Colorectal cancer outcome prediction from H&E whole slide images using machine learning and automatically inferred phenotype profiles

Xingzhi Yue; Neofytos Dimitriou; Peter Caie; David Harrison; Ognjen Arandjelovic

doi:10.29007/n912

Colorectal cancer outcome prediction from H&E whole slide images using machine learning and automatically inferred phenotype profiles

Xingzhi Yue, Neofytos Dimitriou, Peter Caie, David Harrison, Ognjen Arandjelovic

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

Abstract

Digital pathology (DP) is a new research area which falls under the broad umbrella of health informatics. Owing to its potential for major public health impact, in recent years DP has been attracting much research attention. Nevertheless, a wide breadth of significant conceptual and technical challenges remain, few of them greater than those encountered in digital oncology. The automatic analysis of digital pathology slides of cancerous tissues is particularly problematic due to the inherent heterogeneity of the disease, extremely large images, and numerous others. In this paper we introduce a novel machine learning based framework for the prediction of colorectal cancer outcome from whole haematoxylin & eosin (H&E) stained histopathology slides. Using a real-world data set we demonstrate the effectiveness of the method and present a detailed analysis of its different elements which corroborate its ability to extract and learn salient, discriminative, and clinically meaningful content.

Original language	English
Title of host publication	Proceedings of 11th International Conference on Bioinformatics and Computational Biology, BICOB 2019
Subtitle of host publication	Honolulu; United States; 18 March 2019 through 20 March 2019
Editors	Oliver Eulenstein, Hisham Al-Mubaid, Qin Ding
Publisher	EasyChair
Pages	139-127
Number of pages	11
DOIs	https://doi.org/10.29007/n912
Publication status	Published - 18 Mar 2019
Event	11th International Conference on Bioinformatics and Computational Biology (BICOB) - Waikiki Beach Marriott Resort, Honolulu, United States Duration: 18 Mar 2019 → 20 Mar 2019 Conference number: 11 https://sceweb.uhcl.edu/bicob19/

Publication series

Name	EPiC Series in Computing
Publisher	EasyChair
Volume	60
ISSN (Electronic)	2398-7340

Conference

Conference	11th International Conference on Bioinformatics and Computational Biology (BICOB)
Abbreviated title	BICOB
Country/Territory	United States
City	Honolulu
Period	18/03/19 → 20/03/19
Internet address	https://sceweb.uhcl.edu/bicob19/

UN SDGs

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

SDG 3 Good Health and Well-being

Keywords

CNN
Convolution
Health
Neural network
Pathology
Public
Tumour

Access to Document

10.29007/n912

https://arxiv.org/abs/1902.03582

Cite this

Yue, X., Dimitriou, N., Caie, P., Harrison, D., & Arandjelovic, O. (2019). Colorectal cancer outcome prediction from H&E whole slide images using machine learning and automatically inferred phenotype profiles. In O. Eulenstein, H. Al-Mubaid, & Q. Ding (Eds.), Proceedings of 11th International Conference on Bioinformatics and Computational Biology, BICOB 2019: Honolulu; United States; 18 March 2019 through 20 March 2019 (pp. 139-127). (EPiC Series in Computing; Vol. 60). EasyChair. https://doi.org/10.29007/n912

Yue, Xingzhi ; Dimitriou, Neofytos ; Caie, Peter et al. / Colorectal cancer outcome prediction from H&E whole slide images using machine learning and automatically inferred phenotype profiles. Proceedings of 11th International Conference on Bioinformatics and Computational Biology, BICOB 2019: Honolulu; United States; 18 March 2019 through 20 March 2019. editor / Oliver Eulenstein ; Hisham Al-Mubaid ; Qin Ding. EasyChair, 2019. pp. 139-127 (EPiC Series in Computing).

@inproceedings{345e220c1b844fde854b9bd4540995f5,

title = "Colorectal cancer outcome prediction from H\&E whole slide images using machine learning and automatically inferred phenotype profiles",

abstract = "Digital pathology (DP) is a new research area which falls under the broad umbrella of health informatics. Owing to its potential for major public health impact, in recent years DP has been attracting much research attention. Nevertheless, a wide breadth of significant conceptual and technical challenges remain, few of them greater than those encountered in digital oncology. The automatic analysis of digital pathology slides of cancerous tissues is particularly problematic due to the inherent heterogeneity of the disease, extremely large images, and numerous others. In this paper we introduce a novel machine learning based framework for the prediction of colorectal cancer outcome from whole haematoxylin \& eosin (H\&E) stained histopathology slides. Using a real-world data set we demonstrate the effectiveness of the method and present a detailed analysis of its different elements which corroborate its ability to extract and learn salient, discriminative, and clinically meaningful content.",

keywords = "CNN, Convolution, Health, Neural network, Pathology, Public, Tumour",

author = "Xingzhi Yue and Neofytos Dimitriou and Peter Caie and David Harrison and Ognjen Arandjelovic",

