Small Bowel Detection for Wireless Capsule Endoscopy Using Convolutional Neural Networks with Temporal Filtering
By automatically classifying the stomach, small bowel, and colon, the reading time of the wireless capsule endoscopy (WCE) can be reduced. In addition, it is an essential first preprocessing step to localize the small bowel in order to apply automated small bowel lesion detection algorithms based on...
Main Authors: | , , , , , , , , |
---|---|
Format: | Article |
Language: | English |
Published: |
MDPI AG
2022-07-01
|
Series: | Diagnostics |
Subjects: | |
Online Access: | https://www.mdpi.com/2075-4418/12/8/1858 |
_version_ | 1797446092533530624 |
---|---|
author | Geonhui Son Taejoon Eo Jiwoong An Dong Jun Oh Yejee Shin Hyenogseop Rha You Jin Kim Yun Jeong Lim Dosik Hwang |
author_facet | Geonhui Son Taejoon Eo Jiwoong An Dong Jun Oh Yejee Shin Hyenogseop Rha You Jin Kim Yun Jeong Lim Dosik Hwang |
author_sort | Geonhui Son |
collection | DOAJ |
description | By automatically classifying the stomach, small bowel, and colon, the reading time of the wireless capsule endoscopy (WCE) can be reduced. In addition, it is an essential first preprocessing step to localize the small bowel in order to apply automated small bowel lesion detection algorithms based on deep learning. The purpose of the study was to develop an automated small bowel detection method from long untrimmed videos captured from WCE. Through this, the stomach and colon can also be distinguished. The proposed method is based on a convolutional neural network (CNN) with a temporal filtering on the predicted probabilities from the CNN. For CNN, we use a ResNet50 model to classify three organs including stomach, small bowel, and colon. The hybrid temporal filter consisting of a Savitzky–Golay filter and a median filter is applied to the temporal probabilities for the “small bowel” class. After filtering, the small bowel and the other two organs are differentiated with thresholding. The study was conducted on dataset of 200 patients (100 normal and 100 abnormal WCE cases), which was divided into a training set of 140 cases, a validation set of 20 cases, and a test set of 40 cases. For the test set of 40 patients (20 normal and 20 abnormal WCE cases), the proposed method showed accuracy of 99.8% in binary classification for the small bowel. Transition time errors for gastrointestinal tracts were only 38.8 ± 25.8 seconds for the transition between stomach and small bowel and 32.0 ± 19.1 seconds for the transition between small bowel and colon, compared to the ground truth organ transition points marked by two experienced gastroenterologists. |
first_indexed | 2024-03-09T13:35:17Z |
format | Article |
id | doaj.art-aa807aeffdab4c49a2cc577fb34d7a30 |
institution | Directory Open Access Journal |
issn | 2075-4418 |
language | English |
last_indexed | 2024-03-09T13:35:17Z |
publishDate | 2022-07-01 |
publisher | MDPI AG |
record_format | Article |
series | Diagnostics |
spelling | doaj.art-aa807aeffdab4c49a2cc577fb34d7a302023-11-30T21:12:56ZengMDPI AGDiagnostics2075-44182022-07-01128185810.3390/diagnostics12081858Small Bowel Detection for Wireless Capsule Endoscopy Using Convolutional Neural Networks with Temporal FilteringGeonhui Son0Taejoon Eo1Jiwoong An2Dong Jun Oh3Yejee Shin4Hyenogseop Rha5You Jin Kim6Yun Jeong Lim7Dosik Hwang8School of Electrical and Electronic Engineering, Yonsei University, Seoul 03722, KoreaSchool of Electrical and Electronic Engineering, Yonsei University, Seoul 03722, KoreaSchool of Electrical and Electronic Engineering, Yonsei University, Seoul 03722, KoreaDepartment of Internal Medicine, Dongguk University Ilsan Hospital, Dongguk University College of Medicine, Goyang 10326, KoreaSchool of Electrical and Electronic Engineering, Yonsei University, Seoul 03722, KoreaSchool of Electrical and Electronic Engineering, Yonsei University, Seoul 03722, KoreaIntroMedic, Capsule Endoscopy Medical Device Manufacturer, Seoul 08375, KoreaDepartment of Internal Medicine, Dongguk University Ilsan Hospital, Dongguk University College of Medicine, Goyang 10326, KoreaSchool of Electrical and Electronic