A survey on deep learning in medical image registration: New technologies, uncertainty, evaluation metrics, and beyond

J Chen, Y Liu, S Wei, Z Bian, S Subramanian… - Medical Image …, 2024 - Elsevier
Deep learning technologies have dramatically reshaped the field of medical image
registration over the past decade. The initial developments, such as regression-based and U …

The role of AI in prostate MRI quality and interpretation: Opportunities and challenges

H Kim, SW Kang, JH Kim, H Nagar, M Sabuncu… - European Journal of …, 2023 - Elsevier
Prostate MRI plays an important role in imaging the prostate gland and surrounding tissues,
particularly in the diagnosis and management of prostate cancer. With the widespread …

Modality-Agnostic Structural Image Representation Learning for Deformable Multi-Modality Medical Image Registration

TCW Mok, Z Li, Y Bai, J Zhang, W Liu… - Proceedings of the …, 2024 - openaccess.thecvf.com
Establishing dense anatomical correspondence across distinct imaging modalities is a
foundational yet challenging procedure for numerous medical image analysis studies and …

Large Language Models for Multimodal Deformable Image Registration

M Ma, W Wang, J Ning, J He, N Sebe… - arxiv preprint arxiv …, 2024 - arxiv.org
The challenge of Multimodal Deformable Image Registration (MDIR) lies in the conversion
and alignment of features between images of different modalities. Generative models (GMs) …

Unsupervised Exemplar-Based Image-to-Image Translation and Cascaded Vision Transformers for Tagged and Untagged Cardiac Cine MRI Registration

M Ye, M Kanski, D Yang, L Axel… - Proceedings of the …, 2024 - openaccess.thecvf.com
Multi-modal registration between tagged and untagged cardiac cine magnetic resonance
(MR) images remains difficult, due to the domain gap and large deformations between the …

Contrastive Learning of Multimodal Consistency Feature Representation for Remote Sensing Image Registration

Z Han, N Lv, Z Wang, W Han, L Cong… - IEEE Journal of …, 2024 - ieeexplore.ieee.org
Feature representation is a crucial issue in multimodal image registration. The handcrafted
features extracted by traditional methods are highly sensitive to nonlinear radiation …