Deep learning based Nucleus Classification in pancreas histological images

Young Hwan Chang, Guillaume Thibault, Owen Madin, Vahid Azimi, Cole Meyers, Brett Johnson, Jason Link, Adam Margolin, Joe Gray

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

6 Citations (Scopus)

Abstract

Tumor specimens contain a variety of healthy cells as well as cancerous cells, and this heterogeneity underlies resistance to various cancer therapies. But this problem has not been thoroughly investigated until recently. Meanwhile, technological breakthroughs in imaging have led to an explosion of molecular and cellular profiling data from large numbers of samples, and modern machine learning approaches including deep learning have been shown to produce encouraging results by finding hidden structures and make accurate predictions. In this paper, we propose a Deep learning based Nucleus Classification (DeepNC) approach using paired histopathology and immunofluorescence images (for label), and demonstrate its classification prediction power. This method can solve current issue on discrepancy between genomic- or transcriptomic-based and pathology-based tumor purity estimates by improving histological evaluation. We also explain challenges in training a deep learning model for huge dataset.

Original languageEnglish (US)
Title of host publication2017 39th Annual International Conference of the IEEE Engineering in Medicine and Biology Society
Subtitle of host publicationSmarter Technology for a Healthier World, EMBC 2017 - Proceedings
PublisherInstitute of Electrical and Electronics Engineers Inc.
Pages672-675
Number of pages4
ISBN (Electronic)9781509028092
DOIs
StatePublished - Sep 13 2017
Event39th Annual International Conference of the IEEE Engineering in Medicine and Biology Society, EMBC 2017 - Jeju Island, Korea, Republic of
Duration: Jul 11 2017Jul 15 2017

Other

Other39th Annual International Conference of the IEEE Engineering in Medicine and Biology Society, EMBC 2017
CountryKorea, Republic of
CityJeju Island
Period7/11/177/15/17

Fingerprint

Pancreas
Learning
Tumors
Neoplasms
Explosions
Pathology
Fluorescent Antibody Technique
Learning systems
Labels
Cells
Imaging techniques
Deep learning
Therapeutics
Power (Psychology)
Datasets
Machine Learning

Keywords

  • Deep Learning
  • Histopathology
  • Immunofluorescence
  • Segmentation

ASJC Scopus subject areas

  • Signal Processing
  • Biomedical Engineering
  • Computer Vision and Pattern Recognition
  • Health Informatics

Cite this

Chang, Y. H., Thibault, G., Madin, O., Azimi, V., Meyers, C., Johnson, B., ... Gray, J. (2017). Deep learning based Nucleus Classification in pancreas histological images. In 2017 39th Annual International Conference of the IEEE Engineering in Medicine and Biology Society: Smarter Technology for a Healthier World, EMBC 2017 - Proceedings (pp. 672-675). [8036914] Institute of Electrical and Electronics Engineers Inc.. https://doi.org/10.1109/EMBC.2017.8036914

Deep learning based Nucleus Classification in pancreas histological images. / Chang, Young Hwan; Thibault, Guillaume; Madin, Owen; Azimi, Vahid; Meyers, Cole; Johnson, Brett; Link, Jason; Margolin, Adam; Gray, Joe.

2017 39th Annual International Conference of the IEEE Engineering in Medicine and Biology Society: Smarter Technology for a Healthier World, EMBC 2017 - Proceedings. Institute of Electrical and Electronics Engineers Inc., 2017. p. 672-675 8036914.

