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

Peptide molecular lock-engineered nanobodies enable an oriented dual-modal immunoassay for reliable detection of Cronobacter sakazakii.

Food chemistry·2026
Same author

Turning Motion into Methane: Electromagnetic Induction in Microbial Aggregates Enhances Wastewater Resource Recovery.

Environmental science & technology·2026
Same author

Reverse Tesla valve modulated efficient water evaporation and cooling.

Nature communications·2026
Same author

Genome-wide identification and expression analysis of the Glutathione S-transferase (GST) gene family in Avicennia marina under salt and auxin stress.

BMC plant biology·2026
Same author

Modeling Hereditary Angioedema With Personalized EPSC-Derived Hepatocytes: A CRISPR-Validated Platform for Mutation-Specific Mechanisms and Therapeutic Innovation.

Allergy·2026
Same author

Porcine Parvovirus virus-like particle vaccine induces long-term humoral immunity by recruiting T follicular helper and germinal center B cell responses.

Frontiers in immunology·2026

Related Experiment Video

Updated: Aug 9, 2025

Anti-Nuclear Antibody Screening Using HEp-2 Cells
13:01

Anti-Nuclear Antibody Screening Using HEp-2 Cells

Published on: June 23, 2014

135.0K

Automatic Segmentation and Classification for Antinuclear Antibody Images Based on Deep Learning.

Qinghua Xie1, Pengyu Chen2, Zhaohuan Li1

  • 1The Affiliated Changsha Central Hospital, Hengyang Medical School, University of South China, Changsha, Hunan, China.

Computational Intelligence and Neuroscience
|February 23, 2023
PubMed
Summary

This study introduces an AI framework for automatic segmentation and classification of antinuclear antibody (ANA) images, improving diagnostic accuracy for autoimmune diseases. The AI approach significantly outperforms traditional methods in classifying these crucial diagnostic images.

More Related Videos

Supervised Machine Learning for Semi-Quantification of Extracellular DNA in Glomerulonephritis
09:16

Supervised Machine Learning for Semi-Quantification of Extracellular DNA in Glomerulonephritis

Published on: June 18, 2020

6.9K
Deep Learning-Based Segmentation of Cryo-Electron Tomograms
10:25

Deep Learning-Based Segmentation of Cryo-Electron Tomograms

Published on: November 11, 2022

9.1K

Related Experiment Videos

Last Updated: Aug 9, 2025

Anti-Nuclear Antibody Screening Using HEp-2 Cells
13:01

Anti-Nuclear Antibody Screening Using HEp-2 Cells

Published on: June 23, 2014

135.0K
Supervised Machine Learning for Semi-Quantification of Extracellular DNA in Glomerulonephritis
09:16

Supervised Machine Learning for Semi-Quantification of Extracellular DNA in Glomerulonephritis

Published on: June 18, 2020

6.9K
Deep Learning-Based Segmentation of Cryo-Electron Tomograms
10:25

Deep Learning-Based Segmentation of Cryo-Electron Tomograms

Published on: November 11, 2022

9.1K

Area of Science:

  • Medical diagnostics
  • Artificial Intelligence in Medicine
  • Immunology

Background:

  • Antinuclear antibodies (ANAs) are key serological markers for autoimmune diseases.
  • Indirect immunofluorescence (IIF) on HEp-2 cells is the standard ANA testing method.
  • IIF testing faces challenges due to high variability and subjectivity, necessitating automated solutions.

Purpose of the Study:

  • To develop an automated artificial intelligence (AI) framework for segmenting and classifying antinuclear antibody (ANA) images.
  • To enhance the efficiency and objectivity of ANA testing for autoimmune disease diagnosis.
  • To compare the performance of traditional machine learning and deep learning models for ANA image analysis.

Main Methods:

  • Image segmentation using Otsu thresholding and watershed algorithms.
  • Extraction of texture features including SIFT, LBP, CoALBP, and RIC-LBP.
  • Classification using traditional machine learning (SVM, KNN, RF) and an ensemble classifier (ECLF).
  • Deep learning classification using the InceptionResNetV2 model.

Main Results:

  • The ensemble classifier (ECLF) combined with SIFT and RIC-LBP features achieved high accuracy (0.9269 on Changsha, 0.9635 on ICPR 2016 datasets).
  • The InceptionResNetV2 deep learning model demonstrated superior performance, reaching accuracies of 0.9465 (Changsha) and 0.9836 (ICPR 2016).
  • Both AI approaches significantly outperformed other tested schemes in ANA image classification.

Conclusions:

  • The developed AI framework offers an efficient and objective method for ANA image analysis.
  • Deep learning models, particularly InceptionResNetV2, show great promise for improving the accuracy of autoimmune disease diagnosis through ANA testing.
  • Automated AI-driven analysis can overcome the limitations of manual interpretation in IIF-based ANA screening.