Skip to main page content
U.S. flag

An official website of the United States government

Dot gov

The .gov means it’s official.
Federal government websites often end in .gov or .mil. Before sharing sensitive information, make sure you’re on a federal government site.

Https

The site is secure.
The https:// ensures that you are connecting to the official website and that any information you provide is encrypted and transmitted securely.

Access keys NCBI Homepage MyNCBI Homepage Main Content Main Navigation
Review
. 2020 Oct 22;65(20):20TR01.
doi: 10.1088/1361-6560/ab843e.

Deep learning in medical image registration: a review

Yabo Fu  1 , Yang Lei, Tonghe Wang, Walter J Curran, Tian Liu, Xiaofeng Yang
Affiliations
Review

Deep learning in medical image registration: a review

Yabo Fu et al. Phys Med Biol. .

Abstract

This paper presents a review of deep learning (DL)-based medical image registration methods. We summarized the latest developments and applications of DL-based registration methods in the medical field. These methods were classified into seven categories according to their methods, functions and popularity. A detailed review of each category was presented, highlighting important contributions and identifying specific challenges. A short assessment was presented following the detailed review of each category to summarize its achievements and future potential. We provided a comprehensive comparison among DL-based methods for lung and brain registration using benchmark datasets. Lastly, we analyzed the statistics of all the cited works from various aspects, revealing the popularity and future trend of DL-based medical image registration.

PubMed Disclaimer

Conflict of interest statement

Disclosures

The authors declare no conflicts of interest.

Figures

Figure 1.
Figure 1.
Overview of seven categories of DL-based methods in medical image registration.
Figure 2.
Figure 2.
Overview of number of publications in DL-based medical image registration. The dotted line indicates increased interest in DL-based registration methods over the years. ‘DeepSimilarity’ is the category of using DL-based similarity measures in traditional registration frameworks. ‘RegValidation’ represents the category of using DL for registration validation.
Figure 3.
Figure 3.
Percentage pie chart of different categories.
Figure 4.
Figure 4.
Percentage pie chart of various attributes of DL-based image registration methods.
See this image and copyright information in PMC

References

    1. Andersen ES, Noe KØ, Sørensen TS, Nielsen SK, Fokdal L, Paludan M, Lindegaard JC and Tanderup K 2013. Simple DVH parameter addition as compared to deformable registration for bladder dose accumulation in cervix cancer brachytherapy Radiother. Oncol 107 52–57 - PubMed
    1. Avants BB, Epstein CL, Grossman M and Gee JC 2008. Symmetric diffeomorphic image registration with cross-correlation: evaluating automated labeling of elderly and neurodegenerative brain Med. Image Anal 12 26–41 - PMC - PubMed
    1. Avants BB, Tustison NJ, Song G, Cook PA, Klein A and Gee JC 2011. A reproducible evaluation of ANTs similarity metric performance in brain image registration Neuroimage 54 2033–44 - PMC - PubMed
    1. Bakker B 2002. Reinforcement learning with long short-term memory Advances in Neural Information Processing Systems 14 (NIPS 2001) ed Dietterich TG, Becker S and Ghahramani Z (Cambridge, MA: MIT Press; ) pp 1475–82
    1. Balakrishnan G, Zhao A, Sabuncu MR, Guttag J and Dalca AV 2018. An unsupervised learning model for deformable medical image registration 2018 IEEE/CVF Conference on Computer Vision and Pattern Recognition (Salt Lake City, UT, 18–23 June 2018) (Piscataway, NJ: IEEE; ) pp 9252–60

Publication types