year = "2019",

month = mar,

day = "18",

doi = "10.29007/n912",

language = "English",

series = "EPiC Series in Computing",

publisher = "EasyChair",

pages = "139--127",

editor = "Oliver Eulenstein and Hisham Al-Mubaid and Qin Ding",

booktitle = "Proceedings of 11th International Conference on Bioinformatics and Computational Biology, BICOB 2019",

note = "11th International Conference on Bioinformatics and Computational Biology (BICOB), BICOB ; Conference date: 18-03-2019 Through 20-03-2019",

url = "https://sceweb.uhcl.edu/bicob19/",

}

Yue, X, Dimitriou, N, Caie, P, Harrison, D & Arandjelovic, O 2019, Colorectal cancer outcome prediction from H&E whole slide images using machine learning and automatically inferred phenotype profiles. in O Eulenstein, H Al-Mubaid & Q Ding (eds), Proceedings of 11th International Conference on Bioinformatics and Computational Biology, BICOB 2019: Honolulu; United States; 18 March 2019 through 20 March 2019. EPiC Series in Computing, vol. 60, EasyChair, pp. 139-127, 11th International Conference on Bioinformatics and Computational Biology (BICOB), Honolulu, Hawaii, United States, 18/03/19. https://doi.org/10.29007/n912

Colorectal cancer outcome prediction from H&E whole slide images using machine learning and automatically inferred phenotype profiles. / Yue, Xingzhi; Dimitriou, Neofytos; Caie, Peter et al.
Proceedings of 11th International Conference on Bioinformatics and Computational Biology, BICOB 2019: Honolulu; United States; 18 March 2019 through 20 March 2019. ed. / Oliver Eulenstein; Hisham Al-Mubaid; Qin Ding. EasyChair, 2019. p. 139-127 (EPiC Series in Computing; Vol. 60).

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

TY - GEN

T1 - Colorectal cancer outcome prediction from H&E whole slide images using machine learning and automatically inferred phenotype profiles

AU - Yue, Xingzhi

AU - Dimitriou, Neofytos

AU - Caie, Peter

AU - Harrison, David

AU - Arandjelovic, Ognjen

N1 - Conference code: 11

PY - 2019/3/18

Y1 - 2019/3/18

N2 - Digital pathology (DP) is a new research area which falls under the broad umbrella of health informatics. Owing to its potential for major public health impact, in recent years DP has been attracting much research attention. Nevertheless, a wide breadth of significant conceptual and technical challenges remain, few of them greater than those encountered in digital oncology. The automatic analysis of digital pathology slides of cancerous tissues is particularly problematic due to the inherent heterogeneity of the disease, extremely large images, and numerous others. In this paper we introduce a novel machine learning based framework for the prediction of colorectal cancer outcome from whole haematoxylin & eosin (H&E) stained histopathology slides. Using a real-world data set we demonstrate the effectiveness of the method and present a detailed analysis of its different elements which corroborate its ability to extract and learn salient, discriminative, and clinically meaningful content.

AB - Digital pathology (DP) is a new research area which falls under the broad umbrella of health informatics. Owing to its potential for major public health impact, in recent years DP has been attracting much research attention. Nevertheless, a wide breadth of significant conceptual and technical challenges remain, few of them greater than those encountered in digital oncology. The automatic analysis of digital pathology slides of cancerous tissues is particularly problematic due to the inherent heterogeneity of the disease, extremely large images, and numerous others. In this paper we introduce a novel machine learning based framework for the prediction of colorectal cancer outcome from whole haematoxylin & eosin (H&E) stained histopathology slides. Using a real-world data set we demonstrate the effectiveness of the method and present a detailed analysis of its different elements which corroborate its ability to extract and learn salient, discriminative, and clinically meaningful content.

KW - CNN

KW - Convolution

KW - Health

KW - Neural network

KW - Pathology

KW - Public

KW - Tumour

U2 - 10.29007/n912

DO - 10.29007/n912

M3 - Conference contribution

T3 - EPiC Series in Computing

SP - 139

EP - 127

BT - Proceedings of 11th International Conference on Bioinformatics and Computational Biology, BICOB 2019

A2 - Eulenstein, Oliver

A2 - Al-Mubaid, Hisham

A2 - Ding, Qin

PB - EasyChair

T2 - 11th International Conference on Bioinformatics and Computational Biology (BICOB)

Y2 - 18 March 2019 through 20 March 2019

ER -

Yue X, Dimitriou N, Caie P, Harrison D , Arandjelovic O. Colorectal cancer outcome prediction from H&E whole slide images using machine learning and automatically inferred phenotype profiles. In Eulenstein O, Al-Mubaid H, Ding Q, editors, Proceedings of 11th International Conference on Bioinformatics and Computational Biology, BICOB 2019: Honolulu; United States; 18 March 2019 through 20 March 2019. EasyChair. 2019. p. 139-127. (EPiC Series in Computing). doi: 10.29007/n912

Colorectal cancer outcome prediction from H&E whole slide images using machine learning and automatically inferred phenotype profiles

Abstract

Publication series

Conference

UN SDGs

Keywords

Access to Document

Fingerprint

Cite this