Deep convolutional neural network-based automated lesion detection in wireless capsule endoscopy

Yejin Jeon; Eunbyul Cho; Sehwa Moon; Seung Hoon Chae; Hae Young Jo; Tae Oh Kim; Chang Mo Moon; Jang Hwan Choi

doi:10.1117/12.2522159

Deep convolutional neural network-based automated lesion detection in wireless capsule endoscopy

Yejin Jeon, Eunbyul Cho, Sehwa Moon, Seung Hoon Chae, Hae Young Jo, Tae Oh Kim, Chang Mo Moon, Jang Hwan Choi

Research output: Chapter in Book/Report/Conference proceeding › Conference contribution › peer-review

7 Scopus citations

Abstract

Because most of the capsule-endoscopic images contain normal mucous membranes, physicians spend most of their reading time observing normal areas. Thus, a significant reduction in their reading time would be possible if only the portion of the image frame for which a particular lesion is suspected can be read intensively. This study aims to develop a deep convolutional neural-network-based model capable of automatically detecting lesions in the capsule-endoscopic images of a small bowel. The proposed model consists of two deep neural networks in parallel, each of which takes in images in RGB and CIELab color spaces, respectively. The neural-networks model is based on transfer-learned GoogLeNet architecture. Our proposed algorithm showed promising results in classifying endoscopic images where lesions exist (98.56% accuracy). If the proposed algorithm is used to screen abnormal images, it is expected to reduce a physician's reading time and to improve his/her reading accuracy.

Original language	English
Title of host publication	International Forum on Medical Imaging in Asia 2019
Editors	Feng Lin, Hiroshi Fujita, Jong Hyo Kim
Publisher	SPIE
ISBN (Electronic)	9781510627758
DOIs	https://doi.org/10.1117/12.2522159
State	Published - 2019
Event	International Forum on Medical Imaging in Asia 2019 - Singapore, Singapore Duration: 7 Jan 2019 → 9 Jan 2019

Publication series

Name	Proceedings of SPIE - The International Society for Optical Engineering
Volume	11050
ISSN (Print)	0277-786X
ISSN (Electronic)	1996-756X

Conference

Conference	International Forum on Medical Imaging in Asia 2019
Country/Territory	Singapore
City	Singapore
Period	7/01/19 → 9/01/19

Bibliographical note

Publisher Copyright:
© 2019 SPIE.

Keywords

Convolutional neural Networks
Deep neural networks
Lesion detection
Small bowel tumor
Small-bowel Wireless Capsule Endoscopy
Wireless capsule endoscopy

Access to Document

10.1117/12.2522159

Cite this

Jeon, Y., Cho, E., Moon, S., Chae, S. H., Jo, H. Y., Kim, T. O., Moon, C. M., & Choi, J. H. (2019). Deep convolutional neural network-based automated lesion detection in wireless capsule endoscopy. In F. Lin, H. Fujita, & J. H. Kim (Eds.), International Forum on Medical Imaging in Asia 2019 Article 110501N (Proceedings of SPIE - The International Society for Optical Engineering; Vol. 11050). SPIE. https://doi.org/10.1117/12.2522159

@inproceedings{157b63610ee845ebaed3f88ad223f23d,

title = "Deep convolutional neural network-based automated lesion detection in wireless capsule endoscopy",

abstract = "Because most of the capsule-endoscopic images contain normal mucous membranes, physicians spend most of their reading time observing normal areas. Thus, a significant reduction in their reading time would be possible if only the portion of the image frame for which a particular lesion is suspected can be read intensively. This study aims to develop a deep convolutional neural-network-based model capable of automatically detecting lesions in the capsule-endoscopic images of a small bowel. The proposed model consists of two deep neural networks in parallel, each of which takes in images in RGB and CIELab color spaces, respectively. The neural-networks model is based on transfer-learned GoogLeNet architecture. Our proposed algorithm showed promising results in classifying endoscopic images where lesions exist (98.56% accuracy). If the proposed algorithm is used to screen abnormal images, it is expected to reduce a physician's reading time and to improve his/her reading accuracy.",

keywords = "Convolutional neural Networks, Deep neural networks, Lesion detection, Small bowel tumor, Small-bowel Wireless Capsule Endoscopy, Wireless capsule endoscopy",

author = "Yejin Jeon and Eunbyul Cho and Sehwa Moon and Chae, {Seung Hoon} and Jo, {Hae Young} and Kim, {Tae Oh} and Moon, {Chang Mo} and Choi, {Jang Hwan}",

