Deep Learning in Medical Image Analysis

Research output: Contribution to journalArticle

499 Citations (Scopus)

Abstract

This review covers computer-assisted analysis of images in the field of medical imaging. Recent advances in machine learning, especially with regard to deep learning, are helping to identify, classify, and quantify patterns in medical images. At the core of these advances is the ability to exploit hierarchical feature representations learned solely from data, instead of features designed by hand according to domain-specific knowledge. Deep learning is rapidly becoming the state of the art, leading to enhanced performance in various medical applications. We introduce the fundamentals of deep learning methods and review their successes in image registration, detection of anatomical and cellular structures, tissue segmentation, computer-aided disease diagnosis and prognosis, and so on. We conclude by discussing research issues and suggesting future directions for further improvement.

Original languageEnglish
Pages (from-to)221-248
Number of pages28
JournalAnnual Review of Biomedical Engineering
Volume19
DOIs
Publication statusPublished - 2017 Jun 21

Fingerprint

Image analysis
Learning
Aptitude
Computer-Assisted Image Processing
Image registration
Medical imaging
Medical applications
Diagnostic Imaging
Cellular Structures
Learning systems
Hand
Tissue
Research
Deep learning
Direction compound
Machine Learning

Keywords

  • Deep learning
  • Medical image analysis
  • Unsupervised feature learning

ASJC Scopus subject areas

  • Medicine (miscellaneous)
  • Biomedical Engineering

Cite this

Deep Learning in Medical Image Analysis. / Shen, Dinggang; Wu, Guorong; Suk, Heung-Il.

In: Annual Review of Biomedical Engineering, Vol. 19, 21.06.2017, p. 221-248.

Research output: Contribution to journalArticle

@article{935881118bfa4851a53fc18196e311b4,
title = "Deep Learning in Medical Image Analysis",
abstract = "This review covers computer-assisted analysis of images in the field of medical imaging. Recent advances in machine learning, especially with regard to deep learning, are helping to identify, classify, and quantify patterns in medical images. At the core of these advances is the ability to exploit hierarchical feature representations learned solely from data, instead of features designed by hand according to domain-specific knowledge. Deep learning is rapidly becoming the state of the art, leading to enhanced performance in various medical applications. We introduce the fundamentals of deep learning methods and review their successes in image registration, detection of anatomical and cellular structures, tissue segmentation, computer-aided disease diagnosis and prognosis, and so on. We conclude by discussing research issues and suggesting future directions for further improvement.",
keywords = "Deep learning, Medical image analysis, Unsupervised feature learning",
author = "Dinggang Shen and Guorong Wu and Heung-Il Suk",
year = "2017",
month = "6",
day = "21",
doi = "10.1146/annurev-bioeng-071516-044442",
language = "English",
volume = "19",
pages = "221--248",
journal = "Annual Review of Biomedical Engineering",
issn = "1523-9829",
publisher = "Annual Reviews Inc.",

}

TY - JOUR

T1 - Deep Learning in Medical Image Analysis

AU - Shen, Dinggang

AU - Wu, Guorong

AU - Suk, Heung-Il

PY - 2017/6/21

Y1 - 2017/6/21

N2 - This review covers computer-assisted analysis of images in the field of medical imaging. Recent advances in machine learning, especially with regard to deep learning, are helping to identify, classify, and quantify patterns in medical images. At the core of these advances is the ability to exploit hierarchical feature representations learned solely from data, instead of features designed by hand according to domain-specific knowledge. Deep learning is rapidly becoming the state of the art, leading to enhanced performance in various medical applications. We introduce the fundamentals of deep learning methods and review their successes in image registration, detection of anatomical and cellular structures, tissue segmentation, computer-aided disease diagnosis and prognosis, and so on. We conclude by discussing research issues and suggesting future directions for further improvement.

AB - This review covers computer-assisted analysis of images in the field of medical imaging. Recent advances in machine learning, especially with regard to deep learning, are helping to identify, classify, and quantify patterns in medical images. At the core of these advances is the ability to exploit hierarchical feature representations learned solely from data, instead of features designed by hand according to domain-specific knowledge. Deep learning is rapidly becoming the state of the art, leading to enhanced performance in various medical applications. We introduce the fundamentals of deep learning methods and review their successes in image registration, detection of anatomical and cellular structures, tissue segmentation, computer-aided disease diagnosis and prognosis, and so on. We conclude by discussing research issues and suggesting future directions for further improvement.

KW - Deep learning

KW - Medical image analysis

KW - Unsupervised feature learning

UR - http://www.scopus.com/inward/record.url?scp=85021145223&partnerID=8YFLogxK

UR - http://www.scopus.com/inward/citedby.url?scp=85021145223&partnerID=8YFLogxK

U2 - 10.1146/annurev-bioeng-071516-044442

DO - 10.1146/annurev-bioeng-071516-044442

M3 - Article

C2 - 28301734

AN - SCOPUS:85021145223

VL - 19

SP - 221

EP - 248

JO - Annual Review of Biomedical Engineering

JF - Annual Review of Biomedical Engineering

SN - 1523-9829

ER -