EasyReg

EasyReg performs symmetric multi-modality registration of brain magnetic resonance imaging (MRI) to enable accurate alignment across modalities and resolutions.


Key Features:

  • Symmetric Registration: Ensures symmetry in the registration process for unbiased image alignment.
  • Diffeomorphic Transformations: Produces diffeomorphic transformations that are invertible and smooth to preserve anatomical topology.
  • Modality and Resolution Agnosticism: Operates independently of MRI modality and resolution to handle diverse imaging scenarios.
  • Affine and Nonlinear Compatibility: Supports both affine and nonlinear registration models for comprehensive alignment.
  • Domain Randomization: Incorporates domain randomization to enhance robustness to modality and resolution changes.
  • Performance: Empirical results show comparable performance to classical methods for 1 mm isotropic single-modality registration and superior accuracy across different modalities and resolutions.

Scientific Applications:

  • Multi-modality Alignment: Aligning different MRI modalities for integrated analysis.
  • Longitudinal Analysis: Measuring anatomical changes over time in longitudinal studies.
  • Template Mapping: Mapping individual scans to a standardized template for group analyses.
  • Registration-based Segmentation: Facilitating segmentation by transferring labels or priors via registration.

Methodology:

Leverages domain randomization and combines classical registration methods with modern deep learning techniques.

Topics

Details

License:
GPL-2.0
Cost:
Free of charge
Tool Type:
command-line tool
Operating Systems:
Mac, Linux, Windows
Programming Languages:
Python
Added:
11/10/2023
Last Updated:
11/24/2024

Operations

Publications

Iglesias JE. A ready-to-use machine learning tool for symmetric multi-modality registration of brain MRI. Scientific Reports. 2023;13(1). doi:10.1038/s41598-023-33781-0. PMID:37095168. PMCID:PMC10126156.

PMID: 37095168
Funding: - National Institutes of Health: 1RF1-MH123195 - Alzheimer’s Research UK: ARUK-IRG2019A-003