note = "Publisher Copyright: {\textcopyright} 2019 SPIE.; International Forum on Medical Imaging in Asia 2019 ; Conference date: 07-01-2019 Through 09-01-2019",

year = "2019",

doi = "10.1117/12.2522159",

language = "English",

series = "Proceedings of SPIE - The International Society for Optical Engineering",

publisher = "SPIE",

editor = "Feng Lin and Hiroshi Fujita and Kim, {Jong Hyo}",

booktitle = "International Forum on Medical Imaging in Asia 2019",

}

Jeon, Y, Cho, E, Moon, S, Chae, SH, Jo, HY, Kim, TO, Moon, CM & Choi, JH 2019, Deep convolutional neural network-based automated lesion detection in wireless capsule endoscopy. in F Lin, H Fujita & JH Kim (eds), International Forum on Medical Imaging in Asia 2019., 110501N, Proceedings of SPIE - The International Society for Optical Engineering, vol. 11050, SPIE, International Forum on Medical Imaging in Asia 2019, Singapore, Singapore, 7/01/19. https://doi.org/10.1117/12.2522159

Deep convolutional neural network-based automated lesion detection in wireless capsule endoscopy. / Jeon, Yejin; Cho, Eunbyul; Moon, Sehwa et al.
International Forum on Medical Imaging in Asia 2019. ed. / Feng Lin; Hiroshi Fujita; Jong Hyo Kim. SPIE, 2019. 110501N (Proceedings of SPIE - The International Society for Optical Engineering; Vol. 11050).

Research output: Chapter in Book/Report/Conference proceeding › Conference contribution › peer-review

TY - GEN

T1 - Deep convolutional neural network-based automated lesion detection in wireless capsule endoscopy

AU - Jeon, Yejin

AU - Cho, Eunbyul

AU - Moon, Sehwa

AU - Chae, Seung Hoon

AU - Jo, Hae Young

AU - Kim, Tae Oh

AU - Moon, Chang Mo

AU - Choi, Jang Hwan

PY - 2019

Y1 - 2019

N2 - Because most of the capsule-endoscopic images contain normal mucous membranes, physicians spend most of their reading time observing normal areas. Thus, a significant reduction in their reading time would be possible if only the portion of the image frame for which a particular lesion is suspected can be read intensively. This study aims to develop a deep convolutional neural-network-based model capable of automatically detecting lesions in the capsule-endoscopic images of a small bowel. The proposed model consists of two deep neural networks in parallel, each of which takes in images in RGB and CIELab color spaces, respectively. The neural-networks model is based on transfer-learned GoogLeNet architecture. Our proposed algorithm showed promising results in classifying endoscopic images where lesions exist (98.56% accuracy). If the proposed algorithm is used to screen abnormal images, it is expected to reduce a physician's reading time and to improve his/her reading accuracy.

AB - Because most of the capsule-endoscopic images contain normal mucous membranes, physicians spend most of their reading time observing normal areas. Thus, a significant reduction in their reading time would be possible if only the portion of the image frame for which a particular lesion is suspected can be read intensively. This study aims to develop a deep convolutional neural-network-based model capable of automatically detecting lesions in the capsule-endoscopic images of a small bowel. The proposed model consists of two deep neural networks in parallel, each of which takes in images in RGB and CIELab color spaces, respectively. The neural-networks model is based on transfer-learned GoogLeNet architecture. Our proposed algorithm showed promising results in classifying endoscopic images where lesions exist (98.56% accuracy). If the proposed algorithm is used to screen abnormal images, it is expected to reduce a physician's reading time and to improve his/her reading accuracy.

KW - Convolutional neural Networks

KW - Deep neural networks

KW - Lesion detection

KW - Small bowel tumor

KW - Small-bowel Wireless Capsule Endoscopy

KW - Wireless capsule endoscopy

UR - http://www.scopus.com/inward/record.url?scp=85063908165&partnerID=8YFLogxK

U2 - 10.1117/12.2522159

DO - 10.1117/12.2522159

M3 - Conference contribution

AN - SCOPUS:85063908165

T3 - Proceedings of SPIE - The International Society for Optical Engineering

BT - International Forum on Medical Imaging in Asia 2019

A2 - Lin, Feng

A2 - Fujita, Hiroshi

A2 - Kim, Jong Hyo

PB - SPIE

T2 - International Forum on Medical Imaging in Asia 2019

Y2 - 7 January 2019 through 9 January 2019

ER -

Deep convolutional neural network-based automated lesion detection in wireless capsule endoscopy

Abstract

Publication series

Conference

Bibliographical note

Keywords

Access to Document

Fingerprint

Cite this