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

Convolution Properties II01:17

Convolution Properties II

581
The important convolution properties include width, area, differentiation, and integration properties.
The width property indicates that if the durations of input signals are T1 and T2, then the width of the output response equals the sum of both durations, irrespective of the shapes of the two functions. For instance, convolving two rectangular pulses with durations of 2 seconds and 1 second results in a function with a width of 3 seconds.
The area property asserts that the area under the...
581
Linearization and Approximation01:26

Linearization and Approximation

31
Linearization is a mathematical technique used to approximate complex, nonlinear functions with simpler linear models in the vicinity of a chosen reference point. The method is based on the idea that, although a function may be difficult to evaluate exactly, its behavior near a specific input value can often be closely approximated by the tangent line at that point. This approach is particularly useful when small deviations from a known value are involved.Consider the square root function, for...
31
Application of Linearization and Approximation01:29

Application of Linearization and Approximation

70
A drone flying through complex terrain often relies on more than one sensing method to estimate small changes in altitude. Along with direct measurements, air pressure provides a useful indirect indicator of vertical movement. Atmospheric pressure decreases as altitude increases, and this relationship is commonly described using an exponential model. Although accurate, converting pressure measurements into altitude values requires calculations that are too complex to perform repeatedly during...
70
Accuracy, limits, and approximation01:28

Accuracy, limits, and approximation

1.1K
Accuracy, limits, and approximations are common in many fields, especially in engineering calculations. These concepts are imperative for ensuring that a given value is as close as possible to its true value.
Accuracy is defined as the closeness of the measured value to the true or actual value. In engineering mechanics, repeated measurements are taken during theoretical or experimental analyses to ensure that the result is precise and accurate.
The accuracy of any solution is based on the...
1.1K
Protein Networks02:26

Protein Networks

4.5K
An organism can have thousands of different proteins, and these proteins must cooperate to ensure the health of an organism. Proteins bind to other proteins and form complexes to carry out their functions. Many proteins interact with multiple other proteins creating a complex network of protein interactions.
These interactions can be represented through maps depicting protein-protein interaction networks, represented as nodes and edges. Nodes are circles that are representative of a protein,...
4.5K
Convolution Properties I01:20

Convolution Properties I

559
Convolution computations can be simplified by utilizing their inherent properties.
The commutative property reveals that the input and the impulse response of an LTI (Linear Time-Invariant) system can be interchanged without affecting the output:
559

You might also read

Related Articles

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

Sort by
Same author

Epidemiology and clinical outcomes of von Hippel-Lindau disease in Korea: a nationwide cohort study.

Scientific reports·2026
Same author

A graph retrieval-augmented generation pipeline for systematic drug target discovery: validation and application to ocular neovascularization.

Briefings in bioinformatics·2026
Same author

Nationwide Analysis of Eye-Related Emergency Department Visits in South Korea: NEDIS-EYE REPORT 1.

Ophthalmic epidemiology·2026
Same author

Age is not a limiting factor for preemptive arteriovenous access creation before hemodialysis to improve patient survival.

Kidney research and clinical practice·2026
Same author

Particle Diffusion Matching: Random Walk Correspondence Search for the Alignment of Standard and Ultra-Widefield Fundus Images.

IEEE transactions on image processing : a publication of the IEEE Signal Processing Society·2026
Same author

Comparison of warfarin and direct oral anticoagulants in kidney transplant recipients: Safety and efficacy outcomes.

Clinical nephrology·2026

Related Experiment Video

Updated: Jan 20, 2026

In vitro Synthesis of Native, Fibrous Long Spacing and Segmental Long Spacing Collagen
07:54

In vitro Synthesis of Native, Fibrous Long Spacing and Segmental Long Spacing Collagen

Published on: September 20, 2012

14.2K

Scale-space approximated convolutional neural networks for retinal vessel segmentation.

Kyoung Jin Noh1, Sang Jun Park1, Soochahn Lee2

  • 1Department of Ophthalmology, Seoul National University College of Medicine, Seoul National University Bundang Hospital, Seongnam, Gyeonggi-do 13620, South Korea.

Computer Methods and Programs in Biomedicine
|August 17, 2019
PubMed
Summary

A new deep learning model, scale-space approximated CNN (SSANet), enhances retinal vessel segmentation accuracy. This novel multi-scale CNN structure improves early diagnosis of vascular diseases and diabetes by accurately identifying thin vessels and junctions.

Keywords:
Convolutional neural networksMulti-scale representationRetinal vessel segmentationScale-space approximation

More Related Videos

Large-Scale Purification of Porcine or Bovine Photoreceptor Outer Segments for Phagocytosis Assays on Retinal Pigment Epithelial Cells
10:02

Large-Scale Purification of Porcine or Bovine Photoreceptor Outer Segments for Phagocytosis Assays on Retinal Pigment Epithelial Cells

Published on: December 12, 2014

12.8K
Author Spotlight: Enhancement of Salient Object Detection for Smart Grid Applications
03:31

Author Spotlight: Enhancement of Salient Object Detection for Smart Grid Applications

Published on: December 15, 2023

1.0K

Related Experiment Videos

Last Updated: Jan 20, 2026

In vitro Synthesis of Native, Fibrous Long Spacing and Segmental Long Spacing Collagen
07:54

In vitro Synthesis of Native, Fibrous Long Spacing and Segmental Long Spacing Collagen

Published on: September 20, 2012

14.2K
Large-Scale Purification of Porcine or Bovine Photoreceptor Outer Segments for Phagocytosis Assays on Retinal Pigment Epithelial Cells
10:02

Large-Scale Purification of Porcine or Bovine Photoreceptor Outer Segments for Phagocytosis Assays on Retinal Pigment Epithelial Cells

Published on: December 12, 2014

12.8K
Author Spotlight: Enhancement of Salient Object Detection for Smart Grid Applications
03:31

Author Spotlight: Enhancement of Salient Object Detection for Smart Grid Applications

Published on: December 15, 2023

1.0K

Area of Science:

  • Medical imaging analysis
  • Deep learning for healthcare
  • Ophthalmology diagnostics

Background:

  • Retinal fundus images are crucial for diagnosing retinal diseases.
  • Early detection of vascular diseases and diabetes can be aided by analyzing retinal images.
  • Existing deep learning methods for retinal vessel segmentation often use standard CNN architectures.

Purpose of the Study:

  • To introduce a novel multi-scale convolutional neural network (CNN) for improved retinal vessel segmentation.
  • To address limitations of existing multi-scale CNN structures in retinal image analysis.
  • To enhance the accuracy of automatic diagnosis of eye conditions and related systemic diseases.

Main Methods:

  • Developed a scale-space approximated CNN (SSANet) utilizing upsampling for multi-scale representation.
  • Incorporated residual blocks into the SSANet architecture for enhanced performance.
  • Theoretically analyzed multi-scale structures using signal processing and scale-space theory.

Main Results:

  • SSANet achieved state-of-the-art Area Under the Curve (AUC) of 0.9916 on the CHASE_DB1 dataset.
  • Quantitative evaluations on four public datasets (DRIVE, STARE, CHASE_DB1, HRF) demonstrated superior performance.
  • Ablative analysis confirmed the contribution of SSANet's components to improved segmentation accuracy.

Conclusions:

  • The proposed SSANet achieves state-of-the-art or comparable accuracy in retinal vessel segmentation.
  • SSANet shows particular improvement in segmenting thin vessels, vessel junctions, and central vessel reflexes.
  • This advancement holds promise for earlier and more accurate diagnosis of diabetic retinopathy and other vascular conditions.