for detection and classification of ulcers in WCE images, based on state-of-the-art deep learning networks. Deep learning techniques, and in particular, convolutional neural networks (CNNs), have recently become popular in the analysis and recognition of medical images. The medical image datasets used in this study were obtained from WCE video frames. In this work, two milestone CNN architectures, namely the AlexNet and the GoogLeNet are extensively evaluated in object classification into ulcer or non-ulcer. Furthermore, we examine and analyze the images identified as containing ulcer objects to evaluate the efficiency of the utilized CNNs. Extensive experiments show that CNNs deliver superior performance, surpassing traditional machine learning methods by large margins, which supports their effectiveness as automated diagnosis tools.

Highlights

Given that deep learning tools were successfully applied to image analysis, researchers have explored their application in medical image analysis [1,2,3,4,5,6,7,8]
The aim of the present study is to investigate the use of deep learning networks in the context of ulcer detection in wireless capsule endoscopy (WCE) images with high accuracy and speed
The experiments aimed at detecting ulcers in WCE images by applying two convolutional neural networks (CNNs) architectures, namely GoogLeNet and AlexNet

Summary

Introduction

Given that deep learning tools were successfully applied to image analysis, researchers have explored their application in medical image analysis [1,2,3,4,5,6,7,8]. Deep learning has proven to be a powerful machine learning tool and has demonstrated its ability in automated diagnosis of diseases [2,3,9] It has been considered for use in medical image analysis and recognition. It can improve medical image examination by enhancing the abilities of clinicians and health professionals in the context of early diagnosis. It can potentially help in prognosis and in the development of effective disease treatment regimes. Several deep learning models were developed and applied [3,4,6,9]

Objectives

Methods

Results

Conclusion