Probabilistic Multilayer Regularization Network for Unsupervised 3D Brain Image Registration

Liu, Lihao; Hu, Xiaowei; Zhu, Lei; Heng, Pheng‐Ann

doi:10.1007/978-3-030-32245-8_39

Cited by 21 publications

(21 citation statements)

References 19 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…LPBA40 consists of 40 T1-weighted MR images and each volume has a segmentation mask with 56 anatomical labels. For a fair comparison, experiments are conducted following the recent work [7]. 42 images with 1722 pairs are used for training and 20 images with 380 pairs are used for testing on Mindboggle101.…”

Section: Experiments and Resultsmentioning

confidence: 99%

“…We further compare our method with several unsupervised registration approaches, including SyN [13], VM [5], RCN [9], and PMRN [7]. We follow [7] and report the average Dice value on five or seven large regions which are grouped from the initial small regions. Table 1 shows the results on the two benchmark datasets.…”

Section: Comparison With Other Methodsmentioning

confidence: 99%

“…Kuang et al [6] designed a new regularization function to improve the registration result. A probabilistic multilayer regularization network proposed by Liu et al [7] adopted direct regularizations to the hidden layers. However, the above methods are not effective when dealing with complicated deformations especially with large displacements.…”

Section: Introductionmentioning

confidence: 99%

See 2 more Smart Citations

Cascaded Feature Warping Network For Unsupervised Medical Image Registration

Zhang

Zhou

et al. 2021

2021 IEEE 18th International Symposium on Biomedical Imaging (ISBI)

View full text Add to dashboard Cite

Deformable image registration is widely utilized in medical image analysis, but most proposed methods fail in the situation of complex deformations. In this paper, we present a cascaded feature warping network to perform the coarse-to-fine registration. To achieve this, a shared-weights encoder network is adopted to generate the feature pyramids for the unaligned images. The feature warping registration module is then used to estimate the deformation field at each level. The coarse-to-fine manner is implemented by cascading the module from the bottom level to the top level. Furthermore, the multi-scale loss is also introduced to boost the registration performance. We employ two public benchmark datasets and conduct various experiments to evaluate our method. The results show that our method outperforms the state-of-the-art methods, which also demonstrates that the cascaded feature warping network can perform the coarse-to-fine registration effectively and efficiently.

show abstract

Section: Experiments and Resultsmentioning

confidence: 99%

Section: Comparison With Other Methodsmentioning

confidence: 99%

Section: Introductionmentioning

confidence: 99%

See 1 more Smart Citation

Cascaded Feature Warping Network For Unsupervised Medical Image Registration

Zhang

Zhou

et al. 2021

2021 IEEE 18th International Symposium on Biomedical Imaging (ISBI)

View full text Add to dashboard Cite

show abstract

“…We used the second baseline symmetric normalization (SyN) with mutual information as a similarity measure in the publicly available Advanced Normalization Tools (ANTs) software package [ 58 ]. We also tested the recently developed CNN-based methods, namely, VoxelMorph [ 41 ], FAIM [ 43 ], and Probab-Mul [ 44 ], and compared their performance with that of the proposed method. The hyperparameters of the CNN-based methods were consistent.…”

Section: Methodsmentioning

confidence: 99%

“…In addition, FAIM has less irreversible regions because of the penalty loss for negative Jacobian determinants [ 43 ]. Some scholars recently proposed the Probab-Mul registration method, which is a feature-level probability model that can perform regularization on the hidden layers of two deep convolutional neural networks [ 44 ].…”

Section: Introductionmentioning

confidence: 99%

Bayesian Fully Convolutional Networks for Brain Image Registration

Cui

et al. 2021

Journal of Healthcare Engineering

View full text Add to dashboard Cite

The purpose of medical image registration is to find geometric transformations that align two medical images so that the corresponding voxels on two images are spatially consistent. Nonrigid medical image registration is a key step in medical image processing, such as image comparison, data fusion, target recognition, and pathological change analysis. Existing registration methods only consider registration accuracy but largely neglect the uncertainty of registration results. In this work, a method based on the Bayesian fully convolutional neural network is proposed for nonrigid medical image registration. The proposed method can generate a geometric uncertainty map to calculate the uncertainty of registration results. This uncertainty can be interpreted as a confidence interval, which is essential for judging whether the source data are abnormal. Moreover, the proposed method introduces group normalization, which is conducive to the network convergence of the Bayesian neural network. Some representative learning-based image registration methods are compared with the proposed method on different image datasets. Experimental results show that the registration accuracy of the proposed method is better than that of the methods, and its antifolding performance is comparable to that of fast image registration and VoxelMorph. Furthermore, the proposed method can evaluate the uncertainty of registration results.

show abstract

MDReg‐Net: Multi‐resolution diffeomorphic image registration using fully convolutional networks with deep self‐supervision

Fan

2022

Human Brain Mapping

View full text Add to dashboard Cite

We present a diffeomorphic image registration algorithm to learn spatial transformations between pairs of images to be registered using fully convolutional networks (FCNs) under a self-supervised learning setting. The network is trained to estimate diffeomorphic spatial transformations between pairs of images by maximizing an image-wise similarity metric between fixed and warped moving images, similar to conventional image registration algorithms. It is implemented in a multi-resolution image registration framework to optimize and learn spatial transformations at different image resolutions jointly and incrementally with deep self-supervision in order to better handle large deformation between images. A spatial Gaussian smoothing kernel is integrated with the FCNs to yield sufficiently smooth deformation fields to achieve diffeomorphic image registration. Particularly, spatial transformations learned at coarser resolutions are utilized to warp the moving image, which is subsequently used for learning incremental transformations at finer resolutions. This procedure proceeds recursively to the full image resolution and the accumulated transformations serve as the final transformation to warp the moving image at the finest resolution. Experimental results for registering high resolution 3D structural brain magnetic resonance (MR) images have demonstrated that image registration networks trained by our method obtain robust, diffeomorphic image registration results within seconds with improved accuracy compared with state-of-the-art image registration algorithms.

show abstract

Probabilistic Multilayer Regularization Network for Unsupervised 3D Brain Image Registration

Cited by 21 publications

References 19 publications

Cascaded Feature Warping Network For Unsupervised Medical Image Registration

Cascaded Feature Warping Network For Unsupervised Medical Image Registration

Bayesian Fully Convolutional Networks for Brain Image Registration

MDReg‐Net: Multi‐resolution diffeomorphic image registration using fully convolutional networks with deep self‐supervision

Contact Info

Product

Resources

About