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

AI-Driven Design and Comparative Evaluation of SNEDDS for the Optimized Nanoencapsulation of Phytoextracts.

Nanomaterials (Basel, Switzerland)·2026
Same author

A modern radiologist's guide to artificial intelligence.

Pediatric radiology·2026
Same author

From Bench to Greenhouse: The Comparative Nano-Bio System Effects of Green-Synthesized TiO<sub>2</sub>-NPs and Plant-Growth-Promoting Microorganisms in <i>Capsicum annuum</i>.

Plants (Basel, Switzerland)·2025
Same author

From sonochemical synthesis to predictive modeling: Unraveling the antioxidant properties of La-doped CeO<sub>2</sub> nanoparticles.

Ultrasonics sonochemistry·2025
Same author

Using machine learning to predict clinical remission with exclusive enteral nutrition in pediatric Crohn disease.

Journal of pediatric gastroenterology and nutrition·2025
Same author

Optimizing machine learning models for cytotoxicity prediction in lanthanide-doped nanomaterials: A data-driven approach for minimizing environmental hazards.

Journal of hazardous materials·2025

Related Experiment Video

Updated: Apr 18, 2026

Time-Lapse Imaging of Neuronal Arborization using Sparse Adeno-Associated Virus Labeling of Genetically Targeted Retinal Cell Populations
13:13

Time-Lapse Imaging of Neuronal Arborization using Sparse Adeno-Associated Virus Labeling of Genetically Targeted Retinal Cell Populations

Published on: March 19, 2021

3.4K

Retinal vessel extraction using Lattice Neural Networks with Dendritic Processing.

Roberto Vega1, Gildardo Sanchez-Ante1, Luis E Falcon-Morales1

  • 1Tecnológico de Monterrey, Campus Guadalajara, Computer Science Department, Av. Gral Ramon Corona 2514, Zapopan, Jal, Mexico.

Computers in Biology and Medicine
|January 16, 2015
PubMed
Summary

A new Lattice Neural Network with Dendritic Processing (LNNDP) method improves automated retinal image classification for chronic disease detection. This advanced system outperforms existing methods like Support Vector Machines (SVM) and Multilayer Perceptrons (MLP).

Keywords:
Blood vessel segmentationDendritic processingDiabetic retinopathyMachine visionNeural networksPattern recognition

More Related Videos

Computational Modeling of Retinal Neurons for Visual Prosthesis Research - Fundamental Approaches
10:50

Computational Modeling of Retinal Neurons for Visual Prosthesis Research - Fundamental Approaches

Published on: June 21, 2022

2.3K
Assessment of Vascular Regeneration in the CNS Using the Mouse Retina
07:32

Assessment of Vascular Regeneration in the CNS Using the Mouse Retina

Published on: June 23, 2014

15.0K

Related Experiment Videos

Last Updated: Apr 18, 2026

Time-Lapse Imaging of Neuronal Arborization using Sparse Adeno-Associated Virus Labeling of Genetically Targeted Retinal Cell Populations
13:13

Time-Lapse Imaging of Neuronal Arborization using Sparse Adeno-Associated Virus Labeling of Genetically Targeted Retinal Cell Populations

Published on: March 19, 2021

3.4K
Computational Modeling of Retinal Neurons for Visual Prosthesis Research - Fundamental Approaches
10:50

Computational Modeling of Retinal Neurons for Visual Prosthesis Research - Fundamental Approaches

Published on: June 21, 2022

2.3K
Assessment of Vascular Regeneration in the CNS Using the Mouse Retina
07:32

Assessment of Vascular Regeneration in the CNS Using the Mouse Retina

Published on: June 23, 2014

15.0K

Area of Science:

  • Ophthalmology
  • Medical Imaging
  • Artificial Intelligence

Background:

  • Automated classification of retinal images is crucial for detecting chronic diseases but is limited by the need for expert ophthalmologists.
  • Existing automated systems have shown partial success, highlighting the need for more effective and less intervention-dependent solutions.
  • Retinal image analysis is key for managing chronic conditions, yet accessibility for routine screenings by general physicians remains a challenge.

Purpose of the Study:

  • To introduce and evaluate a novel Lattice Neural Network with Dendritic Processing (LNNDP) for automated retinal image classification.
  • To demonstrate the superior performance of LNNDP compared to established methods like Support Vector Machines (SVM) and Multilayer Perceptrons (MLP).
  • To highlight LNNDP's advantages, including parameter-free operation and automatic structure construction for specific problems.

Main Methods:

  • The study employed a four-step methodology: Pre-processing, Feature computation, Classification, and Post-processing.
  • A Lattice Neural Network with Dendritic Processing (LNNDP) was utilized for the classification task.
  • The Hotelling T(2) control chart was implemented for feature vector dimensionality reduction from 7 to 5, and experiments were conducted on the DRIVE and STARE databases.

Main Results:

  • The LNNDP method demonstrated superior performance in classifying retinal images compared to SVM and MLP.
  • Key performance metrics including F1-Score, Matthews Correlation Coefficient (MCC), and accuracy were improved using LNNDP.
  • LNNDP achieved better average F1-Score, MCC, and accuracy on the DRIVE and STARE datasets.

Conclusions:

  • The Lattice Neural Network with Dendritic Processing (LNNDP) offers a significant advancement in automated retinal image analysis for disease detection.
  • LNNDP provides a more effective and efficient alternative to existing methods, requiring no parameter tuning and adapting its structure automatically.
  • This technology has the potential to overcome the bottleneck of expert ophthalmologist dependency, facilitating routine screenings by general physicians.