Search research articles

ABOUT JoVE

Overview Leadership Blog JoVE Help Center

AUTHORS

Publishing Process Editorial Board Scope & Policies Peer Review FAQ Submit

LIBRARIANS

Testimonials Subscriptions Access Resources Library Advisory Board FAQ

RESEARCH

JoVE Journal Methods Collections JoVE Encyclopedia of Experiments Archive

EDUCATION

JoVE Core JoVE Business JoVE Science Education JoVE Lab Manual Faculty Resource Center Faculty Site

Terms & Conditions of Use

Search research articles

Related Experiment Video

Updated: May 14, 2026

Application of Deep Learning-Based Medical Image Segmentation via Orbital Computed Tomography

Application of Deep Learning-Based Medical Image Segmentation via Orbital Computed Tomography

Published on: November 30, 2022

Superpixel classification for initialization in model based optic disc segmentation.

Jun Cheng¹, Jiang Liu, Yanwu Xu

¹Institute for Infocomm Research, A*Star, Singapore.

Annual International Conference of the IEEE Engineering in Medicine and Biology Society. IEEE Engineering in Medicine and Biology Society. Annual International Conference

|February 1, 2013

Summary

This summary is machine-generated.

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

Solving the Puzzle of Hans' Algorithm (HA) Methodological Shortcomings: Canadian Harmonization of Hans' Algorithm for Diffuse Large B-Cell Lymphoma (DLBCL) and Development of Fit-for-Purpose Modified Hans' Algorithm (mHA).

Applied immunohistochemistry & molecular morphology : AIMM·2026

Same author

Blinatumomab in de novo AYA ALL-Results of the Australasian Leukaemia and Lymphoma Group ALL09 "SUBLIME" study.

HemaSphere·2026

Same author

International Consensus and Guidelines on Diagnosing and Managing Pachydrusen from APVRS, AEEC, APOIS, AAPPO, and ARI.

American journal of ophthalmology·2025

Same author

Longitudinal analysis of retinal and choriocapillaris in patients with multiple sclerosis: a 3-year study.

Journal of neurology·2025

Same author

Fit-for-Purpose Ki-67 Immunohistochemistry Assays for Breast Cancer.

Laboratory investigation; a journal of technical methods and pathology·2024

Same author

Enhancing the structure-function relationship in glaucoma using anatomical compensation of retinal nerve fibre layer.

The British journal of ophthalmology·2024

A new superpixel classification method improves optic disc segmentation in retinal images, crucial for computer-aided diagnosis. This approach enhances initialization accuracy, leading to more reliable ocular image analysis.

Area of Science:

Ophthalmology
Medical Image Analysis
Computer Vision

Background:

Optic disc segmentation is vital for diagnosing eye conditions using retinal fundus images.
Deformable models require accurate initialization, often challenged by peripapillary atrophy in retinal images.

Purpose of the Study:

To propose a superpixel classification-based method for robust optic disc segmentation initialization.
To develop a self-assessment reliability score to evaluate segmentation quality.

Main Methods:

Utilized superpixel classification with contrast-enhanced image histograms as features for initialization.
Employed bootstrapping during training to address class imbalance caused by peripapillary atrophy.
Computed a self-assessment reliability score to gauge initialization and segmentation quality.

More Related Videos

Ultrahigh Resolution Mouse Optical Coherence Tomography to Aid Intraocular Injection in Retinal Gene Therapy Research

Ultrahigh Resolution Mouse Optical Coherence Tomography to Aid Intraocular Injection in Retinal Gene Therapy Research

Published on: November 2, 2018

Related Experiment Videos

Last Updated: May 14, 2026

Application of Deep Learning-Based Medical Image Segmentation via Orbital Computed Tomography

Application of Deep Learning-Based Medical Image Segmentation via Orbital Computed Tomography

Published on: November 30, 2022

Ultrahigh Resolution Mouse Optical Coherence Tomography to Aid Intraocular Injection in Retinal Gene Therapy Research

Ultrahigh Resolution Mouse Optical Coherence Tomography to Aid Intraocular Injection in Retinal Gene Therapy Research

Published on: November 2, 2018

Main Results:

Achieved a mean overlapping error of 10.0% with a standard deviation of 7.5% on a 650-image dataset.
Demonstrated a correlation between reduced reliability scores and increased overlapping errors, validating the self-assessment.
The proposed method shows significant potential for accurate optic disc boundary detection.

Conclusions:

The superpixel classification method provides effective initialization for optic disc segmentation.
The self-assessment reliability score accurately indicates segmentation quality, enhancing clinical utility.
This approach can improve computer-aided diagnosis systems for ocular diseases.