Deep Model-Based Semi-Supervised Learning Way for Outlier Detection in Wireless Capsule Endoscopy Images
Wireless capsule endoscopy (WCE) has become an irreplaceable tool for diagnosing small intestinal diseases, and detecting the outliers in WCE images automatically remains as a hot research topic. Considering the difficulties in obtaining sufficient labeled WCE data, it is necessary to develop the di...
Main Authors: | , , , |
---|---|
Format: | Article |
Language: | English |
Published: |
IEEE
2020-01-01
|
Series: | IEEE Access |
Subjects: | |
Online Access: | https://ieeexplore.ieee.org/document/9079823/ |
id |
doaj-ce3421e1edbf406c88e6d0f0f81416be |
---|---|
record_format |
Article |
spelling |
doaj-ce3421e1edbf406c88e6d0f0f81416be2021-03-30T01:42:55ZengIEEEIEEE Access2169-35362020-01-018816218163210.1109/ACCESS.2020.29911159079823Deep Model-Based Semi-Supervised Learning Way for Outlier Detection in Wireless Capsule Endoscopy ImagesYan Gao0Weining Lu1https://orcid.org/0000-0002-0927-1259Xiaobei Si2Yu Lan3Department of Gastroenterology, Beijing Jishuitan Hospital, Beijing, ChinaBeijing National Research Center for Information Science and Technology, Tsinghua University, Beijing, ChinaDepartment of Gastroenterology, Beijing Jishuitan Hospital, Beijing, ChinaDepartment of Gastroenterology, Beijing Jishuitan Hospital, Beijing, ChinaWireless capsule endoscopy (WCE) has become an irreplaceable tool for diagnosing small intestinal diseases, and detecting the outliers in WCE images automatically remains as a hot research topic. Considering the difficulties in obtaining sufficient labeled WCE data, it is necessary to develop the diagnosis model which works well with only little labeled or even unlabeled training samples. In this paper, a novel semi-supervised deep-structured framework is introduced to solve the problem of outlier detection in WCE images. The key idea of our model is to mine the anomalous graphical patterns existed in the image by analyzing the spatial-scale trends of sequential image regions. Three main contributions are concluded: 1) we integrate a convolutional neural network into long short term memory network, so that the intrinsic differences between outliers and normal instances could be captured. Besides, 2) a assessment model is built by using various signs of anomaly occurrence and fake outliers knowledge learned during the training stage, which enhances the outlier alarm accuracy significantly. Furthermore, 3) a nest-structured training method is proposed, which helps our model achieving efficient training process. Experimental results on the real WCE images demonstrate the effectiveness of our model.https://ieeexplore.ieee.org/document/9079823/Convolutional neural networklong short term memory networkoutlier detectionsemi-supervisedwireless capsule endoscopy |
collection |
DOAJ |
language |
English |
format |
Article |
sources |
DOAJ |
author |
Yan Gao Weining Lu Xiaobei Si Yu Lan |
spellingShingle |
Yan Gao Weining Lu Xiaobei Si Yu Lan Deep Model-Based Semi-Supervised Learning Way for Outlier Detection in Wireless Capsule Endoscopy Images IEEE Access Convolutional neural network long short term memory network outlier detection semi-supervised wireless capsule endoscopy |
author_facet |
Yan Gao Weining Lu Xiaobei Si Yu Lan |
author_sort |
Yan Gao |
title |
Deep Model-Based Semi-Supervised Learning Way for Outlier Detection in Wireless Capsule Endoscopy Images |
title_short |
Deep Model-Based Semi-Supervised Learning Way for Outlier Detection in Wireless Capsule Endoscopy Images |
title_full |
Deep Model-Based Semi-Supervised Learning Way for Outlier Detection in Wireless Capsule Endoscopy Images |
title_fullStr |
Deep Model-Based Semi-Supervised Learning Way for Outlier Detection in Wireless Capsule Endoscopy Images |
title_full_unstemmed |
Deep Model-Based Semi-Supervised Learning Way for Outlier Detection in Wireless Capsule Endoscopy Images |
title_sort |
deep model-based semi-supervised learning way for outlier detection in wireless capsule endoscopy images |
publisher |
IEEE |
series |
IEEE Access |
issn |
2169-3536 |
publishDate |
2020-01-01 |
description |
Wireless capsule endoscopy (WCE) has become an irreplaceable tool for diagnosing small intestinal diseases, and detecting the outliers in WCE images automatically remains as a hot research topic. Considering the difficulties in obtaining sufficient labeled WCE data, it is necessary to develop the diagnosis model which works well with only little labeled or even unlabeled training samples. In this paper, a novel semi-supervised deep-structured framework is introduced to solve the problem of outlier detection in WCE images. The key idea of our model is to mine the anomalous graphical patterns existed in the image by analyzing the spatial-scale trends of sequential image regions. Three main contributions are concluded: 1) we integrate a convolutional neural network into long short term memory network, so that the intrinsic differences between outliers and normal instances could be captured. Besides, 2) a assessment model is built by using various signs of anomaly occurrence and fake outliers knowledge learned during the training stage, which enhances the outlier alarm accuracy significantly. Furthermore, 3) a nest-structured training method is proposed, which helps our model achieving efficient training process. Experimental results on the real WCE images demonstrate the effectiveness of our model. |
topic |
Convolutional neural network long short term memory network outlier detection semi-supervised wireless capsule endoscopy |
url |
https://ieeexplore.ieee.org/document/9079823/ |
work_keys_str_mv |
AT yangao deepmodelbasedsemisupervisedlearningwayforoutlierdetectioninwirelesscapsuleendoscopyimages AT weininglu deepmodelbasedsemisupervisedlearningwayforoutlierdetectioninwirelesscapsuleendoscopyimages AT xiaobeisi deepmodelbasedsemisupervisedlearningwayforoutlierdetectioninwirelesscapsuleendoscopyimages AT yulan deepmodelbasedsemisupervisedlearningwayforoutlierdetectioninwirelesscapsuleendoscopyimages |
_version_ |
1724186595740876800 |