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

Effect of Increased Inoculum Size on Drug Susceptibility of Mycobacterium tuberculosis: Challenges in Reliable Drug Resistance Detection.

MicrobiologyOpen·2026
Same author

A Novel ConvNeXtV2-MIL Approach for Accurate and Efficient Classification of Microscopic Fungal Morphology.

Journal of imaging informatics in medicine·2026
Same author

DiagPat: An Explainable Language Detection Model Using EEG Signals.

Sensors (Basel, Switzerland)·2026
Same author

A novel and accurate EEG emotion classification model based on multiple attention local binary patterns.

BMC medicine·2026
Same author

Different pattern: a new EEG-based method for mental performance detection.

BMC medical informatics and decision making·2026
Same author

PyramidPat explainable feature engineering for multiclass electroencephalography psychiatric disorders: Explainable feature engineering and classification.

Psychiatry research·2026

Related Experiment Video

Updated: Jul 31, 2025

Automation of the Micronucleus Assay Using Imaging Flow Cytometry and Artificial Intelligence
09:11

Automation of the Micronucleus Assay Using Imaging Flow Cytometry and Artificial Intelligence

Published on: January 27, 2023

2.2K

Automated Urine Cell Image Classification Model Using Chaotic Mixer Deep Feature Extraction.

Mehmet Erten1, Ilknur Tuncer2, Prabal D Barua3,4,5,6,7,8,9,10,11

  • 1Department of Medical Biochemistry, Malatya Training and Research Hospital, Malatya, Türkiye.

Journal of Digital Imaging
|May 2, 2023
PubMed
Summary

A new AI model uses an Arnold Cat Map mixer and DenseNet201 for automated urinary sediment analysis. This deep learning approach achieves high accuracy, reducing costs and analysis time for microscopic urine examinations.

Keywords:
Biomedical image classificationChaotic mixer deep feature extractionFeature engineeringImage classificationUrine analysisUrine cell classificationUrine sediment

More Related Videos

Author Spotlight: Enhancing PSC-to-Functional Cell Differentiation Using ML Models Based on Live-Cell Bright-Field Imaging
11:38

Author Spotlight: Enhancing PSC-to-Functional Cell Differentiation Using ML Models Based on Live-Cell Bright-Field Imaging

Published on: October 4, 2024

641
Author Spotlight: Enhancement of Salient Object Detection for Smart Grid Applications
03:31

Author Spotlight: Enhancement of Salient Object Detection for Smart Grid Applications

Published on: December 15, 2023

591

Related Experiment Videos

Last Updated: Jul 31, 2025

Automation of the Micronucleus Assay Using Imaging Flow Cytometry and Artificial Intelligence
09:11

Automation of the Micronucleus Assay Using Imaging Flow Cytometry and Artificial Intelligence

Published on: January 27, 2023

2.2K
Author Spotlight: Enhancing PSC-to-Functional Cell Differentiation Using ML Models Based on Live-Cell Bright-Field Imaging
11:38

Author Spotlight: Enhancing PSC-to-Functional Cell Differentiation Using ML Models Based on Live-Cell Bright-Field Imaging

Published on: October 4, 2024

641
Author Spotlight: Enhancement of Salient Object Detection for Smart Grid Applications
03:31

Author Spotlight: Enhancement of Salient Object Detection for Smart Grid Applications

Published on: December 15, 2023

591

Area of Science:

  • Medical Diagnostics
  • Computer Vision
  • Artificial Intelligence

Background:

  • Microscopic examination of urinary sediments is a standard diagnostic procedure.
  • Automated classification systems offer potential for reduced analysis time and cost-efficiency.

Purpose of the Study:

  • To develop and evaluate an accurate, computationally lightweight image classification model for automated urinary sediment analysis.
  • To combine cryptographic mixing protocols with computer vision techniques for enhanced feature extraction.

Main Methods:

  • A novel image classification model integrating an Arnold Cat Map (ACM)-based mixer with fixed-size patch processing and DenseNet201 transfer learning.
  • Feature extraction involved concatenating raw and ACM-mixed image features, followed by iterative neighborhood component analysis for dimensionality reduction.
  • Classification was performed using a shallow k-nearest neighbor (kNN) classifier with ten-fold cross-validation on a dataset of 6,687 urinary sediment images across seven classes.

Main Results:

  • The developed model achieved an overall accuracy of 98.52% for the seven-class classification of urinary sediments.
  • The ACM-based mixer algorithm effectively enhanced deep feature engineering when combined with DenseNet201.
  • The model demonstrated superior performance compared to existing published models for urinary cell and sediment analysis.

Conclusions:

  • The proposed deep learning model, utilizing an ACM-based mixer and DenseNet201, is accurate and computationally efficient for automated urine sediment analysis.
  • This approach shows significant potential for real-world clinical applications, improving the speed and reliability of microscopic urine examinations.