SVF-Net: Learning Deformable Image Registration Using Shape Matching

By Marc-Michel Rohé, M. Datar, Tobias Heimann, Maxime Sermesant, Xavier Pennec. International Conference on Medical Image Computing and Computer-Assisted Intervention, 2017

329 citations recorded by the source corpus.

Subfields: Computer Vision and Pattern Recognition

View Paper: https://www.semanticscholar.org/paper/f9a53dcd92bd7c1f4e1689a08ad33dae77209eef

How researchers see this paper

The researchers whose trusted networks rank it highest, strongest advocate first. Every researcher gets a different order.

In Computer Vision and Pattern Recognition

Citations in the corpus

Understanding and Interpreting Machine Learning in Medical Image Computing Applications (2018, background): “Although some of these approaches have been tested on fMRI data, the performance of classifiers learned from multi-site datasets is in many cases lower than using a single site [16].”
TransMorph: Transformer for unsupervised medical image registration (2021, unknown): “Initially, the supervision of ground-truth deformation fields (which are usually generated using traditional registration methods) is needed for training the neural networks (Onofrey et al., 2013; Yang et al., 2017b; Rohé et al., 2017).”
Unsupervised Learning for Fast Probabilistic Diffeomorphic Registration (2018, background): “which can introduce a bias and necessitate significant preprocessing [23,26,28].”
Data Augmentation Using Learned Transformations for One-Shot Medical Image Segmentation (2019, methodology): “This mature field spans optimization-based methods [4, 7, 67, 70], and recent learning-based methods [8, 9, 20, 42, 62, 72, 80].”
An Unsupervised Learning Model for Deformable Medical Image Registration (2018, methodology): “Most of these rely on ground truth warp fields or segmentations [26, 35, 39, 45], a significant drawback compared to our method, which does not require either.”
Deep Learning Techniques for Automatic MRI Cardiac Multi-Structures Segmentation and Diagnosis: Is the Problem Solved? (2018, methodology): “The registration module implements an encoder-decoder network called SVFNet [56].”
Deep learning in medical image registration: a survey (2019, methodology): “The following year, Rohe et al. [102] also used a U-net [103] inspired network to estimate the deformation ﬁeld used to register 3D cardiac MR volumes.”
A review of multimodal image matching: Methods and applications (2021, methodology): “o using existing labeled datasets of real scenarios [95,96], many data”
Large Deformation Diffeomorphic Image Registration with Laplacian Pyramid Networks (2020, background): “ndent on the degree of misalignment between the input images and can be time-consuming with high-resolution 3D image volumes. Recent unsupervised deep learning-based image registration (DLIR) methods [4,5,20,26] have demonstrated promising registration speed and quality in a variety of deformable im”
Deformable Image Registration Using Cue-aware Deep Regression Network (2018, methodology): “Speciﬁ-cally, fully convolutional network (FCN) has been employed in [10] and [51] to learn the deformation momenta and stationary velocity ﬁeld (SVF), respectively.”
Unsupervised Learning of Probabilistic Diffeomorphic Registration for Images and Surfaces (2019, background): “Most earlier approaches demonstrated the feasibility of deep learning based registration, and required ground truth registration fields [13, 42, 59, 64, 68].”