Search research articles

ABOUT JoVE

Overview Leadership Blog JoVE Help Center

AUTHORS

Publishing Process Editorial Board Scope & Policies Peer Review FAQ Submit

LIBRARIANS

Testimonials Subscriptions Access Resources Library Advisory Board FAQ

RESEARCH

JoVE Journal Methods Collections JoVE Encyclopedia of Experiments Archive

EDUCATION

JoVE Core JoVE Business JoVE Science Education JoVE Lab Manual Faculty Resource Center Faculty Site

Terms & Conditions of Use

Search research articles

Home
Deep Computational Anatomy Via Latent-aligned Multiview Normalizing Flows.

Home
Deep Computational Anatomy Via Latent-aligned Multiview Normalizing Flows.

Related Concept Videos

Uniform Depth Channel Flow

Uniform Depth Channel Flow

Uniform depth channel flow keeps fluid depth consistent along channels such as irrigation canals. In natural channels, such as rivers, approximate uniform flow is often assumed. This condition occurs when the channel’s bottom slope matches the energy slope, balancing potential energy lost from gravity with head loss due to shear stress. This balance prevents depth changes along the channel length, resulting in a steady, uniform flow.Uniform flow in open channels with a constant cross-section...

You might also read

Related Articles

Articles linked to this work by shared authors, journal, and citation graph.

Sort by

Same author

Adaptive Riemannian optimization for multi-scale diffeomorphic matching.

Nature communications·2026

Same author

Evaluation of a PET Insert for Trimodal Imaging: A Step Toward PET/MRI-Guided Focused Ultrasound.

IEEE transactions on radiation and plasma medical sciences·2026

Same author

Highly replicable multisite patterns of adolescent white matter maturation.

bioRxiv : the preprint server for biology·2026

Same author

Case 1-2026: A 50-Year-Old Woman with Fever and Abdominal Pain.

The New England journal of medicine·2026

Same author

A Reference Atlas of the Human Dorsal Root Ganglion.

bioRxiv : the preprint server for biology·2025

Same author

The ANTsX ecosystem for mapping the mouse brain.

Nature communications·2025

Same journal

Complex Indel Detection: A Simulation-Based Framework and Parsing with FreeBayes.

bioRxiv : the preprint server for biology·2026

Same journal

Emulating the gingival-tooth interface during bacterial, fungal, and viral infection in a microphysiological model of the human oral cavity.

bioRxiv : the preprint server for biology·2026

Same journal

Local SNP-explained methylation variation reveals genetically anchored and exposure-associated methylation architecture in the human brain.

bioRxiv : the preprint server for biology·2026

Same journal

Perinatal Semaglutide Treatment Improves Maternal Health and Mitigates Offspring Metabolic Dysfunction in a Mouse Model of Maternal Obesity.

bioRxiv : the preprint server for biology·2026

Same journal

Pervasive cryptic selection in the human noncoding genome.

bioRxiv : the preprint server for biology·2026

Same journal

Secreted ORF8 reprograms macrophages to enhance SARS-CoV-2 infection of lung epithelial cells.

bioRxiv : the preprint server for biology·2026

See all related articles

Related Experiment Video

Swin-PSAxialNet: An Efficient Multi-Organ Segmentation Technique

Swin-PSAxialNet: An Efficient Multi-Organ Segmentation Technique

Published on: July 5, 2024

Deep Computational Anatomy via Latent-Aligned Multiview Normalizing Flows.

Nicholas J Tustison¹, Brian B Avants¹, Philip A Cook²

¹Department of Radiology and Medical Imaging, University of Virginia, Charlottesville, VA.

Biorxiv : the Preprint Server for Biology

|May 18, 2026

View abstract on PubMed

Summary

This summary is machine-generated.

Latent-aligned multiview normalizing flows learn shared features across diverse datasets by mapping data into a continuous space. This framework enables novel deep learning interpretations in computational anatomy and exact cross-view data imputation.

Related Experiment Videos

Swin-PSAxialNet: An Efficient Multi-Organ Segmentation Technique

Swin-PSAxialNet: An Efficient Multi-Organ Segmentation Technique

Published on: July 5, 2024

Area of Science:

Computational anatomy
Machine learning
Medical imaging analysis

Background:

Normalizing flows model complex probability distributions with exact likelihoods.
Existing methods struggle with heterogeneous, multimodal datasets.
Learning shared latent spaces is crucial for cross-modal data analysis.

Purpose of the Study:

Introduce latent-aligned multiview normalizing (LAMNr) flows for multimodal data.
Develop a framework for deep learning interpretations in computational anatomy.
Enable exact cross-view imputation and latent space manipulation.

Main Methods:

Utilize normalizing flows for bijective data mapping.
Employ formal latent-alignment constraints to separate shared and view-specific features.
Integrate with the ANTsX ecosystem (ANTsTorch) for PyTorch implementation.

Main Results:

Demonstrated the framework's efficacy on imaging-derived phenotypes and multimodal MRI.
Showcased potential for deep learning interpretations of computational anatomy concepts.
Enabled closed-form conditional modeling for exact cross-view imputation.

Conclusions:

LAMNr flows offer a powerful approach for multimodal data analysis.
The framework provides a foundation for novel computational anatomy deep learning models.
Open-source implementation facilitates further research and application in medical imaging.