Classification of ulcerative colitis severity in colonoscopy videos using CNN

Ali Alammari, A. B.M.Rezbaul Islam, Jung Hwan Oh, Wallapak Tavanapong, Johnny Wong, Piet C. De Groen

Research output: Chapter in Book/Report/Conference proceedingConference contribution

2 Citations (Scopus)

Abstract

Ulcerative Colitis (UC) is a chronic inflammatory disease characterized by periods of relapses and remissions affecting more than 500,000 people in the United States. The therapeutic goals of UC are to first induce and then maintain disease remission. However, it is very difficult to evaluate the severity of UC objectively because of non-uniform nature of symptoms and large variations in their patterns. To address this, we already developed an approach using the image textures in our previous work. But, we found that it could not handle larger number of variations in their patterns. In this paper, we propose a different approach using CNN (Convolutional Neural Network) to measure and classify objectively the severity of UC presented in optical colonoscopy video frames. We call the proposed approach using CNN as Ulcerative Colitis Severity CNN (UCS-CNN) which utilizes endoscopic domain knowledge and convolutional neural network to classify different UC severity of colonoscopy images. The experimental results show that the proposed UCS-CNN can evaluate the severity of UC reasonably.

Original languageEnglish (US)
Title of host publication2017 9th International Conference on Information Management and Engineering, ICIME 2017
PublisherAssociation for Computing Machinery
Pages139-144
Number of pages6
VolumePart F133044
ISBN (Electronic)9781450353373
DOIs
StatePublished - Oct 9 2017
Externally publishedYes
Event9th International Conference on Information Management and Engineering, ICIME 2017 - Barcelona, Spain
Duration: Oct 9 2017Oct 11 2017

Other

Other9th International Conference on Information Management and Engineering, ICIME 2017
CountrySpain
CityBarcelona
Period10/9/1710/11/17

Fingerprint

Neural networks
Image texture

Keywords

  • Convolutional neural network
  • Medical image classification
  • Medical video processing
  • Ulcerative colitis severity

ASJC Scopus subject areas

  • Human-Computer Interaction
  • Computer Networks and Communications
  • Computer Vision and Pattern Recognition
  • Software

Cite this

Alammari, A., Islam, A. B. M. R., Oh, J. H., Tavanapong, W., Wong, J., & De Groen, P. C. (2017). Classification of ulcerative colitis severity in colonoscopy videos using CNN. In 2017 9th International Conference on Information Management and Engineering, ICIME 2017 (Vol. Part F133044, pp. 139-144). Association for Computing Machinery. https://doi.org/10.1145/3149572.3149613

Classification of ulcerative colitis severity in colonoscopy videos using CNN. / Alammari, Ali; Islam, A. B.M.Rezbaul; Oh, Jung Hwan; Tavanapong, Wallapak; Wong, Johnny; De Groen, Piet C.

2017 9th International Conference on Information Management and Engineering, ICIME 2017. Vol. Part F133044 Association for Computing Machinery, 2017. p. 139-144.

Research output: Chapter in Book/Report/Conference proceedingConference contribution

