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

Age-stratified associations of glycemia, blood pressure, and cholesterol with mortality in diabetes: A prospective cohort study.

BMC medicine·2026
Same author

An Annotated Corneal Confocal Microscopy Dataset for Nerve Segmentation and Clinical Characterization.

Scientific data·2026
Same author

Age-specific effects of hemoglobin A1c, blood pressure, and cholesterol levels on incident cardiovascular diseases among adults with diabetes in China: a 10-year prospective cohort study.

Life metabolism·2026
Same author

Association Between Socioeconomic Status and the Prevalence of Metabolic Diseases: A Nationwide Cross-Sectional Study in China.

Journal of diabetes·2026
Same author

Diabetic peripheral neuropathy identification using enface optical coherence tomography and multi-head attention deep learning algorithm.

Digital health·2026
Same author

Ancestry-specific genetics of amino acids and microbiota-related metabolites reveal causal effects on cardiometabolic disease in Chinese populations.

Cardiovascular diabetology·2026

Related Experiment Video

Updated: Sep 15, 2025

Corneal Confocal Microscopy: A Novel Non-invasive Technique to Quantify Small Fibre Pathology in Peripheral Neuropathies
11:29

Corneal Confocal Microscopy: A Novel Non-invasive Technique to Quantify Small Fibre Pathology in Peripheral Neuropathies

Published on: January 3, 2011

26.8K

ConNeCT: weakly supervised corneal confocal microscopy image inpainting network based on a diffusion model.

Qincheng Qiao1,2, Xinguo Hou1,2,3,4,5

  • 1Department of Endocrinology and Metabolism, Qilu Hospital, Shandong University, Jinan 250012, China.

Biomedical Optics Express
|July 18, 2025
PubMed
Summary
This summary is machine-generated.

We developed ConNeCT, a novel deep learning method for restoring artifact-laden corneal confocal microscopy (CCM) images. This technique improves neurodegenerative disease diagnosis by enhancing nerve morphology analysis in CCM scans.

More Related Videos

Sample Drift Correction Following 4D Confocal Time-lapse Imaging
10:04

Sample Drift Correction Following 4D Confocal Time-lapse Imaging

Published on: April 12, 2014

16.6K
Measuring the Shape and Size of Activated Sludge Particles Immobilized in Agar with an Open Source Software Pipeline
09:27

Measuring the Shape and Size of Activated Sludge Particles Immobilized in Agar with an Open Source Software Pipeline

Published on: January 30, 2019

7.2K

Related Experiment Videos

Last Updated: Sep 15, 2025

Corneal Confocal Microscopy: A Novel Non-invasive Technique to Quantify Small Fibre Pathology in Peripheral Neuropathies
11:29

Corneal Confocal Microscopy: A Novel Non-invasive Technique to Quantify Small Fibre Pathology in Peripheral Neuropathies

Published on: January 3, 2011

26.8K
Sample Drift Correction Following 4D Confocal Time-lapse Imaging
10:04

Sample Drift Correction Following 4D Confocal Time-lapse Imaging

Published on: April 12, 2014

16.6K
Measuring the Shape and Size of Activated Sludge Particles Immobilized in Agar with an Open Source Software Pipeline
09:27

Measuring the Shape and Size of Activated Sludge Particles Immobilized in Agar with an Open Source Software Pipeline

Published on: January 30, 2019

7.2K

Area of Science:

  • Ophthalmology
  • Medical Imaging
  • Neuroscience

Background:

  • Corneal confocal microscopy (CCM) enables quantitative analysis of corneal nerve morphology for diagnosing neurodegenerative diseases.
  • Artifacts in CCM images hinder accurate parameter measurements and diagnostic potential.

Purpose of the Study:

  • To introduce ConNeCT, a weakly supervised image inpainting network for artifact removal in CCM images.
  • To enhance the accuracy of corneal nerve morphology analysis for improved disease diagnosis.

Main Methods:

  • ConNeCT utilizes a guided diffusion model (DDPM) with deformable convolutions and a U-Net segmentation model.
  • An improved DDPM resampling algorithm reconstructs images by leveraging artifact-free regions and gradient signals.
  • The framework performs end-to-end image restoration from raw artifact-laden images and user-provided masks.

Main Results:

  • ConNeCT achieved state-of-the-art performance, outperforming existing methods on a manually annotated dataset.
  • Quantitative evaluation showed high accuracy with SSIM=0.9838, PSNR=17.68, HD=13.74, MSD=6.30, and MAE=14.80.
  • The method effectively preserved nerve fiber structures during image reconstruction.

Conclusions:

  • ConNeCT is the first deep learning-based method specifically designed for CCM image inpainting.
  • The proposed framework significantly improves the quality of CCM images, aiding in the diagnosis of neurodegenerative diseases.
  • This work advances quantitative analysis of corneal nerve morphology for clinical applications.