Classification of tissue types in histological colorectal cancer images using residual networks

Ko Hua Lai; Meng Chou Chang

doi:10.1109/GCCE46687.2019.9015250

Classification of tissue types in histological colorectal cancer images using residual networks

Ko Hua Lai
, Meng Chou Chang

National Changhua University of Education

研究成果: 圖書/報告稿件的類型 › 會議稿件 › 同行評審

8 引文斯高帕斯（Scopus）

摘要

Colorectal cancer (CRC) is one of the most prevalent cancer types, but until now only few studies have addressed the problem of automatic recognition of distinct tissue types in histological CRC images. In this paper, we employ two deep convolutional neural networks, the original 50-layer residual network ResNet-50 and a modified residual network ResNet-50-fla-drop, to automatically perform eight-class tissue separation in histological CRC images. Experimental results showed that the proposed modified residual network ResNet-50-fla-drop can achieve a classification accuracy of 94.4% for eight-class CRC tissue separation, and it outperforms other published machine learning methods, including the radial-basis function SVM and VGG-VD-16.

原文	英語
主出版物標題	2019 IEEE 8th Global Conference on Consumer Electronics, GCCE 2019
發行者	Institute of Electrical and Electronics Engineers Inc.
頁面	299-300
頁數	2
ISBN（電子）	9781728135755
DOIs	https://doi.org/10.1109/GCCE46687.2019.9015250
出版狀態	已出版 - 10 2019
對外發佈	是
事件	8th IEEE Global Conference on Consumer Electronics, GCCE 2019 - Osaka, 日本持續時間: 15 10 2019 → 18 10 2019

出版系列

名字	2019 IEEE 8th Global Conference on Consumer Electronics, GCCE 2019

Conference

Conference	8th IEEE Global Conference on Consumer Electronics, GCCE 2019
國家/地區	日本
城市	Osaka
期間	15/10/19 → 18/10/19

文獻附註

Publisher Copyright:
© 2019 IEEE.

UN SDG

此研究成果有助於以下永續發展目標

SDG3 健康與福祉

存取文件

10.1109/GCCE46687.2019.9015250

其它文件與鏈接

Link to publication in Scopus

引用此

Lai, K. H., & Chang, M. C. (2019). Classification of tissue types in histological colorectal cancer images using residual networks. 於 2019 IEEE 8th Global Conference on Consumer Electronics, GCCE 2019 (頁 299-300). 文章 9015250 (2019 IEEE 8th Global Conference on Consumer Electronics, GCCE 2019). Institute of Electrical and Electronics Engineers Inc.. https://doi.org/10.1109/GCCE46687.2019.9015250

@inproceedings{221a373e27a3469da855c63969b759d8,

title = "Classification of tissue types in histological colorectal cancer images using residual networks",

abstract = "Colorectal cancer (CRC) is one of the most prevalent cancer types, but until now only few studies have addressed the problem of automatic recognition of distinct tissue types in histological CRC images. In this paper, we employ two deep convolutional neural networks, the original 50-layer residual network ResNet-50 and a modified residual network ResNet-50-fla-drop, to automatically perform eight-class tissue separation in histological CRC images. Experimental results showed that the proposed modified residual network ResNet-50-fla-drop can achieve a classification accuracy of 94.4\% for eight-class CRC tissue separation, and it outperforms other published machine learning methods, including the radial-basis function SVM and VGG-VD-16.",

keywords = "Colorectal cancer (CRC), Deep neural network, Histological image, Residual network",

author = "Lai, \{Ko Hua\} and Chang, \{Meng Chou\}",

note = "Publisher Copyright: {\textcopyright} 2019 IEEE.; 8th IEEE Global Conference on Consumer Electronics, GCCE 2019 ; Conference date: 15-10-2019 Through 18-10-2019",

year = "2019",

month = oct,

doi = "10.1109/GCCE46687.2019.9015250",

language = "英语",

series = "2019 IEEE 8th Global Conference on Consumer Electronics, GCCE 2019",

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

pages = "299--300",

booktitle = "2019 IEEE 8th Global Conference on Consumer Electronics, GCCE 2019",

