Deep Learning in Medical Image Analysis

Deep Learning in Medical Image Analysis

Dinggang Shen,^1,2 Guorong Wu,¹ and Heung-Il Suk^2
1 Department of Radiology, University of North Carolina, Chapel Hill, North Carolina 27599; email: [e-mail]
² Department of Brain and Cognitive Engineering, Korea University, Seoul 02841, Republic of Korea; email: [e-mail]

Annu. Rev. Biomed. Eng. 2017.19:221-248. Downloaded from www.annualreviews.org Access provided by 82.215.98.77 on 06/08/22. For personal use only.
Annu. Rev. Biomed. Eng. 2017. 19:221–48
First published as a Review in Advance on March 9, 2017
The Annual Review of Biomedical Engineering is online at bioeng.annualreviews.org
https://doi.org/10.1146/annurev-bioeng-071516-
044442

Ⓧ
Copyright c 2017 by Annual Reviews. All rights reserved

Keywords

medical image analysis, deep learning, unsupervised feature learning

Abstract

This review covers computer-assisted analysis of images in the field of med- ical 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 hier- archical 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 learn- ing methods and review their successes in image registration, detection of anatomical and cellular structures, tissue segmentation, computer-aided dis- ease diagnosis and prognosis, and so on. We conclude by discussing research issues and suggesting future directions for further improvement.
221

Contents

1. 
   INTRODUCTION 222
   
2. 
   DEEP LEARNING 224
   
   1. 
      Feed-Forward Neural Networks 224
      
   2. 
      Deep Models 225
      
   3. 
      Unsupervised Feature Representation Learning 226
      
   4. 
      Fine-Tuning Deep Models for Target Tasks 228
      
   5. 
      Convolutional Neural Networks 229
      
   6. 
      Reducing Overfitting 230
      
3. 
   APPLICATIONS IN MEDICAL IMAGING 230
   
   1. 
      Deep Feature Representation Learning in Medical Images 230
      
   2. 
      Deep Learning for Detection of Anatomical Structures 233
      
   3. 
      Deep Learning for Segmentation 235
      
   4. 
      Deep Learning for Computer-Aided Detection 236
      
   5. 
      Deep Learning for Computer-Aided Diagnosis 239
      
4. 
   CONCLUSION 242
   

Annu. Rev. Biomed. Eng. 2017.19:221-248. Downloaded from www.annualreviews.org Access provided by 82.215.98.77 on 06/08/22. For personal use only.

1.