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

Chang, YH, Thibault, G, Madin, O, Azimi, V, Meyers, C, Johnson, B, Link, J, Margolin, A & Gray, J 2017, Deep learning based Nucleus Classification in pancreas histological images. in 2017 39th Annual International Conference of the IEEE Engineering in Medicine and Biology Society: Smarter Technology for a Healthier World, EMBC 2017 - Proceedings., 8036914, Institute of Electrical and Electronics Engineers Inc., pp. 672-675, 39th Annual International Conference of the IEEE Engineering in Medicine and Biology Society, EMBC 2017, Jeju Island, Korea, Republic of, 7/11/17. https://doi.org/10.1109/EMBC.2017.8036914
Chang YH, Thibault G, Madin O, Azimi V, Meyers C, Johnson B et al. Deep learning based Nucleus Classification in pancreas histological images. In 2017 39th Annual International Conference of the IEEE Engineering in Medicine and Biology Society: Smarter Technology for a Healthier World, EMBC 2017 - Proceedings. Institute of Electrical and Electronics Engineers Inc. 2017. p. 672-675. 8036914 https://doi.org/10.1109/EMBC.2017.8036914
Chang, Young Hwan ; Thibault, Guillaume ; Madin, Owen ; Azimi, Vahid ; Meyers, Cole ; Johnson, Brett ; Link, Jason ; Margolin, Adam ; Gray, Joe. / Deep learning based Nucleus Classification in pancreas histological images. 2017 39th Annual International Conference of the IEEE Engineering in Medicine and Biology Society: Smarter Technology for a Healthier World, EMBC 2017 - Proceedings. Institute of Electrical and Electronics Engineers Inc., 2017. pp. 672-675
@inproceedings{18f02a16a77045e99fd415073e0c2784,
title = "Deep learning based Nucleus Classification in pancreas histological images",
abstract = "Tumor specimens contain a variety of healthy cells as well as cancerous cells, and this heterogeneity underlies resistance to various cancer therapies. But this problem has not been thoroughly investigated until recently. Meanwhile, technological breakthroughs in imaging have led to an explosion of molecular and cellular profiling data from large numbers of samples, and modern machine learning approaches including deep learning have been shown to produce encouraging results by finding hidden structures and make accurate predictions. In this paper, we propose a Deep learning based Nucleus Classification (DeepNC) approach using paired histopathology and immunofluorescence images (for label), and demonstrate its classification prediction power. This method can solve current issue on discrepancy between genomic- or transcriptomic-based and pathology-based tumor purity estimates by improving histological evaluation. We also explain challenges in training a deep learning model for huge dataset.",
keywords = "Deep Learning, Histopathology, Immunofluorescence, Segmentation",
author = "Chang, {Young Hwan} and Guillaume Thibault and Owen Madin and Vahid Azimi and Cole Meyers and Brett Johnson and Jason Link and Adam Margolin and Joe Gray",
year = "2017",
month = "9",
day = "13",
doi = "10.1109/EMBC.2017.8036914",
language = "English (US)",
pages = "672--675",
booktitle = "2017 39th Annual International Conference of the IEEE Engineering in Medicine and Biology Society",
publisher = "Institute of Electrical and Electronics Engineers Inc.",

}

TY - GEN

T1 - Deep learning based Nucleus Classification in pancreas histological images

AU - Chang, Young Hwan

AU - Thibault, Guillaume

AU - Madin, Owen

AU - Azimi, Vahid

AU - Meyers, Cole

AU - Johnson, Brett

AU - Link, Jason

AU - Margolin, Adam

AU - Gray, Joe

PY - 2017/9/13

Y1 - 2017/9/13

N2 - Tumor specimens contain a variety of healthy cells as well as cancerous cells, and this heterogeneity underlies resistance to various cancer therapies. But this problem has not been thoroughly investigated until recently. Meanwhile, technological breakthroughs in imaging have led to an explosion of molecular and cellular profiling data from large numbers of samples, and modern machine learning approaches including deep learning have been shown to produce encouraging results by finding hidden structures and make accurate predictions. In this paper, we propose a Deep learning based Nucleus Classification (DeepNC) approach using paired histopathology and immunofluorescence images (for label), and demonstrate its classification prediction power. This method can solve current issue on discrepancy between genomic- or transcriptomic-based and pathology-based tumor purity estimates by improving histological evaluation. We also explain challenges in training a deep learning model for huge dataset.

AB - Tumor specimens contain a variety of healthy cells as well as cancerous cells, and this heterogeneity underlies resistance to various cancer therapies. But this problem has not been thoroughly investigated until recently. Meanwhile, technological breakthroughs in imaging have led to an explosion of molecular and cellular profiling data from large numbers of samples, and modern machine learning approaches including deep learning have been shown to produce encouraging results by finding hidden structures and make accurate predictions. In this paper, we propose a Deep learning based Nucleus Classification (DeepNC) approach using paired histopathology and immunofluorescence images (for label), and demonstrate its classification prediction power. This method can solve current issue on discrepancy between genomic- or transcriptomic-based and pathology-based tumor purity estimates by improving histological evaluation. We also explain challenges in training a deep learning model for huge dataset.

KW - Deep Learning

KW - Histopathology

KW - Immunofluorescence

KW - Segmentation

UR - http://www.scopus.com/inward/record.url?scp=85032208905&partnerID=8YFLogxK

UR - http://www.scopus.com/inward/citedby.url?scp=85032208905&partnerID=8YFLogxK

U2 - 10.1109/EMBC.2017.8036914

DO - 10.1109/EMBC.2017.8036914

M3 - Conference contribution

C2 - 29059962

AN - SCOPUS:85032208905

SP - 672

EP - 675

BT - 2017 39th Annual International Conference of the IEEE Engineering in Medicine and Biology Society

PB - Institute of Electrical and Electronics Engineers Inc.

ER -