mlsanityData to 14 Oct 2026

MultiMorph: On-demand Atlas Construction

arXiv 2504.00247 ↗First posted 31 Mar 2025cs.CV cs.AIcited by 9

Not on the map. Why?

Abstract (arXiv)

We present MultiMorph, a fast and efficient method for constructing anatomical atlases on the fly. Atlases capture the canonical structure of a collection of images and are essential for quantifying anatomical variability across populations. However, current atlas construction methods often require days to weeks of computation, thereby discouraging rapid experimentation. As a result, many scientific studies rely on suboptimal, precomputed atlases from mismatched populations, negatively impacting downstream analyses. MultiMorph addresses these challenges with a feedforward model that rapidly produces high-quality, population-specific atlases in a single forward pass for any 3D brain dataset, without any fine-tuning or optimization. MultiMorph is based on a linear group-interaction layer that aggregates and shares features within the group of input images. Further, by leveraging auxiliary synthetic data, MultiMorph generalizes to new imaging modalities and population groups at test-time. Experimentally, MultiMorph outperforms state-of-the-art optimization-based and learning-based atlas construction methods in both small and large population settings, with a 100-fold reduction in time. This makes MultiMorph an accessible framework for biomedical researchers without machine learning expertise, enabling rapid, high-quality atlas generation for diverse studies.

Key facts. Cited by 9 papers in the map (data through 14 Oct 2026). Builds on 32 of its 90 references that are in the map. First posted on arXiv 31 Mar 2025.

Builds on

32 of 90 references.

References · 32

  1. 2015U-Net: Convolutional Networks for Biomedical Image Segmentationcited by 19,713
  2. 2015Spatial Transformer Networkscited by 1,429
  3. 2018VoxelMorph: A Learning Framework for Deformable Medical Image Registrationcited by 662
  4. 2016Geometric deep learning on graphs and manifolds using mixture model CNNscited by 468
  5. 2021SynthSeg: Segmentation of brain MRI scans of any contrast and resolution without retrainingcited by 237
  6. 2019Unsupervised Learning of Probabilistic Diffeomorphic Registration for Images and Surfacescited by 186
  7. 2020SynthMorph: learning contrast-invariant registration without acquired imagescited by 140
  8. 2022SynthStrip: Skull-Stripping for Any Brain Imagecited by 127
  9. 2017Quicksilver: Fast Predictive Image Registration - a Deep Learning Approachcited by 113
  10. 2021Self-Attention Between Datapoints: Going Beyond Individual Input-Output Pairs in Deep Learningcited by 113
  11. 2017End-to-End Unsupervised Deformable Image Registration with a Convolutional Neural Networkcited by 75
  12. 2019Learning Conditional Deformable Templates with Convolutional Networkscited by 65
20 more
  1. 2018Learning a Probabilistic Model for Diffeomorphic Registrationcited by 62
  2. 2022Robust machine learning segmentation for large-scale analysis of heterogeneous clinical brain MRI datasetscited by 51
  3. 2018DenseReg: Fully Convolutional Dense Shape Regression In-the-Wildcited by 32
  4. 2021Generative Adversarial Registration for Improved Conditional Deformable Templatescited by 31
  5. 2024Learning General-Purpose Biomedical Volume Representations using Randomized Synthesiscited by 29
  6. 2022SVoRT: Iterative Transformer for Slice-to-Volume Registration in Fetal Brain MRIcited by 26
  7. 2020Atlas-ISTN: Joint Segmentation, Registration and Atlas Construction with Image-and-Spatial Transformer Networkscited by 25
  8. 2023A Robust and Interpretable Deep Learning Framework for Multi-modal Registration via Keypointscited by 25
  9. 2023Neuralizer: General Neuroimage Analysis without Re-Trainingcited by 24
  10. 2023Non-iterative Coarse-to-fine Transformer Networks for Joint Affine and Deformable Image Registrationcited by 21
  11. 2023Anatomy-aware and acquisition-agnostic joint registration with SynthMorphcited by 19
  12. 2022Aladdin: Joint Atlas Building and Diffeomorphic Registration Learning with Pairwise Alignmentcited by 18
  13. 2020Partial Volume Segmentation of Brain MRI Scans of any Resolution and Contrastcited by 16
  14. 2024CINA: Conditional Implicit Neural Atlas for Spatio-Temporal Representation of Fetal Brainscited by 14
  15. 2022SuperWarp: Supervised Learning and Warping on U-Net for Invariant Subvoxel-Precise Registrationcited by 8
  16. 2024Boosting Skull-Stripping Performance for Pediatric Brain Imagescited by 8
  17. 2024Diff-Def: Diffusion-Generated Deformation Fields for Conditional Atlasescited by 8
  18. 2024Registration by Regression (RbR): a framework for interpretable and flexible atlas registrationcited by 8
  19. 2023Dynamic Neural Fields for Learning Atlases of 4D Fetal MRI Time-seriescited by 4
  20. 2022InstantGroup: Instant Template Generation for Scalable Group of Brain MRI Registrationcited by 2

Built on by

Cited by year (2026 to 14 Oct)

Citing papers per year: 2025: 4; 2026: 5.

9 papers.

  1. 2025OmniBrainBench: A Comprehensive Multimodal Benchmark for Brain Imaging Analysis Across Multi-stage Clinical Taskscited by 8
  2. 2025Conditional Fetal Brain Atlas Learning for Automatic Tissue Segmentationcited by 1
  3. 2025Deep infant brain segmentation from multi-contrast MRIcited by 1
  4. 2025Unified Brain Surface and Volume Registrationcited by 0
  5. 2026Volumetrically Consistent Implicit Atlas Learning via Neural Diffeomorphic Flow for Placenta MRIcited by 0
  6. 2026Set-Based Groupwise Registration for Variable-Length, Variable-Contrast Cardiac MRIcited by 0
  7. 2026Deep Image Prototype Learning with Geometric Heat-Kernel Priorscited by 0
  8. 2026textttDisMorph: learning to disentangle technical distortions from true biological changecited by 0
  9. 2026Atlases Are Already Inside: Recovering Population Templates from Pretrained Diffusion Modelscited by 0