AEAU-Net: an unsupervised end-to-end registration network by combining affine transformation and deformable medical image registration

Qiu, Wei; Xiong, Lianjin; Li, Ning; Luo, Zhangrong; Wang, Yaobin; Zhang, Yangsong

doi:10.1007/s11517-023-02887-y

Cited by 3 publications

(2 citation statements)

References 30 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…It is possible that other architectures, such as the trained DL baselines tested in this work, perform equally well when trained using our strategy. Specifically, novel Bayesian similarity learning methods ( Grzech et al, 2022 ; Su & Yang, 2023 ) and frameworks that jointly optimize the affine and deformable components emerged since the initial submission of this work ( Chang et al, 2023 ; Meng et al, 2023 ; Qiu et al, 2023 ; L. Zhao et al, 2023 ).…”

Section: Discussionmentioning

confidence: 99%

Anatomy-aware and acquisition-agnostic joint registration with SynthMorph

Hoffmann,

Hoopes,

Greve

et al. 2024

Imaging Neuroscience

View full text Add to dashboard Cite

Affine image registration is a cornerstone of medical-image analysis. While classical algorithms can achieve excellent accuracy, they solve a time-consuming optimization for every image pair. Deep-learning (DL) methods learn a function that maps an image pair to an output transform. Evaluating the function is fast, but capturing large transforms can be challenging, and networks tend to struggle if a test-image characteristic shifts from the training domain, such as the resolution. Most affine methods are agnostic to the anatomy the user wishes to align, meaning the registration will be inaccurate if algorithms consider all structures in the image. We address these shortcomings with SynthMorph, a fast, symmetric, diffeomorphic, and easy-to-use DL tool for joint affine-deformable registration of any brain image without preprocessing. First, we leverage a strategy that trains networks with widely varying images synthesized from label maps, yielding robust performance across acquisition specifics unseen at training. Second, we optimize the spatial overlap of select anatomical labels. This enables networks to distinguish anatomy of interest from irrelevant structures, removing the need for preprocessing that excludes content which would impinge on anatomy-specific registration. Third, we combine the affine model with a deformable hypernetwork that lets users choose the optimal deformation-field regularity for their specific data, at registration time, in a fraction of the time required by classical methods. This framework is applicable to learning anatomy-aware, acquisition-agnostic registration of any anatomy with any architecture, as long as label maps are available for training. We analyze how competing architectures learn affine transforms and compare state-of-the-art registration tools across an extremely diverse set of neuroimaging data, aiming to truly capture the behavior of methods in the real world. SynthMorph demonstrates high accuracy and is available at https://w3id.org/synthmorph, as a single complete end-to-end solution for registration of brain magnetic resonance imaging (MRI) data.

show abstract

Section: Discussionmentioning

confidence: 99%

Anatomy-aware and acquisition-agnostic joint registration with SynthMorph

Hoffmann,

Hoopes,

Greve

et al. 2024

Imaging Neuroscience

View full text Add to dashboard Cite

show abstract

“…The skip connections method used in these methods may introduce certain semantic differences, especially in the connections between high-level and low-level features. To mitigate this difference, Qiu and Li et al (2023) introduced the RSP module to alleviate the difference between encoder and decoder features. This module introduces additional convolution operations in the residual connection, allowing for deeper feature fusion and reducing information loss.…”

Section: Introductionmentioning

confidence: 99%

MSRA-Net: multi-channel semantic-aware and residual attention mechanism network for unsupervised 3D image registration

Ren,

Song,

Zhang

et al. 2024

Phys. Med. Biol.

View full text Add to dashboard Cite

Objective: Convolutional neural network (CNN) is developing rapidly in the field of medical image registration, and the proposed U-Net further improves the precision of registration. However, this method may discard certain important information in the process of encoding and decoding steps, consequently leading to a decline in accuracy. To solve this problem, a multi-channel semantic-aware and residual attention mechanism network (MSRA-Net) is proposed in this paper. Approach: Our proposed network achieves efficient information aggregation by cleverly extracting the features of different channels. Firstly, a context-aware module (CAM) is designed to extract valuable contextual information. And the depth-wise separable convolution is employed in the CAM to alleviate the computational burden. Then, a new multi-channel semantic-aware module (MCSAM) is designed for more comprehensive fusion of up-sampling features. Additionally, the residual attention module (RAM) is introduced in the up-sampling process to extract more semantic information and minimize information loss.Main results: This study utilizes Dice score, ASSD and negative Jacobian determinant evaluation metrics to evaluate the influence of registration. The experimental results demonstrate that our proposed MSRA-Net has the highest accuracy compared to several state-of-the-art methods. Moreover, our network has demonstrated the highest Dice score across multiple datasets, thereby indicating that the superior generalization capabilities of our model.Significance: The proposed MSRA-Net offers a novel approach to improve medical image registration accuracy, with implications for various clinical applications.Our implementation is available at https://github.com/shy922/MSRA-Net.

show abstract