Journal Article
. 2017 Feb;91(6).
doi: 10.1002/cyto.a.23065.

A deep learning based strategy for identifying and associating mitotic activity with gene expression derived risk categories in estrogen receptor positive breast cancers

David Romo-Bucheli 1 Andrew Janowczyk 2 Hannah Gilmore 3 Eduardo Romero 1 Anant Madabhushi 2 
  • PMID: 28192639
  •     17 References
  •     14 citations


The treatment and management of early stage estrogen receptor positive (ER+) breast cancer is hindered by the difficulty in identifying patients who require adjuvant chemotherapy in contrast to those that will respond to hormonal therapy. To distinguish between the more and less aggressive breast tumors, which is a fundamental criterion for the selection of an appropriate treatment plan, Oncotype DX (ODX) and other gene expression tests are typically employed. While informative, these gene expression tests are expensive, tissue destructive, and require specialized facilities. Bloom-Richardson (BR) grade, the common scheme employed in breast cancer grading, has been shown to be correlated with the Oncotype DX risk score. Unfortunately, studies have also shown that the BR grade determined experiences notable inter-observer variability. One of the constituent categories in BR grading is the mitotic index. The goal of this study was to develop a deep learning (DL) classifier to identify mitotic figures from whole slides images of ER+ breast cancer, the hypothesis being that the number of mitoses identified by the DL classifier would correlate with the corresponding Oncotype DX risk categories. The mitosis detector yielded an average F-score of 0.556 in the AMIDA mitosis dataset using a 6-fold validation setup. For a cohort of 174 whole slide images with early stage ER+ breast cancer for which the corresponding Oncotype DX score was available, the distributions of the number of mitoses identified by the DL classifier was found to be significantly different between the high vs low Oncotype DX risk groups (P < 0.01). Comparisons of other risk groups, using both ODX score and histological grade, were also found to present significantly different automated mitoses distributions. Additionally, a support vector machine classifier trained to separate low/high Oncotype DX risk categories using the mitotic count determined by the DL classifier yielded a 83.19% classification accuracy. © 2017 International Society for Advancement of Cytometry.

Keywords: breast cancer risk; digital pathology; mitosis detection; whole slide images.

