BIRNet: Brain image registration using dual-supervised fully convolutional networks

Fan, Jingfan; Cao, Xiaohuan; Yap, Pew Thian; Shen, Dinggang

doi:10.1016/j.media.2019.03.006

Cited by 244 publications

(151 citation statements)

References 63 publications

Supporting

Mentioning

151

Contrasting

Order By: Relevance

“…Using our method with a non-generative U-net style network [55] without a deformation encoding performed similarly compared to the proposed generative model. Adding supervised information such as segmentation masks in the training procedure as in [26], [29] led to a marginal increase in terms of registration performance (∼1-2% in DICE scores), so we decided that the performance gain is not large enough in order to justify the higher training complexity. Theoretically, our method allows measurement of registration uncertainty as proposed in [27] which we did not further investigate in this work.…”

Section: Resultsmentioning

confidence: 99%

“…Instead of using an image similarity, Hu et al [29] proposed to optimize the matching of labels based on a multi-scale DICE loss and a deformation regularization. Fan et al [26] proposed to jointly optimize a supervised and unsupervised objective by regressing ground-truth deformation fields (from an existing algorithm), while simultaneously optimizing an intensity-based similarity criterion. The disadvantage of these semi-supervised approaches is that their training complexity is higher since label information needs to be collected, and for example deformations outside the segmented areas are not guaranteed to be captured.…”

Section: A Deformable Image Registrationmentioning

confidence: 99%

See 1 more Smart Citation

Learning a Probabilistic Model for Diffeomorphic Registration

Krebs

Delingette

Mailhé

et al. 2019

IEEE Trans. Med. Imaging

200

156

View full text Add to dashboard Cite

We propose to learn a low-dimensional probabilistic deformation model from data which can be used for registration and the analysis of deformations. The latent variable model maps similar deformations close to each other in an encoding space. It enables to compare deformations, generate normal or pathological deformations for any new image or to transport deformations from one image pair to any other image.Our unsupervised method is based on variational inference. In particular, we use a conditional variational autoencoder (CVAE) network and constrain transformations to be symmetric and diffeomorphic by applying a differentiable exponentiation layer with a symmetric loss function. We also present a formulation that includes spatial regularization such as diffusion-based filters. Additionally, our framework provides multi-scale velocity field estimations. We evaluated our method on 3-D intra-subject registration using 334 cardiac cine-MRIs. On this dataset, our method showed state-of-the-art performance with a mean DICE score of 81.2% and a mean Hausdorff distance of 7.3mm using 32 latent dimensions compared to three state-of-the-art methods while also demonstrating more regular deformation fields. The average time per registration was 0.32s. Besides, we visualized the learned latent space and show that the encoded deformations can be used to transport deformations and to cluster diseases with a classification accuracy of 83% after applying a linear projection.

show abstract

Section: Resultsmentioning

confidence: 99%

Section: A Deformable Image Registrationmentioning

confidence: 99%

Learning a Probabilistic Model for Diffeomorphic Registration

Krebs

Delingette

Mailhé

et al. 2019

IEEE Trans. Med. Imaging

200

156

View full text Add to dashboard Cite

show abstract

“…The registration network follows the same architecture in [7], which is a hierarchical U-Net regression model [8]. The network takes 3D patches from the subject and template images as input and produces the deformation fields associated with the patches as output.…”

Section: Methodsmentioning

confidence: 99%

Adversarial Similarity Network for Evaluating Image Alignment in Deep Learning Based Registration

Fan

Cao

Xue

et al. 2018

Lecture Notes in Computer Science

Self Cite

103

View full text Add to dashboard Cite

This paper introduces an unsupervised adversarial similarity network for image registration. Unlike existing deep learning registration frameworks, our approach does not require ground-truth deformations and specific similarity metrics. We connect a registration network and a discrimination network with a deformable transformation layer. The registration network is trained with feedback from the discrimination network, which is designed to judge whether a pair of registered images are sufficiently similar. Using adversarial training, the registration network is trained to predict deformations that are accurate enough to fool the discrimination network. Experiments on four brain MRI datasets indicate that our method yields registration performance that is promising in both accuracy and efficiency compared with state-of-the-art registration methods, including those based on deep learning.

show abstract

“…Other supervised methods were presented by [6] who showed a network for predicting the momentum of large deformation diffeomorphic metric mapping model, [7] who presented a network for the registration of magnetic resonance images (MRI) of the brain and [8], [9] showed a method for pulmonary CT registration.…”

Section: Introductionmentioning

confidence: 99%

One-Shot Learning for Deformable Medical Image Registration and Periodic Motion Tracking

Fechter

Baltas

2020

IEEE Trans. Med. Imaging

View full text Add to dashboard Cite

Deformable image registration is a very important field of research in medical imaging. Recently multiple deep learning approaches were published in this area showing promising results. However, drawbacks of deep learning methods are the need for a large amount of training datasets and their inability to register unseen images different from the training datasets. One shot learning comes without the need of large training datasets and has already been proven to be applicable to 3D data. In this work we present an one shot registration approach for periodic motion tracking in 3D and 4D datasets. When applied to 3D dataset the algorithm calculates the inverse of a registration vector field simultaneously. For registration we employed a U-Net combined with a coarse to fine approach and a differential spatial transformer module. The algorithm was thoroughly tested with multiple 4D and 3D datasets publicly available. The results show that the presented approach is able to track periodic motion and to yield a competitive registration accuracy. Possible applications are the use as a stand-alone algorithm for 3D and 4D motion tracking or in the beginning of studies until enough datasets for a separate training phase are available.

show abstract

BIRNet: Brain image registration using dual-supervised fully convolutional networks

Cited by 244 publications

References 63 publications

Learning a Probabilistic Model for Diffeomorphic Registration

Learning a Probabilistic Model for Diffeomorphic Registration

Adversarial Similarity Network for Evaluating Image Alignment in Deep Learning Based Registration

One-Shot Learning for Deformable Medical Image Registration and Periodic Motion Tracking

Contact Info

Product

Resources

About