NeurReg: Neural Registration and Its Application to Image Segmentation

@article{Zhu2020NeurRegNR,
  title={NeurReg: Neural Registration and Its Application to Image Segmentation},
  author={Wentao Zhu and Andriy Myronenko and Ziyue Xu and Wenqi Li and Holger R. Roth and Yufang Huang and Fausto Milletari and Daguang Xu},
  journal={2020 IEEE Winter Conference on Applications of Computer Vision (WACV)},
  year={2020},
  pages={3606-3615}
}
Registration is a fundamental task in medical image analysis which can be applied to several tasks including image segmentation, intra-operative tracking, multi-modal image alignment, and motion analysis. Popular registration tools such as ANTs and NiftyReg optimize an objective function for each pair of images from scratch which is time-consuming for large images with complicated deformation. Facilitated by the rapid progress of deep learning, learning-based approaches such as VoxelMorph have… Expand
Test-Time Training for Deformable Multi-Scale Image Registration
TLDR
This work constructs a test-time training for deep deformable image registration to improve the generalization ability of conventional learning-based registration model, and designs multi-scale deep networks to consecutively model the residual deformations, which is effective for high variational deformations. Expand
Generating Patient-like Phantoms Using Fully Unsupervised Deformable Image Registration with Convolutional Neural Networks
TLDR
It is shown that the resulting deformed phantom competently matches the anatomy model of a real human while providing the "gold-standard" for the anatomies, which could potentially serve as a data augmentation tool in today's deep learning studies. Expand
Deep multispectral image registration network
TLDR
This paper proposes a weakly supervised MSI image registration network, called MSI-R-NET, which utilizes the blood vessel segmentation label to provide spatial correspondence and demonstrates that the proposed segmentation-driven registration method is highly accurate. Expand
Modeling the Probabilistic Distribution of Unlabeled Data forOne-shot Medical Image Segmentation
TLDR
This paper develops a data augmentation method for one-shot brain magnetic resonance imaging (MRI) image segmentation which exploits only one labeled MRI image (named atlas) and a few unlabeled images and introduces a new standard segmentation benchmark to evaluate the generalization performance of a segmentation network through a cross-dataset setting. Expand
Joint Progressive and Coarse-to-fine Registration of Brain MRI via Deformation Field Integration and Non-Rigid Feature Fusion
  • Jinxin Lv, Zhiwei Wang, +4 authors Qiang Li
  • Computer Science, Engineering
  • ArXiv
  • 2021
TLDR
This paper proposes a unified framework for robust brain MRI registration in both progressive and coarse-to-fine manners simultaneously, building on a dual-encoder U-Net, where the fixed-moving MRI pair is encoded and decoded into multi-scale deformation subfields from coarse to fine. Expand
Shape-Regularized Unsupervised Left Ventricular Motion Network With Segmentation Capability In 3d+ Time Echocardiography
TLDR
A shape regularized convolutional neural network for estimating dense displacement fields between sequential 3D B-mode echocardiography images with the capability of also predicting left ventricular segmentation masks and performs favorably against competing methods. Expand
The Power of Proxy Data and Proxy Networks for Hyper-Parameter Optimization in Medical Image Segmentation
TLDR
This work focuses on accelerating the estimation of hyper-parameters by proposing two novel methodologies: proxy data and proxy networks, and shows that the proposed approach of utilizing a proxy network can speed up an AutoML framework forhyper-parameter search by 3.3×, and by 4.4× if proxyData and proxy network are utilized together. Expand
A Review of Uncertainty Quantification in Deep Learning: Techniques, Applications and Challenges
TLDR
This study reviews recent advances in UQ methods used in deep learning and investigates the application of these methods in reinforcement learning (RL), and outlines a few important applications of UZ methods. Expand
Detecting Pancreatic Adenocarcinoma in Multi-phase CT Scans via Alignment Ensemble
TLDR
An extensive empirical evaluation on two PDAC datasets is provided and it is shown that the proposed alignment ensemble significantly outperforms previous state-of-the-art approaches, illustrating strong potential for clinical use. Expand
Medical Image Computing and Computer Assisted Intervention – MICCAI 2020: 23rd International Conference, Lima, Peru, October 4–8, 2020, Proceedings, Part III
TLDR
This work presents a patientspecific, learning-based method for 3D reconstruction of sinus surface anatomy directly and only from endoscopic videos and demonstrates the effectiveness and accuracy of this method on in and ex vivo data. Expand
...
1
2
...

References

SHOWING 1-10 OF 50 REFERENCES
VoxelMorph: A Learning Framework for Deformable Medical Image Registration
TLDR
VoxelMorph promises to speed up medical image analysis and processing pipelines while facilitating novel directions in learning-based registration and its applications and demonstrates that the unsupervised model’s accuracy is comparable to the state-of-the-art methods while operating orders of magnitude faster. Expand
An Unsupervised Learning Model for Deformable Medical Image Registration
TLDR
The proposed method uses a spatial transform layer to reconstruct one image from another while imposing smoothness constraints on the registration field, and demonstrates registration accuracy comparable to state-of-the-art 3D image registration, while operating orders of magnitude faster in practice. Expand
An Artificial Agent for Robust Image Registration
TLDR
This paper demonstrates, on two 3-D/3-D medical image registration examples with drastically different nature of challenges, that the artificial agent outperforms several state-of-art registration methods by a large margin in terms of both accuracy and robustness. Expand
Robust Non-rigid Registration Through Agent-Based Action Learning
TLDR
This paper investigates in this paper how DL could help organ-specific (ROI-specific) deformable registration, to solve motion compensation or atlas-based segmentation problems for instance in prostate diagnosis and presents a training scheme with a large number of synthetically deformed image pairs requiring only a small number of real inter-subject pairs. Expand
SVF-Net: Learning Deformable Image Registration Using Shape Matching
TLDR
An innovative approach for registration based on the deterministic prediction of the parameters from both images instead of the optimization of a energy criteria is proposed and shows an important improvement over a state of the art optimization based algorithm. Expand
AIRNet: Self-Supervised Affine Registration for 3D Medical Images using Neural Networks
TLDR
This work proposes a self-supervised learning method for affine image registration on 3D medical images that achieves better overall performance on registration of images from different patients and modalities with 100x speed-up in execution time. Expand
End-to-End Unsupervised Deformable Image Registration with a Convolutional Neural Network
TLDR
The results demonstrate that registration with DIRNet is as accurate as a conventional deformable image registration method with short execution times. Expand
Nonrigid Image Registration Using Multi-scale 3D Convolutional Neural Networks
TLDR
The proposed RegNet is trained using a large set of artificially generated DVFs, does not explicitly define a dissimilarity metric, and integrates image content at multiple scales to equip the network with contextual information, thereby greatly simplifying the training problem. Expand
Deep learning in medical image registration: a survey
TLDR
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. Expand
A neural network approach for fast, automated quantification of DIR performance
TLDR
A proof‐of‐concept methodology for automated quantification of DIR performance that was able to quantify DIR error to within a single voxel for 95% of the sub‐volumes examined and provided the necessary level of abstraction to estimate a quantified TRE from the ISM expectations described above. Expand
...
1
2
3
4
5
...