Gastroesophageal Reflux Disease Diagnosis Using Hierarchical Heterogeneous Descriptor Fusion Support Vector Machine

Chun Rong Huang, Yan Ting Chen, Wei-Yiing Chen, Hsiu-Chi Cheng, Bor-Shyang Sheu

研究成果: Article

6 引文 (Scopus)

摘要

A new computer-aided diagnosis method is proposed to diagnose the gastroesophageal reflux disease (GERD) from endoscopic images of the esophageal-gastric junction. To avoid the interferences of different endoscope devices and automatic camera white balance adjustment, heterogeneous descriptors computed from heterogeneous color models are used to represent endoscopic images. Instead of concatenating these descriptors to a super vector, a hierarchical heterogeneous descriptor fusion support vector machine (HHDF-SVM) framework is proposed to simultaneously apply heterogeneous descriptors for GERD diagnosis and overcome the curse of dimensionality problem. During validation, heterogeneous descriptors are extracted from test endoscopic images at first. The classification result is obtained by using HHDF-SVM with heterogeneous descriptors. As shown in the experiments, our method can automatically diagnose GERD without any manual selection of region of interest and achieve better accuracy compared to states-of-the-art methods.

原文English
文章編號7182761
頁(從 - 到)588-599
頁數12
期刊IEEE Transactions on Biomedical Engineering
63
發行號3
DOIs
出版狀態Published - 2016 三月 1

指紋

Support vector machines
Fusion reactions
Computer aided diagnosis
Endoscopy
Cameras
Color
Experiments

All Science Journal Classification (ASJC) codes

  • Biomedical Engineering

引用此文

@article{11c1ffedc6aa45f88bc4e1c04c4fbf94,
title = "Gastroesophageal Reflux Disease Diagnosis Using Hierarchical Heterogeneous Descriptor Fusion Support Vector Machine",
abstract = "A new computer-aided diagnosis method is proposed to diagnose the gastroesophageal reflux disease (GERD) from endoscopic images of the esophageal-gastric junction. To avoid the interferences of different endoscope devices and automatic camera white balance adjustment, heterogeneous descriptors computed from heterogeneous color models are used to represent endoscopic images. Instead of concatenating these descriptors to a super vector, a hierarchical heterogeneous descriptor fusion support vector machine (HHDF-SVM) framework is proposed to simultaneously apply heterogeneous descriptors for GERD diagnosis and overcome the curse of dimensionality problem. During validation, heterogeneous descriptors are extracted from test endoscopic images at first. The classification result is obtained by using HHDF-SVM with heterogeneous descriptors. As shown in the experiments, our method can automatically diagnose GERD without any manual selection of region of interest and achieve better accuracy compared to states-of-the-art methods.",
author = "Huang, {Chun Rong} and Chen, {Yan Ting} and Wei-Yiing Chen and Hsiu-Chi Cheng and Bor-Shyang Sheu",
year = "2016",
month = "3",
day = "1",
doi = "10.1109/TBME.2015.2466460",
language = "English",
volume = "63",
pages = "588--599",
journal = "IEEE Transactions on Biomedical Engineering",
issn = "0018-9294",
publisher = "IEEE Computer Society",
number = "3",

}

TY - JOUR

T1 - Gastroesophageal Reflux Disease Diagnosis Using Hierarchical Heterogeneous Descriptor Fusion Support Vector Machine

AU - Huang, Chun Rong

AU - Chen, Yan Ting

AU - Chen, Wei-Yiing

AU - Cheng, Hsiu-Chi

AU - Sheu, Bor-Shyang

PY - 2016/3/1

Y1 - 2016/3/1

N2 - A new computer-aided diagnosis method is proposed to diagnose the gastroesophageal reflux disease (GERD) from endoscopic images of the esophageal-gastric junction. To avoid the interferences of different endoscope devices and automatic camera white balance adjustment, heterogeneous descriptors computed from heterogeneous color models are used to represent endoscopic images. Instead of concatenating these descriptors to a super vector, a hierarchical heterogeneous descriptor fusion support vector machine (HHDF-SVM) framework is proposed to simultaneously apply heterogeneous descriptors for GERD diagnosis and overcome the curse of dimensionality problem. During validation, heterogeneous descriptors are extracted from test endoscopic images at first. The classification result is obtained by using HHDF-SVM with heterogeneous descriptors. As shown in the experiments, our method can automatically diagnose GERD without any manual selection of region of interest and achieve better accuracy compared to states-of-the-art methods.

AB - A new computer-aided diagnosis method is proposed to diagnose the gastroesophageal reflux disease (GERD) from endoscopic images of the esophageal-gastric junction. To avoid the interferences of different endoscope devices and automatic camera white balance adjustment, heterogeneous descriptors computed from heterogeneous color models are used to represent endoscopic images. Instead of concatenating these descriptors to a super vector, a hierarchical heterogeneous descriptor fusion support vector machine (HHDF-SVM) framework is proposed to simultaneously apply heterogeneous descriptors for GERD diagnosis and overcome the curse of dimensionality problem. During validation, heterogeneous descriptors are extracted from test endoscopic images at first. The classification result is obtained by using HHDF-SVM with heterogeneous descriptors. As shown in the experiments, our method can automatically diagnose GERD without any manual selection of region of interest and achieve better accuracy compared to states-of-the-art methods.

UR - http://www.scopus.com/inward/record.url?scp=84962069588&partnerID=8YFLogxK

UR - http://www.scopus.com/inward/citedby.url?scp=84962069588&partnerID=8YFLogxK

U2 - 10.1109/TBME.2015.2466460

DO - 10.1109/TBME.2015.2466460

M3 - Article

C2 - 26276981

AN - SCOPUS:84962069588

VL - 63

SP - 588

EP - 599

JO - IEEE Transactions on Biomedical Engineering

JF - IEEE Transactions on Biomedical Engineering

SN - 0018-9294

IS - 3

M1 - 7182761

ER -