paper-with-me

홈 › Papers

Inverse Consistency by Construction for Multistep Deep Registration

2023-04-28 · Hastings Greer, Lin Tian, Francois-Xavier Vialard, Roland Kwitt, Sylvain Bouix, Raul San Jose Estepar, Richard Rushmore, Marc Niethammer

Inverse consistency is a desirable property for image registration. We propose a simple technique to make a neural registration network inverse consistent by construction, as a consequence of its structure, as long as it parameterizes its output transform by a Lie group. We extend this technique to multi-step neural registration by composing many such networks in a way that preserves inverse consistency. This multi-step approach also allows for inverse-consistent coarse to fine registration. We evaluate our technique on synthetic 2-D data and four 3-D medical image registration tasks and obtain excellent registration accuracy while assuring inverse consistency.

📄 PDF Abstract BibTeX arXiv:2305.00087

Code (2)

uncbiag/ByConstructionICON 공식 구현 pytorch
timH6502/MultiStepConsistent-LUMIRReg pytorch

Tasks

Image RegistrationMedical Image Registration

Similar Papers 제목 키워드 기반

SITReg: Multi-resolution architecture for symmetric, inverse consistent, and topology preserving image registration

2023-03-17 · Joel Honkamaa, Pekka Marttinen

Deep learning has emerged as a strong alternative for classical iterative methods for deformable medical image registration, where the goal is to find a mapping between the coordinate systems of two images. Popular class…

Deep LearningDeformable Medical Image RegistrationImage RegistrationMedical Image Registration

CoSIGN: Few-Step Guidance of ConSIstency Model to Solve General INverse Problems

2024-07-17 · Jiankun Zhao, Bowen Song, Liyue Shen

Diffusion models have been demonstrated as strong priors for solving general inverse problems. Most existing Diffusion model-based Inverse Problem Solvers (DIS) employ a plug-and-play approach to guide the sampling traje…

MORPH-LER: Log-Euclidean Regularization for Population-Aware Image Registration

2025-02-04 · Mokshagna Sai Teja Karanam, Krithika Iyer, Sarang Joshi, Shireen Elhabian

Spatial transformations that capture population-level morphological statistics are critical for medical image analysis. Commonly used smoothness regularizers for image registration fail to integrate population statistics…

Image RegistrationMedical Image AnalysisMORPHUnsupervised Image Registration

$\texttt{GradICON}$: Approximate Diffeomorphisms via Gradient Inverse Consistency

2022-06-13 · Lin Tian, Hastings Greer, François-Xavier Vialard, Roland Kwitt 외

We present an approach to learning regular spatial transformations between image pairs in the context of medical image registration. Contrary to optimization-based registration techniques and many modern learning-based m…

Computed Tomography (CT)Image RegistrationMedical Image RegistrationOptical Flow Estimation

GradICON: Approximate Diffeomorphisms via Gradient Inverse Consistency

2023-01-01 · CVPR 2023 1 · Lin Tian, Hastings Greer, François-Xavier Vialard, Roland Kwitt 외

We present an approach to learning regular spatial transformations between image pairs in the context of medical image registration. Contrary to optimization-based registration techniques and many modern learning-bas…

Image RegistrationMedical Image Registration