Assessment of algorithms for mitosis detection in breast cancer histopathology images.
Mitko Veta, Paul J van Diest, +26 authors, Josien P W Pluim.
Med Image Anal, 2014 Dec 31; 20(1). PMID: 25547073
Breast cancer histopathology image analysis: a review.
Mitko Veta, Josien P W Pluim, Paul J van Diest, Max A Viergever.
IEEE Trans Biomed Eng, 2014 Apr 25; 61(5). PMID: 24759275
Breast carcinoma malignancy grading by Bloom-Richardson system vs proliferation index: reproducibility of grade and advantages of proliferation index.
John S Meyer, Consuelo Alvarez, +8 authors, Cooperative Breast Cancer Tissue Resource.
Mod Pathol, 2005 May 28; 18(8). PMID: 15920556
The 21-gene recurrence score complements IBTR! Estimates in early-stage, hormone receptor-positive, HER2-normal, lymph node-negative breast cancer.
Nikhil G Thaker, Karen E Hoffman, +10 authors, Wendy A Woodward.
Springerplus, 2015 Feb 13; 4. PMID: 25674496    Free PMC article.
Co-occurring gland angularity in localized subgraphs: predicting biochemical recurrence in intermediate-risk prostate cancer patients.
George Lee, Rachel Sparks, +6 authors, Anant Madabhushi.
PLoS One, 2014 May 31; 9(5). PMID: 24875018    Free PMC article.
A quantitative histomorphometric classifier (QuHbIC) identifies aggressive versus indolent p16-positive oropharyngeal squamous cell carcinoma.
James S Lewis, Sahirzeeshan Ali, +2 authors, Anant Madabhushi.
Am J Surg Pathol, 2013 Oct 23; 38(1). PMID: 24145650    Free PMC article.
Deep learning for digital pathology image analysis: A comprehensive tutorial with selected use cases.
Andrew Janowczyk, Anant Madabhushi.
J Pathol Inform, 2016 Aug 27; 7. PMID: 27563488    Free PMC article.
Highly Cited.
Cell orientation entropy (COrE): predicting biochemical recurrence from prostate cancer tissue microarrays.
George Lee, Sahirzeeshan Ali, +3 authors, Anant Madabhushi.
Med Image Comput Comput Assist Interv, 2014 Feb 08; 16(Pt 3). PMID: 24505786
Mitosis detection in breast cancer histological images An ICPR 2012 contest.
Ludovic Roux, Daniel Racoceanu, +7 authors, Metin N Gurcan.
J Pathol Inform, 2013 Jul 17; 4. PMID: 23858383    Free PMC article.
Comparison of Oncotype DX and Mammostrat risk estimations and correlations with histologic tumor features in low-grade, estrogen receptor-positive invasive breast carcinomas.
Geza Acs, John Kiluk, Loretta Loftus, Christine Laronga.
Mod Pathol, 2013 Jun 08; 26(11). PMID: 23743933
Histopathologic variables predict Oncotype DX recurrence score.
Melina B Flanagan, David J Dabbs, +2 authors, Rohit Bhargava.
Mod Pathol, 2008 Mar 25; 21(10). PMID: 18360352
Mitosis detection in breast cancer histology images with deep neural networks.
Dan C Cireşan, Alessandro Giusti, Luca M Gambardella, Jürgen Schmidhuber.
Med Image Comput Comput Assist Interv, 2014 Mar 01; 16(Pt 2). PMID: 24579167
Highly Cited.
Histologic grading of breast carcinoma. A reproducibility study.
L W Dalton, D L Page, W D Dupont.
Cancer, 1994 Jun 01; 73(11). PMID: 8194018
Mitosis detection in breast cancer pathology images by combining handcrafted and convolutional neural network features.
Haibo Wang, Angel Cruz-Roa, +6 authors, Anant Madabhushi.
J Med Imaging (Bellingham), 2015 Jul 15; 1(3). PMID: 26158062    Free PMC article.
Morphometic analysis of TCGA glioblastoma multiforme.
Hang Chang, Gerald V Fontenay, +5 authors, Bahram Parvin.
BMC Bioinformatics, 2011 Dec 22; 12. PMID: 22185703    Free PMC article.
HEp-2 cell classification using shape index histograms with donut-shaped spatial pooling.
Anders Boesen Lindbo Larsen, Jacob Schack Vestergaard, Rasmus Larsen.
IEEE Trans Med Imaging, 2014 Apr 25; 33(7). PMID: 24760904
Comprehensive Histologic Scoring to Maximize the Predictability of Pathology-generated Equation of Breast Cancer Oncotype DX Recurrence Score.
Thaer Khoury, Xiao Huang, +3 authors, Mateusz Opyrchal.
Appl Immunohistochem Mol Morphol, 2016 Jan 26; 24(10). PMID: 26808126    Free PMC article.
Automatic cellularity assessment from post-treated breast surgical specimens.
Mohammad Peikari, Sherine Salama, Sharon Nofech-Mozes, Anne L Martel.
Cytometry A, 2017 Oct 05; 91(11). PMID: 28976721    Free PMC article.
Particle swarm optimization-based automatic parameter selection for deep neural networks and its applications in large-scale and high-dimensional data.
Fei Ye.
PLoS One, 2017 Dec 14; 12(12). PMID: 29236718    Free PMC article.
Association of Pathological Fibrosis With Renal Survival Using Deep Neural Networks.
Vijaya B Kolachalama, Priyamvada Singh, +6 authors, Vipul C Chitalia.
Kidney Int Rep, 2018 May 05; 3(2). PMID: 29725651    Free PMC article.
High-throughput adaptive sampling for whole-slide histopathology image analysis (HASHI) via convolutional neural networks: Application to invasive breast cancer detection.
Angel Cruz-Roa, Hannah Gilmore, +6 authors, Fabio González.
PLoS One, 2018 May 26; 13(5). PMID: 29795581    Free PMC article.
Quantitative nuclear histomorphometry predicts oncotype DX risk categories for early stage ER+ breast cancer.
Jon Whitney, German Corredor, +6 authors, Anant Madabhushi.
BMC Cancer, 2018 Jun 01; 18(1). PMID: 29848291    Free PMC article.
Nuclear shape and orientation features from H&E images predict survival in early-stage estrogen receptor-positive breast cancers.
Cheng Lu, David Romo-Bucheli, +5 authors, Anant Madabhushi.
Lab Invest, 2018 Jul 01; 98(11). PMID: 29959421    Free PMC article.
Novel Quantitative Imaging for Predicting Response to Therapy: Techniques and Clinical Applications.
Kaustav Bera, Vamsidhar Velcheti, Anant Madabhushi.
Am Soc Clin Oncol Educ Book, 2018 Sep 21; 38. PMID: 30231314    Free PMC article.
Artificial intelligence in digital pathology - new tools for diagnosis and precision oncology.
Kaustav Bera, Kurt A Schalper, +2 authors, Anant Madabhushi.
Nat Rev Clin Oncol, 2019 Aug 11; 16(11). PMID: 31399699    Free PMC article.
Highly Cited. Review.
Quantitative Histopathology of Stained Tissues using Color Spatial Light Interference Microscopy (cSLIM).
Hassaan Majeed, Adib Keikhosravi, +6 authors, Gabriel Popescu.
Sci Rep, 2019 Oct 13; 9(1). PMID: 31604963    Free PMC article.
Clinical implications of intratumor heterogeneity: challenges and opportunities.
Santiago Ramón Y Cajal, Marta Sesé, +5 authors, Josep Castellví.
J Mol Med (Berl), 2020 Jan 24; 98(2). PMID: 31970428    Free PMC article.
Applications of machine learning in drug discovery and development.
Jessica Vamathevan, Dominic Clark, +8 authors, Shanrong Zhao.
Nat Rev Drug Discov, 2019 Apr 13; 18(6). PMID: 30976107    Free PMC article.
Highly Cited. Review.
Artificial Intelligence Algorithms to Assess Hormonal Status From Tissue Microarrays in Patients With Breast Cancer.
Gil Shamai, Yoav Binenbaum, +3 authors, Ron Kimmel.
JAMA Netw Open, 2019 Jul 28; 2(7). PMID: 31348505    Free PMC article.
Artificial Intelligence to Decode Cancer Mechanism: Beyond Patient Stratification for Precision Oncology.
Sandip Kumar Patel, Bhawana George, Vineeta Rai.
Front Pharmacol, 2020 Sep 10; 11. PMID: 32903628    Free PMC article.
Artificial intelligence in automatic classification of invasive ductal carcinoma breast cancer in digital pathology images.
Mohammad Abdolahi, Mohammad Salehi, Iman Shokatian, Reza Reiazi.
Med J Islam Repub Iran, 2021 Jan 14; 34. PMID: 33437736    Free PMC article.