Colorectal Disease Classification Using Efficiently Scaled Dilation in Convolutional Neural Network
Computer-aided diagnosis systems developed by computer vision researchers have helped doctors to recognize several endoscopic colorectal diseases more rapidly, which allows appropriate treatment and increases the patient's survival ratio. Herein, we present a robust architecture for endoscopic...
Main Authors: | , , , |
---|---|
Format: | Article |
Language: | English |
Published: |
IEEE
2020-01-01
|
Series: | IEEE Access |
Subjects: | |
Online Access: | https://ieeexplore.ieee.org/document/9098911/ |
id |
doaj-603f40d1e9f940e8ade813b22d083b64 |
---|---|
record_format |
Article |
spelling |
doaj-603f40d1e9f940e8ade813b22d083b642021-03-30T02:29:44ZengIEEEIEEE Access2169-35362020-01-018992279923810.1109/ACCESS.2020.29967709098911Colorectal Disease Classification Using Efficiently Scaled Dilation in Convolutional Neural NetworkSahadev Poudel0https://orcid.org/0000-0002-6574-038XYoon Jae Kim1Duc My Vo2Sang-Woong Lee3https://orcid.org/0000-0001-8117-6566Department of Software, Gachon University, Seongnam, South KoreaDepartment of Internal Medicine, Gachon University Gil Medical Center, Incheon, South KoreaDepartment of Software, Gachon University, Seongnam, South KoreaDepartment of Software, Gachon University, Seongnam, South KoreaComputer-aided diagnosis systems developed by computer vision researchers have helped doctors to recognize several endoscopic colorectal diseases more rapidly, which allows appropriate treatment and increases the patient's survival ratio. Herein, we present a robust architecture for endoscopic image classification using an efficient dilation in Convolutional Neural Network (CNNs). It has a high receptive field of view at the deep layers in increasing and decreasing dilation factor to preserve spatial details. We argue that dimensionality reduction in CNN can cause the loss of spatial information, resulting in miss of polyps and confusion in similar-looking images. Additionally, we use a regularization technique called DropBlock to reduce overfitting and deal with noise and artifacts. We compare and evaluate our method using various metrics: accuracy, recall, precision, and F1-score. Our experiments demonstrate that the proposed method provides the F1-score of 0.93 for Colorectal dataset and F1-score of 0.88 for KVASIR dataset. Experiments show higher accuracy of the proposed method over traditional methods when classifying endoscopic colon diseases.https://ieeexplore.ieee.org/document/9098911/Colorectal image classificationcolon disease classificationcolon disease classification with CNN |
collection |
DOAJ |
language |
English |
format |
Article |
sources |
DOAJ |
author |
Sahadev Poudel Yoon Jae Kim Duc My Vo Sang-Woong Lee |
spellingShingle |
Sahadev Poudel Yoon Jae Kim Duc My Vo Sang-Woong Lee Colorectal Disease Classification Using Efficiently Scaled Dilation in Convolutional Neural Network IEEE Access Colorectal image classification colon disease classification colon disease classification with CNN |
author_facet |
Sahadev Poudel Yoon Jae Kim Duc My Vo Sang-Woong Lee |
author_sort |
Sahadev Poudel |
title |
Colorectal Disease Classification Using Efficiently Scaled Dilation in Convolutional Neural Network |
title_short |
Colorectal Disease Classification Using Efficiently Scaled Dilation in Convolutional Neural Network |
title_full |
Colorectal Disease Classification Using Efficiently Scaled Dilation in Convolutional Neural Network |
title_fullStr |
Colorectal Disease Classification Using Efficiently Scaled Dilation in Convolutional Neural Network |
title_full_unstemmed |
Colorectal Disease Classification Using Efficiently Scaled Dilation in Convolutional Neural Network |
title_sort |
colorectal disease classification using efficiently scaled dilation in convolutional neural network |
publisher |
IEEE |
series |
IEEE Access |
issn |
2169-3536 |
publishDate |
2020-01-01 |
description |
Computer-aided diagnosis systems developed by computer vision researchers have helped doctors to recognize several endoscopic colorectal diseases more rapidly, which allows appropriate treatment and increases the patient's survival ratio. Herein, we present a robust architecture for endoscopic image classification using an efficient dilation in Convolutional Neural Network (CNNs). It has a high receptive field of view at the deep layers in increasing and decreasing dilation factor to preserve spatial details. We argue that dimensionality reduction in CNN can cause the loss of spatial information, resulting in miss of polyps and confusion in similar-looking images. Additionally, we use a regularization technique called DropBlock to reduce overfitting and deal with noise and artifacts. We compare and evaluate our method using various metrics: accuracy, recall, precision, and F1-score. Our experiments demonstrate that the proposed method provides the F1-score of 0.93 for Colorectal dataset and F1-score of 0.88 for KVASIR dataset. Experiments show higher accuracy of the proposed method over traditional methods when classifying endoscopic colon diseases. |
topic |
Colorectal image classification colon disease classification colon disease classification with CNN |
url |
https://ieeexplore.ieee.org/document/9098911/ |
work_keys_str_mv |
AT sahadevpoudel colorectaldiseaseclassificationusingefficientlyscaleddilationinconvolutionalneuralnetwork AT yoonjaekim colorectaldiseaseclassificationusingefficientlyscaleddilationinconvolutionalneuralnetwork AT ducmyvo colorectaldiseaseclassificationusingefficientlyscaleddilationinconvolutionalneuralnetwork AT sangwoonglee colorectaldiseaseclassificationusingefficientlyscaleddilationinconvolutionalneuralnetwork |
_version_ |
1724185068502515712 |