Engineering, Yonsei University, Seoul 03722, KoreaBy automatically classifying the stomach, small bowel, and colon, the reading time of the wireless capsule endoscopy (WCE) can be reduced. In addition, it is an essential first preprocessing step to localize the small bowel in order to apply automated small bowel lesion detection algorithms based on deep learning. The purpose of the study was to develop an automated small bowel detection method from long untrimmed videos captured from WCE. Through this, the stomach and colon can also be distinguished. The proposed method is based on a convolutional neural network (CNN) with a temporal filtering on the predicted probabilities from the CNN. For CNN, we use a ResNet50 model to classify three organs including stomach, small bowel, and colon. The hybrid temporal filter consisting of a Savitzky–Golay filter and a median filter is applied to the temporal probabilities for the “small bowel” class. After filtering, the small bowel and the other two organs are differentiated with thresholding. The study was conducted on dataset of 200 patients (100 normal and 100 abnormal WCE cases), which was divided into a training set of 140 cases, a validation set of 20 cases, and a test set of 40 cases. For the test set of 40 patients (20 normal and 20 abnormal WCE cases), the proposed method showed accuracy of 99.8% in binary classification for the small bowel. Transition time errors for gastrointestinal tracts were only 38.8 ± 25.8 seconds for the transition between stomach and small bowel and 32.0 ± 19.1 seconds for the transition between small bowel and colon, compared to the ground truth organ transition points marked by two experienced gastroenterologists.https://www.mdpi.com/2075-4418/12/8/1858capsule endoscopysmall bowel detectionconvolutional neural networkstemporal filtering |
spellingShingle | Geonhui Son Taejoon Eo Jiwoong An Dong Jun Oh Yejee Shin Hyenogseop Rha You Jin Kim Yun Jeong Lim Dosik Hwang Small Bowel Detection for Wireless Capsule Endoscopy Using Convolutional Neural Networks with Temporal Filtering Diagnostics capsule endoscopy small bowel detection convolutional neural networks temporal filtering |
title | Small Bowel Detection for Wireless Capsule Endoscopy Using Convolutional Neural Networks with Temporal Filtering |
title_full | Small Bowel Detection for Wireless Capsule Endoscopy Using Convolutional Neural Networks with Temporal Filtering |
title_fullStr | Small Bowel Detection for Wireless Capsule Endoscopy Using Convolutional Neural Networks with Temporal Filtering |
title_full_unstemmed | Small Bowel Detection for Wireless Capsule Endoscopy Using Convolutional Neural Networks with Temporal Filtering |
title_short | Small Bowel Detection for Wireless Capsule Endoscopy Using Convolutional Neural Networks with Temporal Filtering |
title_sort | small bowel detection for wireless capsule endoscopy using convolutional neural networks with temporal filtering |
topic | capsule endoscopy small bowel detection convolutional neural networks temporal filtering |
url | https://www.mdpi.com/2075-4418/12/8/1858 |
work_keys_str_mv | AT geonhuison smallboweldetectionforwirelesscapsuleendoscopyusingconvolutionalneuralnetworkswithtemporalfiltering AT taejooneo smallboweldetectionforwirelesscapsuleendoscopyusingconvolutionalneuralnetworkswithtemporalfiltering AT jiwoongan smallboweldetectionforwirelesscapsuleendoscopyusingconvolutionalneuralnetworkswithtemporalfiltering AT dongjunoh smallboweldetectionforwirelesscapsuleendoscopyusingconvolutionalneuralnetworkswithtemporalfiltering AT yejeeshin smallboweldetectionforwirelesscapsuleendoscopyusingconvolutionalneuralnetworkswithtemporalfiltering AT hyenogseoprha smallboweldetectionforwirelesscapsuleendoscopyusingconvolutionalneuralnetworkswithtemporalfiltering AT youjinkim smallboweldetectionforwirelesscapsuleendoscopyusingconvolutionalneuralnetworkswithtemporalfiltering AT yunjeonglim smallboweldetectionforwirelesscapsuleendoscopyusingconvolutionalneuralnetworkswithtemporalfiltering AT dosikhwang smallboweldetectionforwirelesscapsuleendoscopyusingconvolutionalneuralnetworkswithtemporalfiltering |