Pair-Wise and Group-Wise Deformation Consistency in Deep Registration Network

Gu, Dongdong; Cao, Xiaohuan; Ma, Shanshan; Chen, Lei; Liu, Guocai; Shen, Dinggang; Zhang, Xue

doi:10.1007/978-3-030-59716-0_17

Cited by 11 publications

(10 citation statements)

References 38 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…It can not ensure that the pair of DDFs satisfies a correspondence [35], i.e., the point-to-point mappings defined by U and V are consistent with each other. Notably, transformation-cycle, which could improve the consistency of a pair of DDFs [35], has been introduced in recent registration networks [36]- [38]. Unlike previous approaches, BiRegNet aims to jointly predict and regularize the forward and backward DDFs, and the transformation consistency is achieved by introducing a constraint loss as follows,…”

Section: Methodsmentioning

confidence: 99%

Cross-Modality Multi-Atlas Segmentation via Deep Registration and Label Fusion

Ding¹,

Li²,

Zhuang³

et al. 2022

Preprint

View full text Add to dashboard Cite

Multi-atlas segmentation (MAS) is a promising framework for medical image segmentation. Generally, MAS methods register multiple atlases, i.e., medical images with corresponding labels, to a target image; and the transformed atlas labels can be combined to generate target segmentation via label fusion schemes. Many conventional MAS methods employed the atlases from the same modality as the target image. However, the number of atlases with the same modality may be limited or even missing in many clinical applications. Besides, conventional MAS methods suffer from the computational burden of registration or label fusion procedures. In this work, we design a novel crossmodality MAS framework, which uses available atlases from a certain modality to segment a target image from another modality. To boost the computational efficiency of the framework, both the image registration and label fusion are achieved by well-designed deep neural networks. For the atlas-to-target image registration, we propose a bi-directional registration network (BiRegNet), which can efficiently align images from different modalities. For the label fusion, we design a similarity estimation network (SimNet), which estimates the fusion weight of each atlas by measuring its similarity to the target image. SimNet can learn multi-scale information for similarity estimation to improve the performance of label fusion. The proposed framework was evaluated by the left ventricle and liver segmentation tasks on the MM-WHS and CHAOS datasets, respectively. Results have shown that the framework is effective for cross-modality MAS in both registration and label fusion 1 .

show abstract

Section: Methodsmentioning

confidence: 99%

Cross-Modality Multi-Atlas Segmentation via Deep Registration and Label Fusion

Ding¹,

Li²,

Zhuang³

et al. 2022

Preprint

View full text Add to dashboard Cite

show abstract

“…Since inverse consistency can reduce systematic bias caused by the order of input images and increase robustness, learningbased registration approaches have sought to incorporate this features. A number of works have attempted to promote symmetry by adding inverse-consistency losses [33][34][35][36][37][38][39][40] . These losses are generally based on computing two deformation fields (one with the order of the images switched), composing them, and penalizing the deviation from identity.…”

Section: Further Related Workmentioning

confidence: 99%

EasyReg: A ready-to-use deep learning tool for symmetric affine and nonlinear brain MRI registration

Iglesias

2023

Preprint

View full text Add to dashboard Cite

Volumetric registration of brain MRI is routinely used in human neuroimaging, e.g., to align different MRI modalities, to measure change in longitudinal analysis, to map an individual to a template, or in registration-based segmentation. Classical registration techniques based on numerical optimization have been very successful in this domain, and are implemented in widespread software suites like ANTs, Elastix, NiftyReg, or DARTEL. Over the last 7-8 years, learning-based techniques have emerged, which have a number of advantages like high computational efficiency, potential for higher accuracy, easy integration of supervision, and the ability to be part of a meta-architectures. However, their adoption in neuroimaging pipelines has so far been almost inexistent. Reasons include: lack of robustness to changes in MRI modality and resolution; lack of robust affine registration modules; lack of (guaranteed) symmetry; and, at a more practical level, the requirement of deep learning expertise that may be lacking at neuroimaging research sites. Here, we present EasyReg, an open-source, learning-based registration tool that can be easily used from the command line without any deep learning expertise or specific hardware. EasyReg combines the features of classical registration tools, the capabilities of modern deep learning methods, and the robustness to changes in MRI modality and resolution provided by our recent work in domain randomization. As a result, EasyReg is: fast; symmetric; diffeomorphic (and thus invertible); agnostic to MRI modality and resolution; compatible with affine and nonlinear registration; and does not require any preprocessing or parameter tuning. We present results on challenging registration tasks, showing that EasyReg is as accurate as classical methods when registering 1mm isotropic scans within MRI modality, but much more accurate across modalities and resolutions. EasyReg is publicly available as part of FreeSurfer; see https://surfer.nmr.mgh.harvard.edu/fswiki/EasyReg.

show abstract

“…Basically, we used the iterative registration and group mean method (Joshi et al, 2004) to update the average warped image to obtain the final template. A DL-based group-wise image registration network (Gu et al, 2020) was employed to perform intersubject registration, wherein the conventional losses like the smoothness and the mean squared image intensity similarity losses, as well as the inverseconsistency loss were used for training the network. In the first iteration (Figure 2a), the initial template (blue) was set as the average of the inputs (green), and DL-registration was performed to register the input images onto the template, resulting in respective warped images (yellow).…”

Section: Astc Algorithm Detailsmentioning

confidence: 99%

“…For intersubject deformable registration, we trained a group-wise consistent CNN to preserve cycle consistency in the deformations among the images (Gu et al, 2020). The training strategy of this network is shown in Figure 3.…”

Section: Consistent Registration Networkmentioning

confidence: 99%

“…However, iterative optimization procedures made the computing slow. DL-based registration has been investigated to improve computational efficiency while providing comparable accuracy (Fu et al, 2020;Gu et al, 2020;Litjens et al, 2017). To train registration networks, supervised learning is based on carefully building/simulating the ground-truth deformations (X.…”

Section: Introductionmentioning

confidence: 99%

See 1 more Smart Citation

An artificial‐intelligence‐based age‐specific template construction framework for brain structural analysis using magnetic resonance images

Shi

Hua

et al. 2022

Human Brain Mapping

Self Cite

View full text Add to dashboard Cite

It is an essential task to construct brain templates and analyze their anatomical structures in neurological and cognitive science. Generally, templates constructed from magnetic resonance imaging (MRI) of a group of subjects can provide a standard reference space for analyzing the structural and functional characteristics of the group. With recent development of artificial intelligence (AI) techniques, it is desirable to explore AI registration methods for quantifying age‐specific brain variations and tendencies across different ages. In this article, we present an AI‐based age‐specific template construction (called ASTC) framework for longitudinal structural brain analysis using T1‐weighted MRIs of 646 subjects from 18 to 82 years old collected from four medical centers. Altogether, 13 longitudinal templates were constructed at a 5‐year age interval using ASTC, and tissue segmentation and substructure parcellation were performed for analysis across different age groups. The results indicated consistent changes in brain structures along with aging and demonstrated the capability of ASTC for longitudinal neuroimaging study.

show abstract

Pair-Wise and Group-Wise Deformation Consistency in Deep Registration Network

Cited by 11 publications

References 38 publications

Cross-Modality Multi-Atlas Segmentation via Deep Registration and Label Fusion

Cross-Modality Multi-Atlas Segmentation via Deep Registration and Label Fusion

EasyReg: A ready-to-use deep learning tool for symmetric affine and nonlinear brain MRI registration

An artificial‐intelligence‐based age‐specific template construction framework for brain structural analysis using magnetic resonance images

Contact Info

Product

Resources

About