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

Explainable dual-stage context-aware SwinUNet for accurate optic disc and optic cup segmentation in glaucoma assessment.

International ophthalmology·2026
Same author

Dual vision transformer with bio-inspired optimization for explainable keratoconus classification.

International ophthalmology·2026
Same author

OGTCN-E-MGO: an optimized deep learning framework for EEG-based schizophrenia detection.

Physical and engineering sciences in medicine·2026
Same author

Adsorptive sequestration of noxious uranium (VI) from water resources: A comprehensive review.

Chemosphere·2022
Same author

Hybridization of long short-term memory with Sparrow Search Optimization model for water quality index prediction.

Chemosphere·2022
Same author

Biodegradation of P-nitro phenol using a novel bacterium Achromobacter denitrifacians isolated from industrial effluent water.

Water science and technology : a journal of the International Association on Water Pollution Research·2021

Related Experiment Video

Updated: Jan 6, 2026

Comparison of Agreement and Accuracy using Binocular Wavefront Optometer with Autorefractor and Phoropter
05:14

Comparison of Agreement and Accuracy using Binocular Wavefront Optometer with Autorefractor and Phoropter

Published on: September 16, 2025

526

Metaheuristic-optimized swin transformer with SHAP explainability for keratoconus classification from corneal

S Maria Seraphin Sujitha1, S Subiramoniyan2, J Mahil3

  • 1Department of Electronics and Communication Engineering, St. Xavier's Catholic College of Engineering, Nagercoil, Tamilnadu, India. mariaseraphinsujithas@outlook.com.

International Ophthalmology
|September 29, 2025
PubMed
Summary

This study introduces a deep learning model for early keratoconus (KCN) detection using corneal images. The automated system achieves high accuracy, offering a reliable alternative to subjective diagnostic methods.

Keywords:
KeratoconusPolar fox optimizerResidual multi-layer perceptronsSwin transformer

More Related Videos

A Swin Transformer-Based Model for Thyroid Nodule Detection in Ultrasound Images
04:23

A Swin Transformer-Based Model for Thyroid Nodule Detection in Ultrasound Images

Published on: April 21, 2023

2.2K
Swin-PSAxialNet: An Efficient Multi-Organ Segmentation Technique
04:48

Swin-PSAxialNet: An Efficient Multi-Organ Segmentation Technique

Published on: July 5, 2024

719

Related Experiment Videos

Last Updated: Jan 6, 2026

Comparison of Agreement and Accuracy using Binocular Wavefront Optometer with Autorefractor and Phoropter
05:14

Comparison of Agreement and Accuracy using Binocular Wavefront Optometer with Autorefractor and Phoropter

Published on: September 16, 2025

526
A Swin Transformer-Based Model for Thyroid Nodule Detection in Ultrasound Images
04:23

A Swin Transformer-Based Model for Thyroid Nodule Detection in Ultrasound Images

Published on: April 21, 2023

2.2K
Swin-PSAxialNet: An Efficient Multi-Organ Segmentation Technique
04:48

Swin-PSAxialNet: An Efficient Multi-Organ Segmentation Technique

Published on: July 5, 2024

719

Area of Science:

  • Ophthalmology
  • Artificial Intelligence
  • Medical Imaging

Background:

  • Keratoconus (KCN) is a progressive corneal disorder causing vision loss.
  • Early KCN detection is crucial for timely intervention.
  • Current diagnostic methods are subjective and lack sensitivity for early detection.

Purpose of the Study:

  • To develop an automated, scalable deep learning (DL) model for KCN detection.
  • To improve the accuracy and reliability of KCN diagnosis.
  • To provide an expert-independent diagnostic tool for clinical use.

Main Methods:

  • Utilized a deep learning model combining Improved Swin Transformer Blocks (ISTB) and Residual Multi-Layer Perceptrons (R-MLP).
  • Employed the Polar Fox Optimizer (PFO) for model training and enhancement.
  • Integrated SHapley additive exPlanations (SHAP) for model interpretability.

Main Results:

  • The proposed DL model achieved 99.4% accuracy on a benchmark dataset.
  • The model outperformed existing diagnostic approaches.
  • SHAP analysis provided insights into the model's decision-making process.

Conclusions:

  • The developed DL model offers a highly accurate and automated solution for KCN detection.
  • This approach has the potential for clinical deployment, especially in low-resource settings.
  • The model provides understandable, real-time, and expert-independent KCN diagnosis.