Deep learning-based assessment of tumor-associated stroma for diagnosing breast cancer in histopathology images

Babak Ehteshami Bejnordi, Jimmy Lin, Ben Glass, Maeve Mullooly, Gretchen L. Gierach, Mark E. Sherman, Nico Karssemeijer, Jeroen Van Der Laak, Andrew H. Beck

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

11 Citations (Scopus)

Abstract

Diagnosis of breast carcinomas has so far been limited to the morphological interpretation of epithelial cells and the assessment of epithelial tissue architecture. Consequently, most of the automated systems have focused on characterizing the epithelial regions of the breast to detect cancer. In this paper, we propose a system for classification of hematoxylin and eosin (H&E) stained breast specimens based on convolutional neural networks that primarily targets the assessment of tumor-associated stroma to diagnose breast cancer patients. We evaluate the performance of our proposed system using a large cohort containing 646 breast tissue biopsies. Our evaluations show that the proposed system achieves an area under ROC of 0.92, demonstrating the discriminative power of previously neglected tumor associated stroma as a diagnostic biomarker.

Original languageEnglish (US)
Title of host publication2017 IEEE 14th International Symposium on Biomedical Imaging, ISBI 2017
PublisherIEEE Computer Society
Pages929-932
Number of pages4
ISBN (Electronic)9781509011711
DOIs
StatePublished - Jun 15 2017
Event14th IEEE International Symposium on Biomedical Imaging, ISBI 2017 - Melbourne, Australia
Duration: Apr 18 2017Apr 21 2017

Other

Other14th IEEE International Symposium on Biomedical Imaging, ISBI 2017
CountryAustralia
CityMelbourne
Period4/18/174/21/17

Fingerprint

Tumors
Breast
Learning
Tissue
Breast Neoplasms
Biopsy
Biomarkers
Neoplasms
Hematoxylin
Eosine Yellowish-(YS)
Neural networks
Epithelium
Epithelial Cells
Deep learning
Power (Psychology)

Keywords

  • Breast Cancer
  • Convolutional Neural Networks
  • Digital pathology
  • Tumor Associated Stroma

ASJC Scopus subject areas

  • Biomedical Engineering
  • Radiology Nuclear Medicine and imaging

Cite this

Ehteshami Bejnordi, B., Lin, J., Glass, B., Mullooly, M., Gierach, G. L., Sherman, M. E., ... Beck, A. H. (2017). Deep learning-based assessment of tumor-associated stroma for diagnosing breast cancer in histopathology images. In 2017 IEEE 14th International Symposium on Biomedical Imaging, ISBI 2017 (pp. 929-932). [7950668] IEEE Computer Society. https://doi.org/10.1109/ISBI.2017.7950668

Deep learning-based assessment of tumor-associated stroma for diagnosing breast cancer in histopathology images. / Ehteshami Bejnordi, Babak; Lin, Jimmy; Glass, Ben; Mullooly, Maeve; Gierach, Gretchen L.; Sherman, Mark E.; Karssemeijer, Nico; Van Der Laak, Jeroen; Beck, Andrew H.

2017 IEEE 14th International Symposium on Biomedical Imaging, ISBI 2017. IEEE Computer Society, 2017. p. 929-932 7950668.

