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

Related Concept Videos

Improving Translational Accuracy

Improving Translational Accuracy

Base complementarity between the three base pairs of mRNA codon and the tRNA anticodon is not a failsafe mechanism. Inaccuracies can range from a single mismatch to no correct base pairing at all. The free energy difference between the correct and nearly correct base pairs can be as small as 3 kcal/ mol. With complementarity being the only proofreading step, the estimated error frequency would be one wrong amino acid in every 100 amino acids incorporated. However, error frequencies observed in...

You might also read

Related Articles

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

Sort by

Same author

Prognostic value of eight immune gene signatures in pancreatic cancer patients.

BMC medical genomics·2021

Same author

PPD: A Manually Curated Database for Experimentally Verified Prokaryotic Promoters.

Journal of molecular biology·2021

Same author

Generation of an induced pluripotent stem cell line from a Chinese Han infant with floating-harbor syndrome accompanied with dilated cardiomyopathy.

Stem cell research·2021

Same author

Identification of Key Histone Modifications and Their Regulatory Regions on Gene Expression Level Changes in Chronic Myelogenous Leukemia.

Frontiers in cell and developmental biology·2021

Same author

DM3Loc: multi-label mRNA subcellular localization prediction and analysis based on multi-head self-attention mechanism.

Nucleic acids research·2021

Same author

Label-free exonuclease I-assisted signal amplification colorimetric sensor for highly sensitive detection of kanamycin.

Food chemistry·2021

Search research articles

Related Experiment Video

Updated: May 27, 2025

Brain Infarct Segmentation and Registration on MRI or CT for Lesion-symptom Mapping

Brain Infarct Segmentation and Registration on MRI or CT for Lesion-symptom Mapping

Published on: September 25, 2019

Boosting 2D brain image registration via priors from large model.

Hao Lin¹, Yonghong Song¹

¹School of Software, Xi 'an Jiaotong University, Xi'an City, Shanxi Province, China.

Medical Physics

|February 20, 2025

Summary

Foundational models like DINOv2 enhance deformable medical image registration by improving accuracy and generalization. This approach overcomes data limitations and overfitting in deep learning models for better medical image analysis.

Keywords:

DINOv2 cross‐attention image registration unsupervised

More Related Videos

Author Spotlight: An Efficient and Robust Software for Automated Fusion of Multiple Preclinical Imaging Modalities

Author Spotlight: An Efficient and Robust Software for Automated Fusion of Multiple Preclinical Imaging Modalities

Published on: October 27, 2023

Multi-modal Pulmonary Imaging: Using Complementary Information from CT and Hyperpolarized 129Xe MRI to Evaluate Lung Structure-Function

Multi-modal Pulmonary Imaging: Using Complementary Information from CT and Hyperpolarized 129Xe MRI to Evaluate Lung Structure-Function

Published on: April 12, 2024

Related Experiment Videos

Last Updated: May 27, 2025

Brain Infarct Segmentation and Registration on MRI or CT for Lesion-symptom Mapping

Brain Infarct Segmentation and Registration on MRI or CT for Lesion-symptom Mapping

Published on: September 25, 2019

Author Spotlight: An Efficient and Robust Software for Automated Fusion of Multiple Preclinical Imaging Modalities

Author Spotlight: An Efficient and Robust Software for Automated Fusion of Multiple Preclinical Imaging Modalities

Published on: October 27, 2023

Multi-modal Pulmonary Imaging: Using Complementary Information from CT and Hyperpolarized 129Xe MRI to Evaluate Lung Structure-Function

Multi-modal Pulmonary Imaging: Using Complementary Information from CT and Hyperpolarized 129Xe MRI to Evaluate Lung Structure-Function

Published on: April 12, 2024

Area of Science:

Medical image analysis
Computer vision
Deep learning

Background:

Deformable medical image registration aligns images with local differences, crucial for accurate medical analysis and diagnostics.
Deep learning has improved registration speed and accuracy but is limited by small datasets, leading to overfitting and poor generalization.

Purpose of the Study:

To leverage foundational models, specifically DINOv2, to enhance deep learning-based unsupervised deformable image registration.
To overcome limitations of small datasets and improve accuracy and generalization in registration models.

Main Methods:

Explored DINOv2's prior knowledge to support unsupervised registration networks.
Investigated three DINOv2-assisted registration architectures: direct, enhanced, and refined.
Studied three feature aggregation methods: convolutional interaction, direct fusion, and cross-attention.

Main Results:

Enhanced and refined DINOv2-assisted architectures significantly improved registration accuracy.
Demonstrated reduced data dependency and maintained strong generalization capabilities on public datasets (IXI, OASIS).

Conclusions:

Introduced novel methods for applying foundational models to deformable image registration.
Showcased the potential of DINOv2 to advance unsupervised learning-based medical image registration.