H-ViT: A Hierarchical Vision Transformer for Deformable Image Registration

M Ghahremani, M Khateri, B Jian… - Proceedings of the …, 2024 - openaccess.thecvf.com
This paper introduces a novel top-down representation approach for deformable image
registration which estimates the deformation field by capturing various short-and long-range …

MUsculo-Skeleton-Aware (MUSA) deep learning for anatomically guided head-and-neck CT deformable registration

H Liu, E McKenzie, D Xu, Q Xu, RK Chin, D Ruan… - Medical Image …, 2025 - Elsevier
Deep-learning-based deformable image registration (DL-DIR) has demonstrated improved
accuracy compared to time-consuming non-DL methods across various anatomical sites …

Unsupervised learning of spatially varying regularization for diffeomorphic image registration

J Chen, S Wei, Y Liu, Z Bian, Y He, A Carass… - arxiv preprint arxiv …, 2024 - arxiv.org
Spatially varying regularization accommodates the deformation variations that may be
necessary for different anatomical regions during deformable image registration. Historically …

TimeFlow: Longitudinal Brain Image Registration and Aging Progression Analysis

B Jian, J Pan, Y Li, F Bongratz, R Li, D Rueckert… - arxiv preprint arxiv …, 2025 - arxiv.org
Predicting future brain states is crucial for understanding healthy aging and
neurodegenerative diseases. Longitudinal brain MRI registration, a cornerstone for such …

CAR: Contrast-Agnostic Deformable Medical Image Registration with Contrast-Invariant Latent Regularization

Y Wang, S Du, S Zheng, X Luo, C Qin - International Workshop on …, 2024 - Springer
Multi-contrast image registration is a challenging task due to the complex intensity
relationships between different imaging contrasts. Conventional image registration methods …

Inference Stage Denoising for Undersampled MRI Reconstruction

Y Xue, C Qin, SA Tsaftaris - arxiv preprint arxiv:2402.08692, 2024 - arxiv.org
Reconstruction of magnetic resonance imaging (MRI) data has been positively affected by
deep learning. A key challenge remains: to improve generalisation to distribution shifts …