address = "美国",

}

Lai, KH & Chang, MC 2019, Classification of tissue types in histological colorectal cancer images using residual networks. 於 2019 IEEE 8th Global Conference on Consumer Electronics, GCCE 2019., 9015250, 2019 IEEE 8th Global Conference on Consumer Electronics, GCCE 2019, Institute of Electrical and Electronics Engineers Inc., 頁 299-300, 8th IEEE Global Conference on Consumer Electronics, GCCE 2019, Osaka, 日本, 15/10/19. https://doi.org/10.1109/GCCE46687.2019.9015250

Classification of tissue types in histological colorectal cancer images using residual networks. / Lai, Ko Hua; Chang, Meng Chou.
2019 IEEE 8th Global Conference on Consumer Electronics, GCCE 2019. Institute of Electrical and Electronics Engineers Inc., 2019. p. 299-300 9015250 (2019 IEEE 8th Global Conference on Consumer Electronics, GCCE 2019).

研究成果: 圖書/報告稿件的類型 › 會議稿件 › 同行評審

TY - GEN

T1 - Classification of tissue types in histological colorectal cancer images using residual networks

AU - Lai, Ko Hua

AU - Chang, Meng Chou

PY - 2019/10

Y1 - 2019/10

N2 - Colorectal cancer (CRC) is one of the most prevalent cancer types, but until now only few studies have addressed the problem of automatic recognition of distinct tissue types in histological CRC images. In this paper, we employ two deep convolutional neural networks, the original 50-layer residual network ResNet-50 and a modified residual network ResNet-50-fla-drop, to automatically perform eight-class tissue separation in histological CRC images. Experimental results showed that the proposed modified residual network ResNet-50-fla-drop can achieve a classification accuracy of 94.4% for eight-class CRC tissue separation, and it outperforms other published machine learning methods, including the radial-basis function SVM and VGG-VD-16.

AB - Colorectal cancer (CRC) is one of the most prevalent cancer types, but until now only few studies have addressed the problem of automatic recognition of distinct tissue types in histological CRC images. In this paper, we employ two deep convolutional neural networks, the original 50-layer residual network ResNet-50 and a modified residual network ResNet-50-fla-drop, to automatically perform eight-class tissue separation in histological CRC images. Experimental results showed that the proposed modified residual network ResNet-50-fla-drop can achieve a classification accuracy of 94.4% for eight-class CRC tissue separation, and it outperforms other published machine learning methods, including the radial-basis function SVM and VGG-VD-16.

KW - Colorectal cancer (CRC)

KW - Deep neural network

KW - Histological image

KW - Residual network

UR - https://www.scopus.com/pages/publications/85081947111

U2 - 10.1109/GCCE46687.2019.9015250

DO - 10.1109/GCCE46687.2019.9015250

M3 - 会议稿件

AN - SCOPUS:85081947111

T3 - 2019 IEEE 8th Global Conference on Consumer Electronics, GCCE 2019

SP - 299

EP - 300

BT - 2019 IEEE 8th Global Conference on Consumer Electronics, GCCE 2019

PB - Institute of Electrical and Electronics Engineers Inc.

T2 - 8th IEEE Global Conference on Consumer Electronics, GCCE 2019

Y2 - 15 October 2019 through 18 October 2019

ER -

Lai KH, Chang MC. Classification of tissue types in histological colorectal cancer images using residual networks. 於 2019 IEEE 8th Global Conference on Consumer Electronics, GCCE 2019. Institute of Electrical and Electronics Engineers Inc. 2019. p. 299-300. 9015250. (2019 IEEE 8th Global Conference on Consumer Electronics, GCCE 2019). doi: 10.1109/GCCE46687.2019.9015250

Classification of tissue types in histological colorectal cancer images using residual networks

摘要

出版系列

Conference

文獻附註

UN SDG

存取文件

其它文件與鏈接

指紋

引用此