Jove
Visualize
Contact Us
JoVE
x logofacebook logolinkedin logoyoutube logo
ABOUT JoVE
OverviewLeadershipBlogJoVE Help Center
AUTHORS
Publishing ProcessEditorial BoardScope & PoliciesPeer ReviewFAQSubmit
LIBRARIANS
TestimonialsSubscriptionsAccessResourcesLibrary Advisory BoardFAQ
RESEARCH
JoVE JournalMethods CollectionsJoVE Encyclopedia of ExperimentsArchive
EDUCATION
JoVE CoreJoVE BusinessJoVE Science EducationJoVE Lab ManualFaculty Resource CenterFaculty Site
Terms & Conditions of Use
Privacy Policy
Policies

Related Concept Videos

You might also read

Related Articles

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

Sort by
Same author

YBX1 phase separation promotes radioresistance in lung adenocarcinoma by suppressing ferroptosis through GPX4 regulation.

Cellular signalling·2026
Same author

NIARE: Noise-Induced Analysis for Model Robustness Evaluation in Asthma Phenotype Classification.

IEEE journal of biomedical and health informatics·2026
Same author

Anthocyanin biosynthesis in blueberry is regulated by light and abscisic acid signaling via a VcABF2-miR156-VcSPL9 feedback loop.

The New phytologist·2026
Same author

Breaking self-incompatibility for diploid hybrid potato breeding: advances, mechanisms, and emerging technologies.

Frontiers in plant science·2026
Same author

Genome-wide identification and functional characterization of drought-responsive U-box E3 ubiquitin ligase genes in Rosa chinensis.

International journal of biological macromolecules·2026
Same author

Topologically Structured PLLA Fibers With Stress Concentration Effects for Health Monitoring.

Advanced science (Weinheim, Baden-Wurttemberg, Germany)·2026

Related Experiment Video

Updated: Sep 2, 2025

Profiling Maternal Behavior Responses During Whole-Brain Imaging
07:12

Profiling Maternal Behavior Responses During Whole-Brain Imaging

Published on: January 24, 2025

1.0K

A Convolutional Neural Network Pipeline For Multi-Temporal Retinal Image Registration.

Chi-Jui Ho1, Yiqian Wang1, Junkang Zhang1

  • 1Department of Electrical and Computer Engineering, UC San Diego, La Jolla, USA.

International Soc Design Conference. International Soc Design Conference
|August 11, 2022
PubMed
Summary

This study introduces a novel convolutional neural network pipeline for accurate retinal image registration. The method effectively aligns multi-temporal sequences, even with severe deformation, aiding medical diagnosis.

Keywords:
CNNImage temporal registrationretinal imaging

More Related Videos

A Pipeline for 3D Multimodality Image Integration and Computer-assisted Planning in Epilepsy Surgery
09:41

A Pipeline for 3D Multimodality Image Integration and Computer-assisted Planning in Epilepsy Surgery

Published on: May 20, 2016

12.4K
Time-Lapse Imaging of Neuronal Arborization using Sparse Adeno-Associated Virus Labeling of Genetically Targeted Retinal Cell Populations
13:13

Time-Lapse Imaging of Neuronal Arborization using Sparse Adeno-Associated Virus Labeling of Genetically Targeted Retinal Cell Populations

Published on: March 19, 2021

3.0K

Related Experiment Videos

Last Updated: Sep 2, 2025

Profiling Maternal Behavior Responses During Whole-Brain Imaging
07:12

Profiling Maternal Behavior Responses During Whole-Brain Imaging

Published on: January 24, 2025

1.0K
A Pipeline for 3D Multimodality Image Integration and Computer-assisted Planning in Epilepsy Surgery
09:41

A Pipeline for 3D Multimodality Image Integration and Computer-assisted Planning in Epilepsy Surgery

Published on: May 20, 2016

12.4K
Time-Lapse Imaging of Neuronal Arborization using Sparse Adeno-Associated Virus Labeling of Genetically Targeted Retinal Cell Populations
13:13

Time-Lapse Imaging of Neuronal Arborization using Sparse Adeno-Associated Virus Labeling of Genetically Targeted Retinal Cell Populations

Published on: March 19, 2021

3.0K

Area of Science:

  • Medical Imaging
  • Computer Vision
  • Artificial Intelligence

Background:

  • Medical diagnosis often relies on sequential image analysis to track health status over time.
  • Analyzing multi-temporal image sequences, particularly retinal images, is challenging due to severe deformation, hindering accurate pattern matching.

Purpose of the Study:

  • To develop an automated and robust method for aligning multi-temporal retinal image sequences.
  • To address the limitations of manual pattern matching in deformed medical images.

Main Methods:

  • A coarse-to-fine registration pipeline utilizing a convolutional neural network was proposed.
  • The pipeline integrates feature matching, outlier rejection, and local registration for deformation recovery.
  • The network was designed to handle significant geometric transformations and variations in image quality.

Main Results:

  • The proposed convolutional neural network pipeline demonstrated robust performance in registering retinal images with severe deformation.
  • The method effectively aligned multi-temporal image sequences, overcoming challenges related to illumination and contrast variations.
  • Accurate alignment facilitated the identification of changes in image patterns over time.

Conclusions:

  • The developed registration pipeline offers a significant advancement for analyzing longitudinal medical image data.
  • This approach enhances the efficiency and accuracy of medical diagnosis by enabling reliable visual analysis of image changes.
  • The technique shows promise for improving the monitoring of health status through medical imaging.