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

Ehteshami Bejnordi, B, Lin, J, Glass, B, Mullooly, M, Gierach, GL, Sherman, ME, Karssemeijer, N, Van Der Laak, J & Beck, AH 2017, Deep learning-based assessment of tumor-associated stroma for diagnosing breast cancer in histopathology images. in 2017 IEEE 14th International Symposium on Biomedical Imaging, ISBI 2017., 7950668, IEEE Computer Society, pp. 929-932, 14th IEEE International Symposium on Biomedical Imaging, ISBI 2017, Melbourne, Australia, 4/18/17. https://doi.org/10.1109/ISBI.2017.7950668
Ehteshami Bejnordi B, Lin J, Glass B, Mullooly M, Gierach GL, Sherman ME et al. Deep learning-based assessment of tumor-associated stroma for diagnosing breast cancer in histopathology images. In 2017 IEEE 14th International Symposium on Biomedical Imaging, ISBI 2017. IEEE Computer Society. 2017. p. 929-932. 7950668 https://doi.org/10.1109/ISBI.2017.7950668
Ehteshami Bejnordi, Babak ; Lin, Jimmy ; Glass, Ben ; Mullooly, Maeve ; Gierach, Gretchen L. ; Sherman, Mark E. ; Karssemeijer, Nico ; Van Der Laak, Jeroen ; Beck, Andrew H. / Deep learning-based assessment of tumor-associated stroma for diagnosing breast cancer in histopathology images. 2017 IEEE 14th International Symposium on Biomedical Imaging, ISBI 2017. IEEE Computer Society, 2017. pp. 929-932
@inproceedings{ec106df5e97447ae966d1214b1092886,
title = "Deep learning-based assessment of tumor-associated stroma for diagnosing breast cancer in histopathology images",
abstract = "Diagnosis of breast carcinomas has so far been limited to the morphological interpretation of epithelial cells and the assessment of epithelial tissue architecture. Consequently, most of the automated systems have focused on characterizing the epithelial regions of the breast to detect cancer. In this paper, we propose a system for classification of hematoxylin and eosin (H&E) stained breast specimens based on convolutional neural networks that primarily targets the assessment of tumor-associated stroma to diagnose breast cancer patients. We evaluate the performance of our proposed system using a large cohort containing 646 breast tissue biopsies. Our evaluations show that the proposed system achieves an area under ROC of 0.92, demonstrating the discriminative power of previously neglected tumor associated stroma as a diagnostic biomarker.",
keywords = "Breast Cancer, Convolutional Neural Networks, Digital pathology, Tumor Associated Stroma",
author = "{Ehteshami Bejnordi}, Babak and Jimmy Lin and Ben Glass and Maeve Mullooly and Gierach, {Gretchen L.} and Sherman, {Mark E.} and Nico Karssemeijer and {Van Der Laak}, Jeroen and Beck, {Andrew H.}",
year = "2017",
month = "6",
day = "15",
doi = "10.1109/ISBI.2017.7950668",
language = "English (US)",
pages = "929--932",
booktitle = "2017 IEEE 14th International Symposium on Biomedical Imaging, ISBI 2017",
publisher = "IEEE Computer Society",

}

TY - GEN

T1 - Deep learning-based assessment of tumor-associated stroma for diagnosing breast cancer in histopathology images

AU - Ehteshami Bejnordi, Babak

AU - Lin, Jimmy

AU - Glass, Ben

AU - Mullooly, Maeve

AU - Gierach, Gretchen L.

AU - Sherman, Mark E.

AU - Karssemeijer, Nico

AU - Van Der Laak, Jeroen

AU - Beck, Andrew H.

PY - 2017/6/15

Y1 - 2017/6/15

N2 - Diagnosis of breast carcinomas has so far been limited to the morphological interpretation of epithelial cells and the assessment of epithelial tissue architecture. Consequently, most of the automated systems have focused on characterizing the epithelial regions of the breast to detect cancer. In this paper, we propose a system for classification of hematoxylin and eosin (H&E) stained breast specimens based on convolutional neural networks that primarily targets the assessment of tumor-associated stroma to diagnose breast cancer patients. We evaluate the performance of our proposed system using a large cohort containing 646 breast tissue biopsies. Our evaluations show that the proposed system achieves an area under ROC of 0.92, demonstrating the discriminative power of previously neglected tumor associated stroma as a diagnostic biomarker.

AB - Diagnosis of breast carcinomas has so far been limited to the morphological interpretation of epithelial cells and the assessment of epithelial tissue architecture. Consequently, most of the automated systems have focused on characterizing the epithelial regions of the breast to detect cancer. In this paper, we propose a system for classification of hematoxylin and eosin (H&E) stained breast specimens based on convolutional neural networks that primarily targets the assessment of tumor-associated stroma to diagnose breast cancer patients. We evaluate the performance of our proposed system using a large cohort containing 646 breast tissue biopsies. Our evaluations show that the proposed system achieves an area under ROC of 0.92, demonstrating the discriminative power of previously neglected tumor associated stroma as a diagnostic biomarker.

KW - Breast Cancer

KW - Convolutional Neural Networks

KW - Digital pathology

KW - Tumor Associated Stroma

UR - http://www.scopus.com/inward/record.url?scp=85023173631&partnerID=8YFLogxK

UR - http://www.scopus.com/inward/citedby.url?scp=85023173631&partnerID=8YFLogxK

U2 - 10.1109/ISBI.2017.7950668

DO - 10.1109/ISBI.2017.7950668

M3 - Conference contribution

AN - SCOPUS:85023173631

SP - 929

EP - 932

BT - 2017 IEEE 14th International Symposium on Biomedical Imaging, ISBI 2017

PB - IEEE Computer Society

ER -