Anatomy-aware, label-informed approach improves image registration for challenging datasets
- 1Center for Developmental Biology and Regenerative Medicine, Seattle Children’s Research Institute, Seattle, Washington, United States of America
- 2Department of Radiology and Medical Imaging, University of Virginia, Charlottesville, Virginia, United States of America
- 3Department of Pediatrics, University of Washington, Seattle, Washington, United States of America
Abstract
Image registration-based volumetric morphometrics have emerged as a valuable method for identifying subtle morphological differences in neuroimaging and other biomedical images. However, accurate registration out-of-the-box remains challenging when overt morphological phenotypes are present, limiting the application of registration-based morphometrics in developmental and comparative studies where overt phenotypic differences are common. A new label-informed image registration function developed in the ANTsX ecosystem provides an easy to use, generalizable solution for anatomy-aware registration of a wider diversity of morphological variation including many overt phenotypes. In this approach, segmentations (i.e., labels) provide a priori regional correspondences that guide the registration, allowing morphological experts to define regions of correspondence based on biological concepts of homology (e.g., tissue origin, gene expression patterns). Here we demonstrate the utility of this label-informed image registration approach for registering knockout mouse embryos with overt phenotypes which fail to register to a wildtype (normative) template image by traditional registration methods. Due to severe scoliosis, E15.5 Gli2-/- mouse embryos exhibit a radical topological rearrangement of the internal organs; traditional intensity-only registration fails to accurately align the organs of knockout embryos with the normative template, limiting the interpretability of registration-based morphometric analyses. In contrast, label-informed image registration improved the correspondence of knockout subjects to the canonical template image, increasing the biological interpretability, power, and sensitivity of registration-derived morphometrics. All in all, label-informed image registration provides a flexible and customizable method to allow image registration in datasets for which registration-based morphometrics were previously unfeasible, unlocking new potential applications of registration-based morphometrics in developmental, comparative, and evolutionary studies.
Related
- Refined anatomy-based fitting reduces interaural place mismatch and improves speech outcomes, with preliminary evidence for reduced listening effort
- SeCAT (Sequence Consensus Amplicon Trimming): a simulation-informed Nextflow pipeline for cross-study harmonisation of 16S rRNA metabarcoding datasets
- GWAS-biologically informed SNP selection improves genomic relationship matrices and genetic parameter estimation in forest trees: insights from spruce and Eucalyptus
- Balanced DNA interpolation improves learning of genetic distance-informed embeddings in plants
- Lorlatinib in frontline treatment of advanced ALK-positive non-small cell lung cancer: a highly efficient new standard of care but still challenging to manage
BibTeX
@article{roston2026anatomyaware,
title = {{Anatomy-aware, label-informed approach improves image registration for challenging datasets}},
author = {Rachel A. Roston and Nicholas J. Tustison and A. Murat Maga},
journal = {PLOS One},
year = {2026},
month = sep,
doi = {10.1371/journal.pone.0357448},
url = {https://doi.org/10.1371/journal.pone.0357448},
note = {CC BY 4.0},
}
RIS
TY - JOUR
TI - Anatomy-aware, label-informed approach improves image registration for challenging datasets
AU - Rachel A. Roston
AU - Nicholas J. Tustison
AU - A. Murat Maga
PY - 2026
DA - 2026/09/08
JO - PLOS One
DO - 10.1371/journal.pone.0357448
UR - https://doi.org/10.1371/journal.pone.0357448
AB - Image registration-based volumetric morphometrics have emerged as a valuable method for identifying subtle morphological differences in neuroimaging and other biomedical images. However, accurate registration out-of-the-box remains challenging when overt morphological phenotypes are present, limiting the application of registration-based morphometrics in developmental and comparative studies where overt phenotypic differences are common. A new label-informed image registration function developed in the ANTsX ecosystem provides an easy to use, generalizable solution for anatomy-aware registration of a wider diversity of morphological variation including many overt phenotypes. In this approach, segmentations (i.e., labels) provide a priori regional correspondences that guide the registration, allowing morphological experts to define regions of correspondence based on biological concepts of homology (e.g., tissue origin, gene expression patterns). Here we demonstrate the utility of this label-informed image registration approach for registering knockout mouse embryos with overt phenotypes which fail to register to a wildtype (normative) template image by traditional registration methods. Due to severe scoliosis, E15.5 Gli2-/- mouse embryos exhibit a radical topological rearrangement of the internal organs; traditional intensity-only registration fails to accurately align the organs of knockout embryos with the normative template, limiting the interpretability of registration-based morphometric analyses. In contrast, label-informed image registration improved the correspondence of knockout subjects to the canonical template image, increasing the biological interpretability, power, and sensitivity of registration-derived morphometrics. All in all, label-informed image registration provides a flexible and customizable method to allow image registration in datasets for which registration-based morphometrics were previously unfeasible, unlocking new potential applications of registration-based morphometrics in developmental, comparative, and evolutionary studies.
SN - 1932-6203
ER -