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

Secure Enhancement for MQTT Protocol Using Distributed Machine Learning Framework.

Sensors (Basel, Switzerland)·2024
See all related articles

Related Experiment Video

Updated: Jul 6, 2025

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

557

Micro aneurysm detection using optimized residual-based temporal attention Convolutional Neural Network with

Nouf Saeed Alotaibi1

  • 1Department of Computer Science, Shaqra University, Shaqra, Saudi Arabia.

Microscopy Research and Technique
|January 3, 2024
PubMed
Summary
This summary is machine-generated.

This study introduces a novel method for detecting microaneurysms using a specialized Convolutional Neural Network (CNN) called MA-RTCNN-Inception V3-EOA, achieving superior accuracy and reduced error rates in classifying these critical indicators.

Keywords:
composition‐adjusted thresholding methodequilibrium optimization algorithmguided box filteringmicro aneurysm detectionresidual‐based temporal attention convolutional neural network with Inception V3

More Related Videos

Automated Midline Shift and Intracranial Pressure Estimation based on Brain CT Images
14:08

Automated Midline Shift and Intracranial Pressure Estimation based on Brain CT Images

Published on: April 13, 2013

42.6K
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

2.8K

Related Experiment Videos

Last Updated: Jul 6, 2025

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

557
Automated Midline Shift and Intracranial Pressure Estimation based on Brain CT Images
14:08

Automated Midline Shift and Intracranial Pressure Estimation based on Brain CT Images

Published on: April 13, 2013

42.6K
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

2.8K

Area of Science:

  • Medical Imaging Analysis
  • Artificial Intelligence in Healthcare
  • Ophthalmology Diagnostics

Background:

  • Microaneurysms are early indicators of diabetic retinopathy, necessitating accurate detection methods.
  • Existing deep learning approaches for microaneurysm detection face limitations in accuracy and error rates.
  • Automated detection systems are crucial for timely diagnosis and management of diabetic retinopathy.

Purpose of the Study:

  • To propose and evaluate an advanced deep learning framework for microaneurysm detection.
  • To enhance the accuracy and reduce the classification error rate in identifying microaneurysms.
  • To compare the performance of the proposed method against existing state-of-the-art techniques.

Main Methods:

  • A novel microaneurysm detection framework (MA-RTCNN-Inception V3-EOA) integrating residual-based temporal attention Convolutional Neural Network (CNN) with Inception-V3 transfer learning, optimized by the equilibrium optimization algorithm (EOA).
  • Image pre-processing using guided box filtering for contrast enhancement and background exclusion.
  • Segmentation and classification phases utilizing the proposed RTCNN algorithm for accurate disease identification.

Main Results:

  • The proposed MA-RTCNN-Inception V3-EOA method demonstrated significantly higher accuracy compared to DRD-CNN-NPDR (23.56% higher) and MAFPN-AMD-MAFP-Net (14.99% higher).
  • Achieved substantial reductions in classification error rates: 31.26% lower than DRD-CNN-NPDR and 57.69% lower than MAFPN-AMD-MAFP-Net.
  • The framework showed robust performance across various evaluation metrics, including precision, sensitivity, f-measure, specificity, and Matthews's correlation coefficient, further validated by RoC analysis.

Conclusions:

  • The proposed MA-RTCNN-Inception V3-EOA framework offers a highly effective and accurate solution for microaneurysm detection.
  • This advanced deep learning approach significantly outperforms existing methods, paving the way for improved early diagnosis of diabetic retinopathy.
  • The integration of temporal attention CNN, transfer learning, and optimization algorithms provides a powerful tool for medical image analysis in ophthalmology.