PULPo: Probabilistic Unsupervised Laplacian Pyramid Registration
Deformable image registration is fundamental to many medical imaging applications.
Registration is an inherently ambiguous task often admitting many viable solutions. While …
Registration is an inherently ambiguous task often admitting many viable solutions. While …
CAMLD: Contrast-Agnostic Medical Landmark Detection with Consistency-Based Regularization
S Salari, A Harirpoush, H Rivaz, Y ** the topographic organization of the human zona incerta using diffusion MRI
The zona incerta (ZI) is a deep brain region originally described by Auguste Forel as an"
immensely confusing area about which nothing can be said." Despite the elusive nature of …
immensely confusing area about which nothing can be said." Despite the elusive nature of …
The impact of localization and registration accuracy on estimates of deep brain stimulation electrode position in stereotactic space
Abstract Effects of deep brain stimulation (DBS) depend on millimetric accuracy and are
commonly studied across populations by registering patient scans to a stereotactic space …
commonly studied across populations by registering patient scans to a stereotactic space …
Deformable Image Registration with Multi-scale Feature Fusion from Shared Encoder, Auxiliary and Pyramid Decoders
H Zhou, S Hu - arxiv preprint arxiv:2408.05717, 2024 - arxiv.org
In this work, we propose a novel deformable convolutional pyramid network for
unsupervised image registration. Specifically, the proposed network enhances the …
unsupervised image registration. Specifically, the proposed network enhances the …
DL2G: Anatomical Landmark Detection with Deep Local Features and Geometric Global Constraint
R Wang, W Yang, K **ao, Y Sun… - 2024 IEEE …, 2024 - ieeexplore.ieee.org
Anatomical landmark detection, a pivotal research area in medical image processing, holds
immense value in surgical navigation, image registration, and related fields. Traditional …
immense value in surgical navigation, image registration, and related fields. Traditional …
SIHDConReg: Continual learning for unsupervised 3D medical image registration via an improved synaptic intelligence
A Remigio - 2025 - researchsquare.com
The ability of machine learning algorithms to generalize to data shifts is essential in medical
imaging due to the high accuracy demands in clinical practice. Continual learning …
imaging due to the high accuracy demands in clinical practice. Continual learning …
Characterisation of Longitudinal Brain Morphology, Neurometabolism and Prenatal to Neonatal Brain Growth in Patients with Congenital Heart Disease
C Steger - 2024 - zora.uzh.ch
Congenital heart disease (CHD) affect 8 in 1000 newborns (Liu et al. 2019). The
consequences of CHD vary greatly, depending on the specific type of CHD. While …
consequences of CHD vary greatly, depending on the specific type of CHD. While …