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 Concept Videos

You might also read

Related Articles

Articles linked to this work by shared authors, journal, and citation graph.

Sort by
Same author

A Functional Shape Framework for the Detection of Multiple Sclerosis Using Optical Coherence Tomography Images.

Sensors (Basel, Switzerland)·2026
Same author

Behavioral assessments and differential excitability, oscillatory dynamics in dorsal and ventral hippocampal CA1 neurons in male rats of a prenatal VPA-exposed autism model.

Progress in neuro-psychopharmacology & biological psychiatry·2025
Same author

Divergent responses of glutamatergic and GABAergic prefrontal neurons underlie changes in excitability following low and high frequency repetitive brain stimulation.

Brain stimulation·2025
Same author

Analyzing Retinal Vessel Morphology in MS Using Interpretable AI on Deep Learning-Segmented IR-SLO Images.

Bioengineering (Basel, Switzerland)·2025
Same author

Dual-color optical activation and suppression of neurons with high temporal precision.

eLife·2025
Same author

A single dose of nicotine modulates heart rate variability in rats with induced-ulcerative colitis.

Autonomic neuroscience : basic & clinical·2025

Related Experiment Video

Updated: Jul 25, 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

2.8K

Optimal Deep Learning Architecture for Automated Segmentation of Cysts in OCT Images Using X-Let Transforms.

Reza Darooei1,2, Milad Nazari3,4, Rahele Kafieh1,5

  • 1Medical Image and Signal Processing Research Center, School of Advanced Technologies in Medicine, Isfahan University of Medical Sciences, Isfahan 8174673461, Iran.

Diagnostics (Basel, Switzerland)
|June 28, 2023
PubMed
Summary

This study introduces an optimal deep learning model using contourlet transform for segmenting cystic areas in Optical Coherence Tomography (OCT) images, improving diagnostic accuracy for retinal diseases.

Keywords:
OCTX-letcystsemantic segmentation

More Related Videos

Deep Learning-Based Segmentation of Cryo-Electron Tomograms
10:25

Deep Learning-Based Segmentation of Cryo-Electron Tomograms

Published on: November 11, 2022

9.0K
Swin-PSAxialNet: An Efficient Multi-Organ Segmentation Technique
04:48

Swin-PSAxialNet: An Efficient Multi-Organ Segmentation Technique

Published on: July 5, 2024

444

Related Experiment Videos

Last Updated: Jul 25, 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

2.8K
Deep Learning-Based Segmentation of Cryo-Electron Tomograms
10:25

Deep Learning-Based Segmentation of Cryo-Electron Tomograms

Published on: November 11, 2022

9.0K
Swin-PSAxialNet: An Efficient Multi-Organ Segmentation Technique
04:48

Swin-PSAxialNet: An Efficient Multi-Organ Segmentation Technique

Published on: July 5, 2024

444

Area of Science:

  • Ophthalmology
  • Medical Imaging
  • Artificial Intelligence

Background:

  • Retinal disorders like Age-Related Macular Degeneration (AMD) and Diabetic Macular Edema (DME) significantly impact vision.
  • Optical Coherence Tomography (OCT) is crucial for diagnosing these conditions.
  • Automated segmentation of retinal structures in OCT images is essential for accurate diagnosis and treatment.

Purpose of the Study:

  • To propose an optimal deep learning architecture for automated segmentation of cystic areas in OCT images.
  • To evaluate the effectiveness of various X-let transforms (curvelet, DTCWT, contourlet) and their combinations as network inputs.
  • To identify the best performing sparse basis functions and network configurations for enhanced segmentation accuracy.

Main Methods:

  • Developed a deep learning architecture utilizing sparse basis functions for OCT image analysis.
  • Employed various X-let transforms, including curvelet, Dual-Tree Complex Wavelet Transform (DTCWT), and contourlet, to generate diverse network inputs.
  • Tested different combinations of X-let sub-bands and evaluated performance using Dice coefficient, sensitivity, Jaccard index, and qualitative assessments on original and noisy datasets.

Main Results:

  • Contourlet transform demonstrated optimal results among the tested X-let transforms and their combinations.
  • A five-channel decomposition using high-pass sub-bands of the contourlet transform achieved the best segmentation performance.
  • The proposed method outperformed state-of-the-art techniques, particularly on noisy OCT datasets.

Conclusions:

  • The proposed deep learning approach with contourlet transform offers superior automated segmentation of cystic areas in OCT images.
  • This method shows significant potential for improving the accuracy and speed of retinal disease diagnosis in clinical settings.
  • The findings highlight the efficacy of sparse basis functions in enhancing OCT image analysis for ophthalmological applications.