PMID- 29531073
OWN - NLM
STAT- MEDLINE
DCOM- 20180810
LR  - 20181114
IS  - 1091-6490 (Electronic)
IS  - 0027-8424 (Linking)
VI  - 115
IP  - 13
DP  - 2018 Mar 27
TI  - Predicting cancer outcomes from histology and genomics using convolutional
      networks.
PG  - E2970-E2979
LID - 10.1073/pnas.1717139115 [doi]
AB  - 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.
CI  - Copyright (c) 2018 the Author(s). Published by PNAS.
FAU - Mobadersany, Pooya
AU  - Mobadersany P
AD  - Department of Biomedical Informatics, Emory University School of Medicine,
      Atlanta, GA 30322.
FAU - Yousefi, Safoora
AU  - Yousefi S
AD  - Department of Biomedical Informatics, Emory University School of Medicine,
      Atlanta, GA 30322.
FAU - Amgad, Mohamed
AU  - Amgad M
AD  - Department of Biomedical Informatics, Emory University School of Medicine,
      Atlanta, GA 30322.
FAU - Gutman, David A
AU  - Gutman DA
AD  - Department of Neurology, Emory University School of Medicine, Atlanta, GA 30322.
FAU - Barnholtz-Sloan, Jill S
AU  - Barnholtz-Sloan JS
AD  - Case Comprehensive Cancer Center, Case Western Reserve University School of
      Medicine, Cleveland, OH 44106.
FAU - Velazquez Vega, Jose E
AU  - Velazquez Vega JE
AD  - Department of Pathology and Laboratory Medicine, Emory University School of
      Medicine, Atlanta, GA 30322.
FAU - Brat, Daniel J
AU  - Brat DJ
AD  - Department of Pathology, Northwestern University Feinberg School of Medicine,
      Chicago, IL 60611.
FAU - Cooper, Lee A D
AU  - Cooper LAD
AUID- ORCID: 0000-0002-3504-4965
AD  - Department of Biomedical Informatics, Emory University School of Medicine,
      Atlanta, GA 30322; Lee.Cooper@Emory.edu.
AD  - Winship Cancer Institute, Emory University, Atlanta, GA 30322.
AD  - Department of Biomedical Engineering, Emory University and Georgia Institute of
      Technology, Atlanta, GA 30322.
LA  - eng
GR  - K22 LM011576/LM/NLM NIH HHS/United States
GR  - U24 CA194362/CA/NCI NIH HHS/United States
PT  - Journal Article
PT  - Research Support, N.I.H., Extramural
PT  - Research Support, Non-U.S. Gov't
DEP - 20180312
PL  - United States
TA  - Proc Natl Acad Sci U S A
JT  - Proceedings of the National Academy of Sciences of the United States of America
JID - 7505876
SB  - IM
MH  - Algorithms
MH  - Brain Neoplasms/*genetics/*pathology/therapy
MH  - Genomics/*methods
MH  - Glioma/*genetics/*pathology/therapy
MH  - Histological Techniques/*methods
MH  - Humans
MH  - Image Processing, Computer-Assisted
MH  - *Neural Networks (Computer)
MH  - Precision Medicine
MH  - Prognosis
PMC - PMC5879673
OTO - NOTNLM
OT  - *artificial intelligence
OT  - *cancer
OT  - *deep learning
OT  - *digital pathology
OT  - *machine learning
COIS- 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.
EDAT- 2018/03/14 06:00
MHDA- 2018/08/11 06:00
CRDT- 2018/03/14 06:00
PHST- 2018/03/14 06:00 [pubmed]
PHST- 2018/08/11 06:00 [medline]
PHST- 2018/03/14 06:00 [entrez]
AID - 1717139115 [pii]
AID - 10.1073/pnas.1717139115 [doi]
PST - ppublish
SO  - Proc Natl Acad Sci U S A. 2018 Mar 27;115(13):E2970-E2979. doi:
      10.1073/pnas.1717139115. Epub 2018 Mar 12.