Alammari, A, Islam, ABMR, Oh, JH, Tavanapong, W, Wong, J & De Groen, PC 2017, Classification of ulcerative colitis severity in colonoscopy videos using CNN. in 2017 9th International Conference on Information Management and Engineering, ICIME 2017. vol. Part F133044, Association for Computing Machinery, pp. 139-144, 9th International Conference on Information Management and Engineering, ICIME 2017, Barcelona, Spain, 10/9/17. https://doi.org/10.1145/3149572.3149613
Alammari A, Islam ABMR, Oh JH, Tavanapong W, Wong J, De Groen PC. Classification of ulcerative colitis severity in colonoscopy videos using CNN. In 2017 9th International Conference on Information Management and Engineering, ICIME 2017. Vol. Part F133044. Association for Computing Machinery. 2017. p. 139-144 https://doi.org/10.1145/3149572.3149613
Alammari, Ali ; Islam, A. B.M.Rezbaul ; Oh, Jung Hwan ; Tavanapong, Wallapak ; Wong, Johnny ; De Groen, Piet C. / Classification of ulcerative colitis severity in colonoscopy videos using CNN. 2017 9th International Conference on Information Management and Engineering, ICIME 2017. Vol. Part F133044 Association for Computing Machinery, 2017. pp. 139-144
@inproceedings{9b1b6c920c1048d08df07419a250b527,
title = "Classification of ulcerative colitis severity in colonoscopy videos using CNN",
abstract = "Ulcerative Colitis (UC) is a chronic inflammatory disease characterized by periods of relapses and remissions affecting more than 500,000 people in the United States. The therapeutic goals of UC are to first induce and then maintain disease remission. However, it is very difficult to evaluate the severity of UC objectively because of non-uniform nature of symptoms and large variations in their patterns. To address this, we already developed an approach using the image textures in our previous work. But, we found that it could not handle larger number of variations in their patterns. In this paper, we propose a different approach using CNN (Convolutional Neural Network) to measure and classify objectively the severity of UC presented in optical colonoscopy video frames. We call the proposed approach using CNN as Ulcerative Colitis Severity CNN (UCS-CNN) which utilizes endoscopic domain knowledge and convolutional neural network to classify different UC severity of colonoscopy images. The experimental results show that the proposed UCS-CNN can evaluate the severity of UC reasonably.",
keywords = "Convolutional neural network, Medical image classification, Medical video processing, Ulcerative colitis severity",
author = "Ali Alammari and Islam, {A. B.M.Rezbaul} and Oh, {Jung Hwan} and Wallapak Tavanapong and Johnny Wong and {De Groen}, {Piet C.}",
year = "2017",
month = "10",
day = "9",
doi = "10.1145/3149572.3149613",
language = "English (US)",
volume = "Part F133044",
pages = "139--144",
booktitle = "2017 9th International Conference on Information Management and Engineering, ICIME 2017",
publisher = "Association for Computing Machinery",

}

TY - GEN

T1 - Classification of ulcerative colitis severity in colonoscopy videos using CNN

AU - Alammari, Ali

AU - Islam, A. B.M.Rezbaul

AU - Oh, Jung Hwan

AU - Tavanapong, Wallapak

AU - Wong, Johnny

AU - De Groen, Piet C.

PY - 2017/10/9

Y1 - 2017/10/9

N2 - Ulcerative Colitis (UC) is a chronic inflammatory disease characterized by periods of relapses and remissions affecting more than 500,000 people in the United States. The therapeutic goals of UC are to first induce and then maintain disease remission. However, it is very difficult to evaluate the severity of UC objectively because of non-uniform nature of symptoms and large variations in their patterns. To address this, we already developed an approach using the image textures in our previous work. But, we found that it could not handle larger number of variations in their patterns. In this paper, we propose a different approach using CNN (Convolutional Neural Network) to measure and classify objectively the severity of UC presented in optical colonoscopy video frames. We call the proposed approach using CNN as Ulcerative Colitis Severity CNN (UCS-CNN) which utilizes endoscopic domain knowledge and convolutional neural network to classify different UC severity of colonoscopy images. The experimental results show that the proposed UCS-CNN can evaluate the severity of UC reasonably.

AB - Ulcerative Colitis (UC) is a chronic inflammatory disease characterized by periods of relapses and remissions affecting more than 500,000 people in the United States. The therapeutic goals of UC are to first induce and then maintain disease remission. However, it is very difficult to evaluate the severity of UC objectively because of non-uniform nature of symptoms and large variations in their patterns. To address this, we already developed an approach using the image textures in our previous work. But, we found that it could not handle larger number of variations in their patterns. In this paper, we propose a different approach using CNN (Convolutional Neural Network) to measure and classify objectively the severity of UC presented in optical colonoscopy video frames. We call the proposed approach using CNN as Ulcerative Colitis Severity CNN (UCS-CNN) which utilizes endoscopic domain knowledge and convolutional neural network to classify different UC severity of colonoscopy images. The experimental results show that the proposed UCS-CNN can evaluate the severity of UC reasonably.

KW - Convolutional neural network

KW - Medical image classification

KW - Medical video processing

KW - Ulcerative colitis severity

UR - http://www.scopus.com/inward/record.url?scp=85045668303&partnerID=8YFLogxK

UR - http://www.scopus.com/inward/citedby.url?scp=85045668303&partnerID=8YFLogxK

U2 - 10.1145/3149572.3149613

DO - 10.1145/3149572.3149613

M3 - Conference contribution

AN - SCOPUS:85045668303

VL - Part F133044

SP - 139

EP - 144

BT - 2017 9th International Conference on Information Management and Engineering, ICIME 2017

PB - Association for Computing Machinery

ER -