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

Urinary Tract Infection III: Diagnostic Studies and Interprofessional Care01:30

Urinary Tract Infection III: Diagnostic Studies and Interprofessional Care

440
A healthcare provider can diagnose a urinary tract infection (UTI) through several methods:Medical History and Symptoms: The provider will take a detailed medical history and ask about symptoms such as frequent urination, burning sensation during urination, and lower abdominal pain.Urinalysis: A clean-catch urine sample is collected in a sterile container and tested for the presence of bacteria, white blood cells (leukocytes), nitrites, blood, and protein. The presence of leukocytes and...
440

You might also read

Related Articles

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

Sort by
Same author

The value-based score in laboratory medicine: results of a European pilot study.

Clinical chemistry and laboratory medicine·2026
Same author

Urinary <i>PENK</i> DNA methylation for bladder cancer diagnosis: methodological rigor, interpretive boundaries, and the evidence required for clinical translation.

Translational andrology and urology·2026
Same author

Clinical AI is Not (Yet) Trustworthy-But It Could Be.

Journal of medical Internet research·2026
Same author

Medication, Vaccine, and Folic Acid Use Among Pregnant Women in Belgium: Insights from the BELpREG Cohort.

Pharmacoepidemiology and drug safety·2026
Same author

Reliability of Self-Reported Maternal Health and Mother-Infant Outcome Data in Web-Based Questionnaires.

Drug safety·2026
Same author

Automated high-throughput quantification of plasma p-tau217 and APOE-ε4 for Alzheimer's disease diagnosis and cognitive decline in a memory cohort.

Alzheimer's research & therapy·2026

Related Experiment Video

Updated: May 5, 2026

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

7.3K

Towards Clinical Integration of Deep Learning-Based Classification of Urinary Sediment Particles from Digital

Stylianos G Mouslech1, Sven Wijnants2, Anne-Lisanne van der Schagt2

  • 1STADIUS Center for Dynamical Systems, Signal Processing and Data Analytics-Department of Electrical Engineering (ESAT), KU Leuven, Leuven, Belgium.

Clinical Chemistry
|January 7, 2026
PubMed
Summary

A new deep learning model accurately classifies urine particles from digital microscopy images, offering a faster and more reliable alternative to manual urinalysis. Further validation is needed for optimal clinical integration.

More Related Videos

Application of Deep Learning-Based Medical Image Segmentation via Orbital Computed Tomography
04:48

Application of Deep Learning-Based Medical Image Segmentation via Orbital Computed Tomography

Published on: November 30, 2022

3.3K
Introduction of an Integrated Pathology Image Management, Artificial Intelligence, and Reporting System
05:33

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

Published on: July 11, 2025

786

Related Experiment Videos

Last Updated: May 5, 2026

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

7.3K
Application of Deep Learning-Based Medical Image Segmentation via Orbital Computed Tomography
04:48

Application of Deep Learning-Based Medical Image Segmentation via Orbital Computed Tomography

Published on: November 30, 2022

3.3K
Introduction of an Integrated Pathology Image Management, Artificial Intelligence, and Reporting System
05:33

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

Published on: July 11, 2025

786

Area of Science:

  • Medical diagnostics
  • Artificial intelligence in healthcare
  • Computational pathology

Background:

  • Urinalysis, a key clinical test, involves manual microscopic examination of urine sediment, which is laborious and prone to errors.
  • Automated analysis using digital microscopy and deep learning offers a promising solution to improve efficiency and accuracy.
  • This study investigates the clinical utility of a deep learning model for automated urine sediment classification.

Purpose of the Study:

  • To develop and evaluate a deep learning model for the automatic classification of urinary sediment elements.
  • To assess the model's performance, robustness, and interpretability in a clinical laboratory setting.
  • To provide insights for the reliable clinical application of automated urinalysis.

Main Methods:

  • An EfficientNet-based deep learning model was trained on a dataset of 13 classes of urinary sediment elements from digital microscopy images.
  • Model performance was evaluated across different data collection strategies, including uncertainty calibration and interpretability analyses (Grad-CAM, t-SNE).
  • A graphical user interface was developed for prospective validation in a clinical laboratory environment.

Main Results:

  • The deep learning model achieved approximately 97% overall accuracy on the test set, demonstrating high performance in classifying urine particles.
  • Interpretability analyses confirmed the model focused on relevant image regions and learned distinct feature embeddings for different classes.
  • Prospective evaluation showed top 1 and top 3 accuracies of approximately 78% and 92%, respectively, highlighting the need for further refinement.

Conclusions:

  • A lightweight deep learning model demonstrates high potential for accurate urine particle classification.
  • Discrepancies between retrospective and prospective evaluations underscore the importance of data variability and provide crucial insights for clinical implementation.
  • Automated urinalysis using deep learning can enhance diagnostic efficiency and accuracy in clinical laboratories.