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: Aug 8, 2025

Application of Optical Coherence Tomography to a Mouse Model of Retinopathy
08:22

Application of Optical Coherence Tomography to a Mouse Model of Retinopathy

Published on: January 12, 2022

4.2K

An interpretable transformer network for the retinal disease classification using optical coherence tomography.

Jingzhen He1, Junxia Wang2, Zeyu Han3

  • 1Department of Radiology, Qilu Hospital of Shandong University, Jinan, 250012, China. hjzhhjzh@163.com.

Scientific Reports
|March 3, 2023
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

Unveiling Subtle Lesions in HSV-1 Encephalitis: Advantages of 7T MRI.

Neurology·2026
Same author

CT-guided microwave ablation combined with thoracoscopic resection for multiple ground-glass nodules: a single-session treatment strategy.

Frontiers in medicine·2026
Same author

Text-Image Co-Alignment for Weakly Supervised Polyp Segmentation.

IEEE transactions on medical imaging·2026
Same author

High-Resolution MRI Using Artificial Intelligence-Assisted Acceleration and Radial Dynamic Contrast Enhancement for Improved Detection of Pituitary Microadenomas in Cushing Disease.

AJNR. American journal of neuroradiology·2026
Same author

The impact of social phobia tendency on positive affect: the role of perceived control and its neural correlates.

Brain structure & function·2025
Same author

The Combination of Transcranial Alternating Current Stimulation and Electroencephalogram.

Journal of visualized experiments : JoVE·2025

A new Swin-Poly Transformer network enhances retinal OCT image classification for diagnosing blindness-causing diseases. This interpretable AI model achieves high accuracy, improving efficiency and aiding medical professionals.

Area of Science:

  • Ophthalmology
  • Medical Imaging
  • Artificial Intelligence

Background:

  • Retinal illnesses like age-related macular degeneration and diabetic macular edema cause irreversible blindness.
  • Optical coherence tomography (OCT) is crucial for diagnosing these conditions, but manual analysis is slow and error-prone.
  • Computer-aided diagnosis (CAD) algorithms offer efficiency but require further improvements in accuracy and interpretability.

Purpose of the Study:

  • To develop an interpretable AI model for automated retinal OCT image classification.
  • To enhance the accuracy and interpretability of OCT image analysis for early disease detection.

Main Methods:

  • Proposed an interpretable Swin-Poly Transformer network for retinal OCT image classification.
  • Utilized window partitioning for multi-scale feature modeling and refined cross-entropy loss with polynomial bases.

More Related Videos

Optical Coherence Tomography: Imaging Mouse Retinal Ganglion Cells In Vivo
08:17

Optical Coherence Tomography: Imaging Mouse Retinal Ganglion Cells In Vivo

Published on: September 22, 2017

19.4K
Retinal Vascular Reactivity as Assessed by Optical Coherence Tomography Angiography
07:23

Retinal Vascular Reactivity as Assessed by Optical Coherence Tomography Angiography

Published on: March 26, 2020

7.6K

Related Experiment Videos

Last Updated: Aug 8, 2025

Application of Optical Coherence Tomography to a Mouse Model of Retinopathy
08:22

Application of Optical Coherence Tomography to a Mouse Model of Retinopathy

Published on: January 12, 2022

4.2K
Optical Coherence Tomography: Imaging Mouse Retinal Ganglion Cells In Vivo
08:17

Optical Coherence Tomography: Imaging Mouse Retinal Ganglion Cells In Vivo

Published on: September 22, 2017

19.4K
Retinal Vascular Reactivity as Assessed by Optical Coherence Tomography Angiography
07:23

Retinal Vascular Reactivity as Assessed by Optical Coherence Tomography Angiography

Published on: March 26, 2020

7.6K
  • Incorporated confidence score maps for enhanced model interpretability.

    • Main Results:

    • The Swin-Poly Transformer achieved superior performance compared to traditional CNNs and Vision Transformers (ViT).
    • Demonstrated high accuracy (99.80%) and Area Under the Curve (AUC) (99.99%) on OCT2017 and OCT-C8 datasets.
    • The confidence score maps provided valuable insights into the model's decision-making process.

    Conclusions:

    • The Swin-Poly Transformer network offers a highly accurate and interpretable solution for automated retinal OCT image classification.
    • This AI approach can significantly improve the efficiency and reliability of diagnosing retinal diseases.
    • The method aids medical practitioners by providing understandable diagnostic predictions.