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: Dec 6, 2025

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

3.2K

A Multi-Label Deep Learning Model with Interpretable Grad-CAM for Diabetic Retinopathy Classification.

Hongyang Jiang, Jie Xu, Rongjie Shi

    Annual International Conference of the IEEE Engineering in Medicine and Biology Society. IEEE Engineering in Medicine and Biology Society. Annual International Conference
    |October 6, 2020
    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

    Single-Cell Suspension Preparation from Nile Tilapia Intestine for Single-Cell Sequencing.

    Journal of visualized experiments : JoVE·2023
    Same author

    Effects of Five Prebiotics on Growth, Antioxidant Capacity, Non-Specific Immunity, Stress Resistance, and Disease Resistance of Juvenile Hybrid Grouper (<i>Epinephelus fuscoguttatus</i> ♀ × <i>Epinephelus lanceolatus</i> ♂).

    Animals : an open access journal from MDPI·2023
    Same author

    Management of take-all disease caused by <i>Gaeumannomyces graminis</i> var. <i>tritici</i> in wheat through <i>Bacillus subtilis</i> strains.

    Frontiers in microbiology·2023
    Same author

    Enriched Environment Attenuates Ferroptosis after Cerebral Ischemia/Reperfusion Injury via the HIF-1<i>α</i>-ACSL4 Pathway.

    Oxidative medicine and cellular longevity·2023
    Same author

    Air pollution exposure and heart failure: A systematic review and meta-analysis.

    The Science of the total environment·2023
    Same author

    Case Report: A case of synchronous right upper lobe adenocarcinoma and left lower lobe squamous cell carcinoma treated with immune checkpoint inhibitor plus chemotherapy.

    Frontiers in oncology·2023

    This study introduces a deep learning model for classifying diabetic retinopathy (DR) fundus images and locating lesions. The method achieves high accuracy in DR classification and lesion identification, improving diagnostic efficiency.

    Area of Science:

    • Ophthalmology
    • Medical Imaging
    • Artificial Intelligence

    Background:

    • Diabetic retinopathy (DR) diagnosis relies on identifying multiple lesions in fundus images.
    • Accurate classification and lesion localization are crucial for effective DR management.
    • Current methods may require extensive manual annotation for lesion detection.

    Purpose of the Study:

    • To develop an efficient deep learning model for multi-label classification of DR fundus images.
    • To simultaneously classify DR and automatically detect/localize various types of lesions.
    • To transform lesion detection into an image classification task to reduce annotation burden.

    Main Methods:

    • A novel deep learning multi-label classification model based on ResNet architecture was designed.

    More Related Videos

    Quantification of Diabetes-induced Adherent Leukocytes in Retinal Vasculature
    05:54

    Quantification of Diabetes-induced Adherent Leukocytes in Retinal Vasculature

    Published on: January 24, 2025

    553

    Related Experiment Videos

    Last Updated: Dec 6, 2025

    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

    3.2K
    Quantification of Diabetes-induced Adherent Leukocytes in Retinal Vasculature
    05:54

    Quantification of Diabetes-induced Adherent Leukocytes in Retinal Vasculature

    Published on: January 24, 2025

    553
  • Gradient-weighted Class Activation Mapping (Grad-CAM) was integrated for lesion localization.
  • Five lesion types were pre-defined as labels, utilizing 3228 fundus images for training.

    • Main Results:

    • The model achieved high performance in DR classification with 93.9% sensitivity and 94.4% specificity.
    • The system successfully outlined the corresponding regions of lesions on DR fundus images.
    • The approach demonstrated effectiveness in both DR classification and lesion identification.

    Conclusions:

    • The proposed deep learning model offers an efficient and accurate method for DR fundus image analysis.
    • This approach simplifies lesion detection by reframing it as an image classification task.
    • The model shows significant potential for improving the diagnosis and management of diabetic retinopathy.