☆ 4.7 Article

MD-SGT: Multi-dilation spherical graph transformer for unsupervised medical image registration

COMPUTERIZED MEDICAL IMAGING AND GRAPHICS (2023)

Related references

Note: Only part of the references are listed.

Article Engineering, Biomedical

Symmetric pyramid network for medical image inverse consistent diffeomorphic registration

Liutong Zhang et al.

Summary: This paper presents a novel symmetric pyramid network for medical image inverse consistent diffeomorphic registration. It encodes multi-scale images to feature pyramids and conducts feature-level diffeomorphic registration symmetrically. The proposed method outperforms others in accurate alignment and generates deformation fields with expected properties.

COMPUTERIZED MEDICAL IMAGING AND GRAPHICS (2023)

Add to Collection

Article Computer Science, Artificial Intelligence

Symmetric transformer-based network for unsupervised image registration

Mingrui Ma et al.

Summary: Medical image registration is a crucial task in medical image analysis. This research proposes a convolution-based efficient multihead self-attention (CEMSA) block to address the limitations of the traditional transformer in nonlocal registration. The proposed method achieves state-of-the-art performance in image registration tasks.

KNOWLEDGE-BASED SYSTEMS (2022)

Add to Collection

Article Computer Science, Artificial Intelligence

TransMorph: Transformer for unsupervised medical image registration

Junyu Chen et al.

Summary: Convolutional neural networks (ConvNets) have been a major focus in medical image analysis, but their performance is limited by a lack of consideration for long-range spatial relationships in images. Vision Transformer architectures have recently been proposed to address this issue and have shown state-of-the-art performances in medical imaging applications. In this paper, the researchers propose a hybrid Transformer-ConvNet model called TransMorph for volumetric medical image registration. The proposed model improves the performance significantly compared to existing registration methods and Transformer architectures, demonstrating the effectiveness of Transformers for medical image registration.

MEDICAL IMAGE ANALYSIS (2022)

Add to Collection

Article Mechanics

Deep double descent: where bigger models and more data hurt*

Preetum Nakkiran et al.

Summary: A study reveals a 'double-descent' phenomenon in modern deep learning tasks, where performance initially worsens and then improves as model size increases. The concept of effective model complexity is introduced to unify these phenomena and conjecture a generalized double descent based on this measure. Additionally, certain scenarios are identified where increasing the number of training samples, even quadrupling, can actually harm test performance.

JOURNAL OF STATISTICAL MECHANICS-THEORY AND EXPERIMENT (2021)

Add to Collection

Article Computer Science, Artificial Intelligence

CycleMorph: Cycle consistent unsupervised deformable image registration

Boah Kim et al.

Summary: CycleMorph is a cycle-consistent deformable image registration method that enhances image registration performance by providing implicit regularization to preserve topology during deformation. The method is flexible, applicable to both 2D and 3D registration problems, and can easily handle memory issues in large volume registration. Experiment results show that CycleMorph provides effective and accurate registration on diverse image pairs within seconds, validating the effectiveness of its cycle consistency.

MEDICAL IMAGE ANALYSIS (2021)

Add to Collection

Article Engineering, Biomedical

Deformable adversarial registration network with multiple loss constraints

Yi Luo et al.

Summary: Deformable medical image registration is crucial for theoretical research and clinical application. A new deformable generative adversarial registration framework is proposed, which enhances the model's performance, robustness, and training stability through the extraction of potential information from anatomical segmentation and multiple constraints. Experimental results demonstrate that the model provides a more accurate spatial alignment relationship between different patients' lung organs compared to traditional methods.

COMPUTERIZED MEDICAL IMAGING AND GRAPHICS (2021)

Add to Collection

Article Computer Science, Information Systems

Unsupervised 3D End-to-End Medical Image Registration With Volume Tweening Network

Shengyu Zhao et al.

IEEE JOURNAL OF BIOMEDICAL AND HEALTH INFORMATICS (2020)

Add to Collection

Article Computer Science, Interdisciplinary Applications

VoxelMorph: A Learning Framework for Deformable Medical Image Registration

Guha Balakrishnan et al.

IEEE TRANSACTIONS ON MEDICAL IMAGING (2019)

Add to Collection

Proceedings Paper Computer Science, Artificial Intelligence

Recursive Cascaded Networks for Unsupervised Medical Image Registration

Shengyu Zhao et al.

2019 IEEE/CVF INTERNATIONAL CONFERENCE ON COMPUTER VISION (ICCV 2019) (2019)

Add to Collection

Article Biochemical Research Methods

DRUNET: a dilated-residual U-Net deep learning network to segment optic nerve head tissues in optical coherence tomography images

Sripad Krishna Devalla et al.

BIOMEDICAL OPTICS EXPRESS (2018)

Add to Collection

Article Computer Science, Interdisciplinary Applications

MRF-Based Deformable Registration and Ventilation Estimation of Lung CT

Mattias P. Heinrich et al.

IEEE TRANSACTIONS ON MEDICAL IMAGING (2013)

Add to Collection

Review Neurosciences

FreeSurfer

Bruce Fischl

NEUROIMAGE (2012)

Add to Collection

Article Computer Science, Interdisciplinary Applications

Fast free-form deformation using graphics processing units

Marc Modat et al.

COMPUTER METHODS AND PROGRAMS IN BIOMEDICINE (2010)

Add to Collection

Article Computer Science, Interdisciplinary Applications

elastix: A Toolbox for Intensity-Based Medical Image Registration

Stefan Klein et al.

IEEE TRANSACTIONS ON MEDICAL IMAGING (2010)

Add to Collection

Article Neurosciences

Diffeomorphic demons: Efficient non-parametric image registration

Tom Vercauteren et al.

NEUROIMAGE (2009)

Add to Collection

Article Computer Science, Artificial Intelligence

Symmetric diffeomorphic image registration with cross-correlation: Evaluating automated labeling of elderly and neurodegenerative brain

B. B. Avants et al.

MEDICAL IMAGE ANALYSIS (2008)

Add to Collection

Article Computer Science, Artificial Intelligence

Computing large deformation metric mappings via geodesic flows of diffeomorphisms

MF Beg et al.

INTERNATIONAL JOURNAL OF COMPUTER VISION (2005)

Add to Collection

Article Neurosciences

Fast robust automated brain extraction

SM Smith

HUMAN BRAIN MAPPING (2002)

Add to Collection

Article Neurosciences

Improved optimization for the robust and accurate linear registration and motion correction of brain images

M Jenkinson et al.

NEUROIMAGE (2002)

Add to Collection

Article Computer Science, Artificial Intelligence

A global optimisation method for robust affine registration of brain images

M Jenkinson et al.

MEDICAL IMAGE ANALYSIS (2001)

Add to Collection

© Peeref 2019-2024. All rights reserved.