Colorectal Cancer Image Segmentation and Classification with Deep Neural Network Based on Information Theory

Hwa Rang Kim; Kwang Ju Kim; Kil Taek Lim; Doo Hyun Choi

doi:10.1109/BIBM49941.2020.9313157

Colorectal Cancer Image Segmentation and Classification with Deep Neural Network Based on Information Theory

Hwa Rang Kim
, Kwang Ju Kim
, Kil Taek Lim
, Doo Hyun Choi

School of Electronics Engineering

Kyungpook National University
Electronics and Telecommunications Research Institute

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

4 Scopus citations

Abstract

Colorectal cancer (CRC) is the development of cancer from the colon or rectum. Microsatellite instability (MSI) status can be considered as an indicator to predict the prognosis of CRC. We employ MSI prediction of CRC image by designing a neural network model of which base network is DeepLabv3+ with OctaveResNet. Additionally, we add a channel sort module to divide a feature map along with channel intensity. Then each feature map goes through distinct convolution paths. Each convolution path is designed based on information theory: the most important feature goes through the lightest convolution path, vice versa. By dividing feature map and applying different amount of convolutional operation, the model can extract features efficiently. In the experiment, total model weight is reduced but accuracy increases.

Original language	English
Title of host publication	Proceedings - 2020 IEEE International Conference on Bioinformatics and Biomedicine, BIBM 2020
Editors	Taesung Park, Young-Rae Cho, Xiaohua Tony Hu, Illhoi Yoo, Hyun Goo Woo, Jianxin Wang, Julio Facelli, Seungyoon Nam, Mingon Kang
Publisher	Institute of Electrical and Electronics Engineers Inc.
Pages	2968-2970
Number of pages	3
ISBN (Electronic)	9781728162157
DOIs	https://doi.org/10.1109/BIBM49941.2020.9313157
State	Published - 16 Dec 2020
Event	2020 IEEE International Conference on Bioinformatics and Biomedicine, BIBM 2020 - Virtual, Seoul, Korea, Republic of Duration: 16 Dec 2020 → 19 Dec 2020

Publication series

Name	Proceedings - 2020 IEEE International Conference on Bioinformatics and Biomedicine, BIBM 2020

Conference

Conference	2020 IEEE International Conference on Bioinformatics and Biomedicine, BIBM 2020
Country/Territory	Korea, Republic of
City	Virtual, Seoul
Period	16/12/20 → 19/12/20

UN SDGs

This output contributes to the following UN Sustainable Development Goals (SDGs)

SDG 3 Good Health and Well-being

Keywords

CRC
DeepLabv3+
Information theory
MSI
OctaveResNet

Access to Document

10.1109/BIBM49941.2020.9313157

Cite this

Kim, H. R., Kim, K. J., Lim, K. T., & Choi, D. H. (2020). Colorectal Cancer Image Segmentation and Classification with Deep Neural Network Based on Information Theory. In T. Park, Y.-R. Cho, X. T. Hu, I. Yoo, H. G. Woo, J. Wang, J. Facelli, S. Nam, & M. Kang (Eds.), Proceedings - 2020 IEEE International Conference on Bioinformatics and Biomedicine, BIBM 2020 (pp. 2968-2970). Article 9313157 (Proceedings - 2020 IEEE International Conference on Bioinformatics and Biomedicine, BIBM 2020). Institute of Electrical and Electronics Engineers Inc.. https://doi.org/10.1109/BIBM49941.2020.9313157

Kim, Hwa Rang ; Kim, Kwang Ju ; Lim, Kil Taek et al. / Colorectal Cancer Image Segmentation and Classification with Deep Neural Network Based on Information Theory. Proceedings - 2020 IEEE International Conference on Bioinformatics and Biomedicine, BIBM 2020. editor / Taesung Park ; Young-Rae Cho ; Xiaohua Tony Hu ; Illhoi Yoo ; Hyun Goo Woo ; Jianxin Wang ; Julio Facelli ; Seungyoon Nam ; Mingon Kang. Institute of Electrical and Electronics Engineers Inc., 2020. pp. 2968-2970 (Proceedings - 2020 IEEE International Conference on Bioinformatics and Biomedicine, BIBM 2020).

@inproceedings{533db86748544a8bb38e6ebc1c9b0d92,

title = "Colorectal Cancer Image Segmentation and Classification with Deep Neural Network Based on Information Theory",

abstract = "Colorectal cancer (CRC) is the development of cancer from the colon or rectum. Microsatellite instability (MSI) status can be considered as an indicator to predict the prognosis of CRC. We employ MSI prediction of CRC image by designing a neural network model of which base network is DeepLabv3+ with OctaveResNet. Additionally, we add a channel sort module to divide a feature map along with channel intensity. Then each feature map goes through distinct convolution paths. Each convolution path is designed based on information theory: the most important feature goes through the lightest convolution path, vice versa. By dividing feature map and applying different amount of convolutional operation, the model can extract features efficiently. In the experiment, total model weight is reduced but accuracy increases.",

keywords = "CRC, DeepLabv3+, Information theory, MSI, OctaveResNet",

author = "Kim, \{Hwa Rang\} and Kim, \{Kwang Ju\} and Lim, \{Kil Taek\} and Choi, \{Doo Hyun\}",

note = "Publisher Copyright: {\textcopyright} 2020 IEEE.; 2020 IEEE International Conference on Bioinformatics and Biomedicine, BIBM 2020 ; Conference date: 16-12-2020 Through 19-12-2020",

year = "2020",

month = dec,

day = "16",

doi = "10.1109/BIBM49941.2020.9313157",

language = "English",

series = "Proceedings - 2020 IEEE International Conference on Bioinformatics and Biomedicine, BIBM 2020",

