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

Machine learning approach to analyzing complex care coordination patterns for medically complex children.

BMC medical informatics and decision making·2026
Same author

Personalized exercise therapy during targeted drug therapy tapering in patients with rheumatoid arthritis: a pilot randomized controlled trial.

BMC rheumatology·2026
Same author

Newborn Screening and Early Cord Blood Transplant for Mucopolysaccharidosis.

JAMA network open·2026
Same author

Automated detection of mulberry bodies in urinary sediment for non-invasive Fabry disease screening.

Clinical chemistry and laboratory medicine·2026
Same author

Vaginal microbiota composition in pregnant women following cervical conization and radical trachelectomy.

Scientific reports·2026
Same author

Quantification of glycosaminoglycans in dried blood spots, and evaluation of its usefulness as a secondary newborn screening test for mucopolysaccharidoses.

Biochemistry and biophysics reports·2026

Related Experiment Video

Updated: Aug 26, 2025

Introduction of an Integrated Pathology Image Management, Artificial Intelligence, and Reporting System
05:30

Introduction of an Integrated Pathology Image Management, Artificial Intelligence, and Reporting System

Published on: July 11, 2025

193

Automated urinary sediment detection for Fabry disease using deep-learning algorithms.

Hidetaka Uryu1,2, Ohsuke Migita3,4,5, Minami Ozawa5

  • 1Medical Genome Center, National Research Institute for Child Health and Development, Tokyo 157-8535, Japan.

Molecular Genetics and Metabolism Reports
|October 3, 2022
PubMed
Summary

Early diagnosis of Fabry disease is crucial. A novel artificial intelligence (AI) model using an image amplification technique can detect Fabry disease from urine samples, improving early intervention for this rare condition.

Keywords:
AI, artificial intelligenceAUC, area under the curveAdHE, adaptive histogram equalizationArtificial intelligenceCNN, convolutional neural networkCntStr, contrast stretchingDeep learningERT, enzyme replacement therapyFabry diseaseImage augmentationInceptResNet, InceptionResNetV2Mulberry cellsOrdHE, ordinary histogram equalizationROC, receiver operating characteristicXcep, Xceptionalpha-Gal A, α- galactosidase A

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
Estimation of Urinary Nanocrystals in Humans using Calcium Fluorophore Labeling and Nanoparticle Tracking Analysis
07:45

Estimation of Urinary Nanocrystals in Humans using Calcium Fluorophore Labeling and Nanoparticle Tracking Analysis

Published on: February 9, 2021

3.7K

Related Experiment Videos

Last Updated: Aug 26, 2025

Introduction of an Integrated Pathology Image Management, Artificial Intelligence, and Reporting System
05:30

Introduction of an Integrated Pathology Image Management, Artificial Intelligence, and Reporting System

Published on: July 11, 2025

193
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
Estimation of Urinary Nanocrystals in Humans using Calcium Fluorophore Labeling and Nanoparticle Tracking Analysis
07:45

Estimation of Urinary Nanocrystals in Humans using Calcium Fluorophore Labeling and Nanoparticle Tracking Analysis

Published on: February 9, 2021

3.7K

Area of Science:

  • Medical Diagnostics
  • Artificial Intelligence in Medicine
  • Rare Disease Research

Background:

  • Fabry disease is a rare, congenital lysosomal storage disorder leading to organ damage.
  • Delayed diagnosis of Fabry disease hinders timely intervention and treatment, despite available therapies.
  • Current diagnostic challenges include low disease recognition and infrequent specific screening tests.

Purpose of the Study:

  • To develop a novel artificial intelligence (AI) based decision support system for early Fabry disease detection.
  • To overcome data limitations in AI for rare diseases using an innovative image amplification method.
  • To enable early intervention by integrating AI detection into widely practiced clinical tests.

Main Methods:

  • A deep neural-network model was constructed using a novel image amplification technique to generate training data.
  • The AI model was trained to detect Fabry disease cases from urine samples.
  • Model performance was evaluated on a validation dataset for sensitivity, specificity, and AUC.

Main Results:

  • The AI model achieved high performance with a sensitivity of 0.902, specificity of 0.977, and AUC of 0.968.
  • The model identified disease-specific findings interpretable by human experts.
  • This represents the first AI-based system for detecting undiagnosed Fabry disease.

Conclusions:

  • The developed AI model, utilizing an image amplification method, shows significant potential for diagnosing Fabry disease.
  • This approach offers a viable strategy for applying AI to rare diseases with limited datasets.
  • The novel image amplification technique can advance AI model development for other rare disorders.