Deep Learning for Medical Image Registration: A Comprehensive Review

  title={Deep Learning for Medical Image Registration: A Comprehensive Review},
  author={Subrato Bharati and M. Rubaiyat Hossain Mondal and Prajoy Podder and V. B. Surya Prasath},
: Image registration is a critical component in the applications of various medical image analyses. In recent years, there has been a tremendous surge in the development of deep learning (DL)-based medical image registration models. This paper provides a comprehensive review of medical image registration. Firstly, a discussion is provided for supervised registration categories, for example, fully supervised, dual supervised, and weakly supervised registration. Next, similarity-based as well as… 

Figures and Tables from this paper

Deep Learning Approaches to Automatic Chronic Venous Disease Classification

This work uses deep learning methods for automatic classification of the stage of CVD for self-diagnosis of a patient by using the image of the patient’s legs to solve the binary classification problem “legs–no legs” and multi-classification problem according to the CEAP classification.

Statistical learning methods for neuroimaging data analysis with applications

Nine major population-based statistical analysis methods and their associated statistical challenges are reviewed and recent progress in statistical methodology is presented to address these challenges.

Automatic classification of deformable shapes

To enhance accuracy of automatic classification, the smallest classes CL j are enriched by diffeomorphic interpolation of smooth surfaces between pairs S, S (cid:48) ∈ CL j and small random perturbations of surfaces S ∈CL j are implemented.



Deep learning in medical image registration: a survey

This survey outlines the evolution of deep learning-based medical image registration in the context of both research challenges and relevant innovations in the past few years and highlights future research directions to show how this field may be possibly moved forward to the next level.

Adversarial Image Registration with Application for MR and TRUS Image Fusion

By training two deep neural networks simultaneously, one being a generator and the other being a discriminator, one can obtain not only a network for image registration, but also a metric network which can help evaluate the quality of image registration.

Adversarial learning for mono- or multi-modal registration

Deep learning in medical image registration: a review

A comprehensive comparison among DL-based methods for lung and brain registration using benchmark datasets is provided and the statistics of all the cited works from various aspects are analyzed, revealing the popularity and future trend ofDL-based medical image registration.

Scalable High-Performance Image Registration Framework by Unsupervised Deep Feature Representations Learning

A learning-based image registration framework is proposed that uses deep learning to discover compact and highly discriminative features upon observed imaging data that scales well to new image modalities or new image applications with little to no human intervention.

End-to-end multimodal image registration via reinforcement learning

Deep adaptive registration of multi-modal prostate images

Deep Learning based Inter-Modality Image Registration Supervised by Intra-Modality Similarity

A non-rigid inter-modality image registration network, which can directly predict the transformation field from the input multimodal images, such as CT and MR images, is proposed.

A supervised network for fast image-guided radiotherapy (IGRT) registration

Abstract3D/3D image registration in IGRT, which aligns planning Computed Tomography (CT) image set with on board Cone Beam CT (CBCT) image set in a short time with high accuracy, is still a challenge