publisher = "Institute of Electrical and Electronics Engineers Inc.",

pages = "2968--2970",

editor = "Taesung Park and Young-Rae Cho and Hu, \{Xiaohua Tony\} and Illhoi Yoo and Woo, \{Hyun Goo\} and Jianxin Wang and Julio Facelli and Seungyoon Nam and Mingon Kang",

booktitle = "Proceedings - 2020 IEEE International Conference on Bioinformatics and Biomedicine, BIBM 2020",

address = "United States",

}

Kim, HR, Kim, KJ, Lim, KT & Choi, DH 2020, Colorectal Cancer Image Segmentation and Classification with Deep Neural Network Based on Information Theory. in T Park, Y-R Cho, XT Hu, I Yoo, HG Woo, J Wang, J Facelli, S Nam & M Kang (eds), Proceedings - 2020 IEEE International Conference on Bioinformatics and Biomedicine, BIBM 2020., 9313157, Proceedings - 2020 IEEE International Conference on Bioinformatics and Biomedicine, BIBM 2020, Institute of Electrical and Electronics Engineers Inc., pp. 2968-2970, 2020 IEEE International Conference on Bioinformatics and Biomedicine, BIBM 2020, Virtual, Seoul, Korea, Republic of, 16/12/20. https://doi.org/10.1109/BIBM49941.2020.9313157

Colorectal Cancer Image Segmentation and Classification with Deep Neural Network Based on Information Theory. / Kim, Hwa Rang; Kim, Kwang Ju; Lim, Kil Taek et al.
Proceedings - 2020 IEEE International Conference on Bioinformatics and Biomedicine, BIBM 2020. ed. / Taesung Park; Young-Rae Cho; Xiaohua Tony Hu; Illhoi Yoo; Hyun Goo Woo; Jianxin Wang; Julio Facelli; Seungyoon Nam; Mingon Kang. Institute of Electrical and Electronics Engineers Inc., 2020. p. 2968-2970 9313157 (Proceedings - 2020 IEEE International Conference on Bioinformatics and Biomedicine, BIBM 2020).

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

TY - GEN

T1 - Colorectal Cancer Image Segmentation and Classification with Deep Neural Network Based on Information Theory

AU - Kim, Hwa Rang

AU - Kim, Kwang Ju

AU - Lim, Kil Taek

AU - Choi, Doo Hyun

PY - 2020/12/16

Y1 - 2020/12/16

N2 - Colorectal cancer (CRC) is the development of cancer from the colon or rectum. Microsatellite instability (MSI) status can be considered as an indicator to predict the prognosis of CRC. We employ MSI prediction of CRC image by designing a neural network model of which base network is DeepLabv3+ with OctaveResNet. Additionally, we add a channel sort module to divide a feature map along with channel intensity. Then each feature map goes through distinct convolution paths. Each convolution path is designed based on information theory: the most important feature goes through the lightest convolution path, vice versa. By dividing feature map and applying different amount of convolutional operation, the model can extract features efficiently. In the experiment, total model weight is reduced but accuracy increases.

AB - Colorectal cancer (CRC) is the development of cancer from the colon or rectum. Microsatellite instability (MSI) status can be considered as an indicator to predict the prognosis of CRC. We employ MSI prediction of CRC image by designing a neural network model of which base network is DeepLabv3+ with OctaveResNet. Additionally, we add a channel sort module to divide a feature map along with channel intensity. Then each feature map goes through distinct convolution paths. Each convolution path is designed based on information theory: the most important feature goes through the lightest convolution path, vice versa. By dividing feature map and applying different amount of convolutional operation, the model can extract features efficiently. In the experiment, total model weight is reduced but accuracy increases.

KW - CRC

KW - DeepLabv3+

KW - Information theory

KW - MSI

KW - OctaveResNet

UR - https://www.scopus.com/pages/publications/85100345751

U2 - 10.1109/BIBM49941.2020.9313157

DO - 10.1109/BIBM49941.2020.9313157

M3 - Conference contribution

AN - SCOPUS:85100345751

T3 - Proceedings - 2020 IEEE International Conference on Bioinformatics and Biomedicine, BIBM 2020

SP - 2968

EP - 2970

BT - Proceedings - 2020 IEEE International Conference on Bioinformatics and Biomedicine, BIBM 2020

A2 - Park, Taesung

A2 - Cho, Young-Rae

A2 - Hu, Xiaohua Tony

A2 - Yoo, Illhoi

A2 - Woo, Hyun Goo

A2 - Wang, Jianxin

A2 - Facelli, Julio

A2 - Nam, Seungyoon

A2 - Kang, Mingon

PB - Institute of Electrical and Electronics Engineers Inc.

T2 - 2020 IEEE International Conference on Bioinformatics and Biomedicine, BIBM 2020

Y2 - 16 December 2020 through 19 December 2020

ER -

Kim HR, Kim KJ, Lim KT, Choi DH. Colorectal Cancer Image Segmentation and Classification with Deep Neural Network Based on Information Theory. In Park T, Cho YR, Hu XT, Yoo I, Woo HG, Wang J, Facelli J, Nam S, Kang M, editors, Proceedings - 2020 IEEE International Conference on Bioinformatics and Biomedicine, BIBM 2020. Institute of Electrical and Electronics Engineers Inc. 2020. p. 2968-2970. 9313157. (Proceedings - 2020 IEEE International Conference on Bioinformatics and Biomedicine, BIBM 2020). doi: 10.1109/BIBM49941.2020.9313157

Colorectal Cancer Image Segmentation and Classification with Deep Neural Network Based on Information Theory

Abstract

Publication series

Conference

UN SDGs

Keywords

Access to Document

Other files and links

Fingerprint

Cite this