Format

Send to

Choose Destination
Proc Natl Acad Sci U S A. 2018 Mar 27;115(13):E2970-E2979. doi: 10.1073/pnas.1717139115. Epub 2018 Mar 12.

Predicting cancer outcomes from histology and genomics using convolutional networks.

Author information

1
Department of Biomedical Informatics, Emory University School of Medicine, Atlanta, GA 30322.
2
Department of Neurology, Emory University School of Medicine, Atlanta, GA 30322.
3
Case Comprehensive Cancer Center, Case Western Reserve University School of Medicine, Cleveland, OH 44106.
4
Department of Pathology and Laboratory Medicine, Emory University School of Medicine, Atlanta, GA 30322.
5
Department of Pathology, Northwestern University Feinberg School of Medicine, Chicago, IL 60611.
6
Department of Biomedical Informatics, Emory University School of Medicine, Atlanta, GA 30322; Lee.Cooper@Emory.edu.
7
Winship Cancer Institute, Emory University, Atlanta, GA 30322.
8
Department of Biomedical Engineering, Emory University and Georgia Institute of Technology, Atlanta, GA 30322.

Abstract

Cancer histology reflects underlying molecular processes and disease progression and contains rich phenotypic information that is predictive of patient outcomes. In this study, we show a computational approach for learning patient outcomes from digital pathology images using deep learning to combine the power of adaptive machine learning algorithms with traditional survival models. We illustrate how these survival convolutional neural networks (SCNNs) can integrate information from both histology images and genomic biomarkers into a single unified framework to predict time-to-event outcomes and show prediction accuracy that surpasses the current clinical paradigm for predicting the overall survival of patients diagnosed with glioma. We use statistical sampling techniques to address challenges in learning survival from histology images, including tumor heterogeneity and the need for large training cohorts. We also provide insights into the prediction mechanisms of SCNNs, using heat map visualization to show that SCNNs recognize important structures, like microvascular proliferation, that are related to prognosis and that are used by pathologists in grading. These results highlight the emerging role of deep learning in precision medicine and suggest an expanding utility for computational analysis of histology in the future practice of pathology.

KEYWORDS:

artificial intelligence; cancer; deep learning; digital pathology; machine learning

Conflict of interest statement

Conflict of interest statement: L.A.D.C. leads a research project that is financially supported by Ventana Medical Systems, Inc. While this project is not directly related to the manuscript, it is in the general area of digital pathology.

Supplemental Content

Full text links

Icon for HighWire Icon for PubMed Central
Loading ...
Support Center