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 Experiment Video

Updated: Oct 1, 2025

Smartphone Fundus Photography
05:51

Smartphone Fundus Photography

Published on: July 6, 2017

39.3K

Optimized hybrid machine learning approach for smartphone based diabetic retinopathy detection.

Shubhi Gupta1, Sanjeev Thakur2, Ashutosh Gupta3

  • 1Department of Computer Science, Amity University, Uttar Pradesh, India.

Multimedia Tools and Applications
|March 2, 2022
PubMed
Summary

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

Kikuchi-Fujimoto Disease Presenting With Complex Neurological Manifestations: A Case Report.

Case reports in neurological medicine·2026
Same author

Quality-by-design optimized reversed phase-high performance liquid chromatography method for quantification of everolimus in bulk drug and nanoparticle-based formulations.

Scientific reports·2026
Same author

Proprioceptive Stimuli as a Trigger for Leucine-Rich Glioma-Inactivated-1 (LGI1) IgG Associated Autoimmune Seizures, a Case Report.

The Neurohospitalist·2026
Same author

A randomized controlled study to compare the efficacy of intravitreal faricimab 6.0 mg versus aflibercept 2.0 mg in management of treatment-naive diabetic macular edema in Indian populations.

Indian journal of ophthalmology·2026
Same author

Ultrawide-field indocyanine angiography changes post 12 weeks of eplerenone in central serous chorioretinopathy.

Indian journal of ophthalmology·2026
Same author

Hemi-Chorea in Anti-GQ1b Syndrome: Expanding the Movement Disorder Spectrum.

Movement disorders clinical practice·2026

A new smartphone-based system offers an affordable and accessible method for detecting Diabetic Retinopathy (DR). This DIY approach utilizes advanced image processing and machine learning for early diagnosis, improving screening accessibility.

Area of Science:

  • Ophthalmology and medical imaging.
  • Biomedical engineering and computational health.

Background:

  • Diabetic Retinopathy (DR) is a diabetes complication damaging retinal blood vessels, often asymptomatic in early stages.
  • Yearly eye exams are crucial for early DR detection and effective treatment.
  • Traditional fundus cameras are costly and bulky, hindering widespread DR screening.

Purpose of the Study:

  • To develop and evaluate a low-cost, smartphone-based system for automated Diabetic Retinopathy detection and screening.
  • To create a DIY (do it yourself) retinal imaging solution using smartphone technology for accessible DR diagnosis.

Main Methods:

  • Smartphone-based retinal image acquisition using a DIY camera setup.
  • Image preprocessing including green channel transformation and Contrast Limited Adaptive Histogram Equalization (CLAHE).
Keywords:
And DIY smartphone enabled cameraDiabetic retinopathyMachine learningOptimizationSegmentationSmartphone

More Related Videos

Author Spotlight: AI-Driven Trypanosome Species Detection from Microscopic Images
08:20

Author Spotlight: AI-Driven Trypanosome Species Detection from Microscopic Images

Published on: October 27, 2023

1.8K
Subjective Refraction Test Using a Smartphone for Vision Screening
05:36

Subjective Refraction Test Using a Smartphone for Vision Screening

Published on: October 18, 2024

1.2K

Related Experiment Videos

Last Updated: Oct 1, 2025

Smartphone Fundus Photography
05:51

Smartphone Fundus Photography

Published on: July 6, 2017

39.3K
Author Spotlight: AI-Driven Trypanosome Species Detection from Microscopic Images
08:20

Author Spotlight: AI-Driven Trypanosome Species Detection from Microscopic Images

Published on: October 27, 2023

1.8K
Subjective Refraction Test Using a Smartphone for Vision Screening
05:36

Subjective Refraction Test Using a Smartphone for Vision Screening

Published on: October 18, 2024

1.2K
  • Segmentation of optic disc (Watershed Transform) and abnormalities (Triplet Half Band Filter bank - THFB).
  • Feature extraction using Haralick and Anisotropic Dual Tree Complex Wavelet Transform (ADTCWT).
  • Optimal feature selection via Life Choice-Based Optimizer (LCBO) algorithm.
  • Classification using a hybrid Machine Learning (ML) model combining Neural Network (NN) and Deep Convolutional Neural Network (DCNN), optimized with Social Ski-Driver (SSD).

    • Main Results:

    • The proposed smartphone-based DR detection system demonstrated high accuracy on the APTOS-2019-Blindness-Detection and EyePacs datasets.
    • The system effectively categorized DR severity levels, including mild, moderate, severe, and proliferative DR, as well as normal cases.
    • Performance evaluation using various metrics confirmed the superiority of the proposed scheme compared to existing approaches.

    Conclusions:

    • Smartphone-based retinal imaging presents a viable, cost-effective alternative for DR screening.
    • The developed DIY system facilitates automated DR detection, enhancing accessibility for early diagnosis.
    • This technology holds significant potential for improving global eye health outcomes by enabling widespread DR screening.