Search research articles

Related Concept Videos

Computed Tomography

Computed Tomography

Tomography refers to imaging by sections. Computed tomography (CT) is a non-invasive imaging technique that uses computers to analyze several cross-sectional X-rays to reveal minute details about structures in the body.
The technique was invented in the 1970s and is based on the principle that as X-rays pass through the body, they are absorbed or reflected at different levels. In the technique, a patient lies on a motorized platform while a computerized axial tomography (CAT) scanner rotates...

Imaging Studies III: Computed Tomography

Imaging Studies III: Computed Tomography

DefinitionComputed Tomography (CT) of the genitourinary (GU) tract is a non-invasive imaging modality that utilizes X-rays and computer processing to generate detailed cross-sectional images of the urinary system, encompassing the kidneys, ureters, bladder, and adjacent structures such as the adrenal glands.PurposeCT scans of the GU tract serve several diagnostic and therapeutic purposes, including:Diagnosis of Urinary Tract Diseases: Detects kidney stones, tumors, cysts, and congenital...

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

Home
Three-dimensional Quantification Of Macular Oct Alterations Improves The Diagnostic Performance Of Artificial Intelligence Models.

Home
Three-dimensional Quantification Of Macular Oct Alterations Improves The Diagnostic Performance Of Artificial Intelligence Models.

Related Experiment Video

In vivo Structural Assessments of Ocular Disease in Rodent Models using Optical Coherence Tomography

In vivo Structural Assessments of Ocular Disease in Rodent Models using Optical Coherence Tomography

Published on: July 24, 2020

Three-Dimensional Quantification of Macular OCT Alterations Improves the Diagnostic Performance of Artificial

Lukas Heine^1,2, Anna Vahldiek¹, Benja Vahldiek¹

¹Institute for AI in Medicine, University Medicine Essen, Essen, North-Rhine Westfalia, Germany.

Translational Vision Science & Technology

|July 16, 2025

View abstract on PubMed

Summary

This summary is machine-generated.

State-of-the-art 3D semantic segmentation models, like nnU-Net, accurately segment retinal layers in OCT scans for age-related macular degeneration (AMD). This technology enhances large-scale cohort analysis and streamlines clinical workflows for AMD monitoring.

More Related Videos

Author Spotlight: Understanding Age-Related Macular Degeneration Pathophysiology with QAF Workflow

Author Spotlight: Understanding Age-Related Macular Degeneration Pathophysiology with QAF Workflow

Published on: May 26, 2023

Author Spotlight: Ex Vivo OCT-Based Multimodal Imaging of Human Donor Eyes for Research into Age-Related Macular Degeneration

Author Spotlight: Ex Vivo OCT-Based Multimodal Imaging of Human Donor Eyes for Research into Age-Related Macular Degeneration

Published on: May 26, 2023

Related Experiment Videos

In vivo Structural Assessments of Ocular Disease in Rodent Models using Optical Coherence Tomography

In vivo Structural Assessments of Ocular Disease in Rodent Models using Optical Coherence Tomography

Published on: July 24, 2020

Author Spotlight: Understanding Age-Related Macular Degeneration Pathophysiology with QAF Workflow

Author Spotlight: Understanding Age-Related Macular Degeneration Pathophysiology with QAF Workflow

Published on: May 26, 2023

Author Spotlight: Ex Vivo OCT-Based Multimodal Imaging of Human Donor Eyes for Research into Age-Related Macular Degeneration

Author Spotlight: Ex Vivo OCT-Based Multimodal Imaging of Human Donor Eyes for Research into Age-Related Macular Degeneration

Published on: May 26, 2023

Area of Science:

Ophthalmology
Medical Imaging
Artificial Intelligence

Background:

Age-related macular degeneration (AMD) diagnosis and monitoring rely on accurate analysis of Optical Coherence Tomography (OCT) data.
Manual segmentation of retinal layers and pathological features in OCT scans is time-consuming and subject to inter-observer variability.
Developing automated segmentation methods is crucial for efficient and objective analysis of AMD progression.

Purpose of the Study:

To evaluate the performance of state-of-the-art semantic segmentation algorithms for segmenting retinal structures and pathological features in OCT data from patients with neovascular AMD (nAMD).
To quantify the variability in manual annotations to establish a benchmark for automated methods.
To assess the potential of 3D segmentation models compared to traditional 2D approaches.

Main Methods:

Utilized 24 volume scans (49 slices each) from 94 patients with nAMD.
Trained annotators created pixel-wise masks for 12 retinal layers and two pathological labels (fluid, hyperreflective material).
Evaluated 2D and 3D semantic segmentation models using fivefold cross-validation, with the best model selected for error quantification against ground truth.

Main Results:

The 3D nnU-Net achieved the highest segmentation performance with a mean Dice Similarity Coefficient (DSC) of 0.907.
The performance gap between the best model and mean interrater agreement (0.036 DSC) indicates high accuracy.
The average error in volume calculation for segmented structures was 0.065 mm³.

Conclusions:

3D semantic segmentation models, exemplified by nnU-Net, can achieve high-quality segmentation of OCT data, challenging the reliance on 2D slices.
The achieved DSC and low volume errors suggest the model's suitability for large-scale cohort analysis in AMD research.
Automated segmentation significantly streamlines clinical workflows, reducing annotation time and effort for AMD monitoring and treatment response assessment.