# CLAIRE -- Parallelized Diffeomorphic Image Registration for Large-Scale Biomedical Imaging Applications

arXiv: https://arxiv.org/abs/2209.08189 · HTML: https://mlsanity.com/paper/2209.08189/

## Key facts

- Cited by 3 papers in the map (data through 14 Oct 2026).
- Builds on 21 of its 96 references that are in the map.
- First posted on arXiv 16 Sep 2022.

## Builds on (most cited first, 21 of 21)

- [Quicksilver: Fast Predictive Image Registration - a Deep Learning Approach](https://mlsanity.com/paper/1703.10908/) (2017)
- [Unsupervised Probabilistic Deformation Modeling for Robust Diffeomorphic Registration](https://mlsanity.com/paper/1804.07172/) (2018)
- [A Lagrangian Gauss-Newton-Krylov Solver for Mass- and Intensity-Preserving Diffeomorphic Image Registration](https://mlsanity.com/paper/1703.04446/) (2017)
- [Learning distributions of shape trajectories from longitudinal datasets: a hierarchical model on a manifold of diffeomorphisms](https://mlsanity.com/paper/1803.10119/) (2018)
- [CLAIRE: A distributed-memory solver for constrained large deformation diffeomorphic image registration](https://mlsanity.com/paper/1808.04487/) (2018)
- [An inexact Newton-Krylov algorithm for constrained diffeomorphic image registration](https://mlsanity.com/paper/1408.6299/) (2014)
- [Constrained H1-regularization schemes for diffeomorphic image registration](https://mlsanity.com/paper/1503.00757/) (2015)
- [Fast GPU 3D Diffeomorphic Image Registration](https://mlsanity.com/paper/2004.08893/) (2020)
- [PDE-constrained optimization in medical image analysis](https://mlsanity.com/paper/1803.00058/) (2018)
- [Integrated Biophysical Modeling and Image Analysis: Application to Neuro-Oncology](https://mlsanity.com/paper/2002.09628/) (2020)
- [A matrix-free approach to parallel and memory-efficient deformable image registration](https://mlsanity.com/paper/1804.10541/) (2018)
- [Image-Driven Biophysical Tumor Growth Model Calibration](https://mlsanity.com/paper/1907.07774/) (2019)
- [A Semi-Lagrangian two-level preconditioned Newton-Krylov solver for constrained diffeomorphic image registration](https://mlsanity.com/paper/1604.02153/) (2016)
- [Distributed-memory large deformation diffeomorphic 3D image registration](https://mlsanity.com/paper/1608.03630/) (2016)
- [Coupling Brain-Tumor Biophysical Models and Diffeomorphic Image Registration](https://mlsanity.com/paper/1710.06420/) (2017)
- [Multi-Node Multi-GPU Diffeomorphic Image Registration for Large-Scale Imaging Problems](https://mlsanity.com/paper/2008.12820/) (2020)
- [Deformably Registering and Annotating Whole CLARITY Brains to an Atlas via Masked LDDMM](https://mlsanity.com/paper/1605.02060/) (2016)
- [A Community-Developed Open-Source Computational Ecosystem for Big Neuro Data](https://mlsanity.com/paper/1804.02835/) (2018)
- [Fully-deformable 3D image registration in two seconds](https://mlsanity.com/paper/1812.06765/) (2018)
- [A Large Deformation Diffeomorphic Approach to Registration of CLARITY Images via Mutual Information](https://mlsanity.com/paper/1612.00356/) (2016)
- [FastReg: Fast Non-Rigid Registration via Accelerated Optimisation on the Manifold of Diffeomorphisms](https://mlsanity.com/paper/1903.01905/) (2019)

## Built on by (most cited first, 3 of 3)

- [Deep learning in medical image registration: introduction and survey](https://mlsanity.com/paper/2309.00727/) (2023)
- [Automatic classification of deformable shapes](https://mlsanity.com/paper/2211.02530/) (2022)
- [Advancing Annotat3D with Harpia: A CUDA-Accelerated Library For Large-Scale Volumetric Data Segmentation](https://mlsanity.com/paper/2511.11890/) (2025)

## Abstract (arXiv)

We study the performance of CLAIRE -- a diffeomorphic multi-node, multi-GPU image-registration algorithm, and software -- in large-scale biomedical imaging applications with billions of voxels. At such resolutions, most existing software packages for diffeomorphic image registration are prohibitively expensive. As a result, practitioners first significantly downsample the original images and then register them using existing tools. Our main contribution is an extensive analysis of the impact of downsampling on registration performance. We study this impact by comparing full-resolution registrations obtained with CLAIRE to lower-resolution registrations for synthetic and real-world imaging datasets. Our results suggest that registration at full resolution can yield a superior registration quality -- but not always. For example, downsampling a synthetic image from 10243 to 2563 decreases the Dice coefficient from 92% to 79%. However, the differences are less pronounced for noisy or low-contrast high-resolution images. CLAIRE allows us not only to register images of clinically relevant size in a few seconds but also to register images at unprecedented resolution in a reasonable time. The highest resolution considered is CLARITY images of size 2816×3016×1162. To the best of our knowledge, this is the first study on image registration quality at such resolutions.