On deep learning for medical image analysis

Published

Journal Article (Review)

© 2018 American Medical Association. All rights reserved. Neural networks, a subclass of methods in the broader field of machine learning, are highly effective in enabling computer systems to analyze data, facilitating thework of clinicians. Neuralnetworks have beenusedsincethe1980s,withconvolutionalneuralnetworks(CNNs) applied to images beginning in the 1990s.1-3 Examples include identifying natural images of everyday life,4 classifying retinal pathology,5 selectingcellular elements on pathological slides,6 andcorrectly identifyingthe spatial orientation ofchest radiographs.7 Successful neural networks for such tasks are typically composed of multiple analysis layers; the term deep learning is also (synonymously) used to describe this class of neural networks.

Full Text

Duke Authors

Cited Authors

  • Carin, L; Pencina, MJ

Published Date

  • September 18, 2018

Published In

Volume / Issue

  • 320 / 11

Start / End Page

  • 1192 - 1193

Electronic International Standard Serial Number (EISSN)

  • 1538-3598

International Standard Serial Number (ISSN)

  • 0098-7484

Digital Object Identifier (DOI)

  • 10.1001/jama.2018.13316

Citation Source

  • Scopus