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

Multi-input and Multi-variable systems01:22

Multi-input and Multi-variable systems

186
Cruise control systems in cars are designed as multi-input systems to maintain a driver's desired speed while compensating for external disturbances such as changes in terrain. The block diagram for a cruise control system typically includes two main inputs: the desired speed set by the driver and any external disturbances, such as the incline of the road. By adjusting the engine throttle, the system maintains the vehicle's speed as close to the desired value as possible.
In the absence...
186
Calibration Curves: Linear Least Squares01:20

Calibration Curves: Linear Least Squares

2.9K
A calibration curve is a plot of the instrument's response against a series of known concentrations of a substance. This curve is used to set the instrument response levels, using the substance and its concentrations as standards. Alternatively, or additionally, an equation is fitted to the calibration curve plot and subsequently used to calculate the unknown concentrations of other samples reliably.
For data that follow a straight line, the standard method for fitting is the linear...
2.9K
Curvilinear Motion: Rectangular Components01:23

Curvilinear Motion: Rectangular Components

706
Curvilinear motion characterizes the movement of a particle or object along a curved path, notably evident when envisioning a car navigating a winding road. If the car starts at point A, its position vector is established within a fixed frame of reference, where the ratio of the position vector to its magnitude signifies the unit vector pointing in the position vector's direction.
As the car advances, its position evolves over time. Quantifying the car's velocity involves computing the...
706
Deconvolution01:20

Deconvolution

284
Deconvolution, also known as inverse filtering, is the process of extracting the impulse response from known input and output signals. This technique is vital in scenarios where the system's characteristics are unknown, and they must be inferred from the observable signals.
Deconvolution involves several mathematical techniques to derive the impulse response. One common approach is polynomial division. In this method, the input and output sequences are treated as coefficients of...
284
Neural Circuits01:25

Neural Circuits

1.8K
Neural circuits and neuronal pools are two of the main structures found in the nervous system. Neural circuits are networks of neurons that work together to carry out a specific task or process. They consist of interconnected neurons and glial cells, which provide structural and metabolic support.
Neuronal pools are collections of nerve cells with similar functions and interact through chemical and electrical signals. These pools include both interneurons (the central neural circuit nodes that...
1.8K
Sequence Networks of Rotating Machines01:24

Sequence Networks of Rotating Machines

161
A Y-connected synchronous generator, grounded through a neutral impedance, is designed to produce balanced internal phase voltages with only positive-sequence components. The generator's sequence networks include a source voltage that is exclusively in the positive-sequence network. The sequence components of line-to-ground voltages at the generator terminals illustrate this configuration.
Zero-sequence current induces a voltage drop across the generator's neutral impedance and other...
161

You might also read

Related Articles

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

Sort by
Same author

Bioactive compounds from <i>Ficus hirta</i> Vahl extract: Molecular mechanisms underlying their anti-inflammatory and antibacterial activities.

Biochemistry and biophysics reports·2026
Same author

Erratum for Zeng et al., "Predictive value of hepatic, hematological, and immunological markers and their temporal dynamics in chronic hepatitis B functional cure".

Microbiology spectrum·2026
Same author

Fluorescent labeled enzyme immobilized on chitosan-coated magnetic microspheres for potential cyclooxygenase-2 inhibitors screening accompanied with molecular modeling and in situ cell imaging.

Mikrochimica acta·2026
Same author

Penicinines A and B: two new 2-pyridone derivatives from a marine-derived fungus <i>Penicillium</i> sp. BTBU20218001.

Natural product research·2026
Same author

Host-viral interaction of HBV infection revealed by single-cell transcriptome jointly profiling the viral replication state.

Hepatology (Baltimore, Md.)·2026
Same author

Berberine Suppresses Pathogenic Fungus <i>Aspergillus fumigatus</i> Hyphal Growth via Mitochondrial Fragmentation-Induced ROS Elevation and Hog1-MAPK Activation.

ACS infectious diseases·2025

Related Experiment Video

Updated: Oct 3, 2025

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

Swin-PSAxialNet: An Efficient Multi-Organ Segmentation Technique

Published on: July 5, 2024

538

Curv-Net: Curvilinear structure segmentation network based on selective kernel and multi-Bi-ConvLSTM.

Yanlin He1, Hui Sun2, Yugen Yi3

  • 1College of Information Sciences and Technology, Northeast Normal University, Changchun, China.

Medical Physics
|February 16, 2022
PubMed
Summary
This summary is machine-generated.

Curv-Net, a novel deep learning network, accurately segments curvilinear structures in medical images by adaptively extracting multi-scale features and fusing information across stages. It outperforms existing methods, improving diagnostic capabilities.

Keywords:
U-shape networkscurvilinear structure segmentationdeep learningmulti-Bi-ConvLSTMselective kernel module

More Related Videos

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

3.0K
Objectification of Tongue Diagnosis in Traditional Medicine, Data Analysis, and Study Application
05:56

Objectification of Tongue Diagnosis in Traditional Medicine, Data Analysis, and Study Application

Published on: April 14, 2023

2.7K

Related Experiment Videos

Last Updated: Oct 3, 2025

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

Swin-PSAxialNet: An Efficient Multi-Organ Segmentation Technique

Published on: July 5, 2024

538
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

3.0K
Objectification of Tongue Diagnosis in Traditional Medicine, Data Analysis, and Study Application
05:56

Objectification of Tongue Diagnosis in Traditional Medicine, Data Analysis, and Study Application

Published on: April 14, 2023

2.7K

Area of Science:

  • Medical Image Analysis
  • Deep Learning
  • Computer Vision

Background:

  • Accurate segmentation of curvilinear structures (e.g., retinal blood vessels, nerve fibers) is crucial for diagnosing various medical conditions.
  • Existing deep learning methods often struggle with preserving details and minimizing false positives in curvilinear structure segmentation.
  • There is a need for improved segmentation techniques to enhance diagnostic accuracy in medical imaging.

Purpose of the Study:

  • To introduce Curv-Net, a novel end-to-end network designed for accurate segmentation of curvilinear structures in medical images.
  • To address limitations of current methods, such as loss of detail and high false-positive rates.
  • To improve the overall performance and reliability of medical image segmentation for clinical diagnosis.

Main Methods:

  • Curv-Net employs an encoder-decoder architecture incorporating selective kernel (SK) modules for adaptive multi-scale feature extraction.
  • A multi-bidirectional convolutional LSTM (multi-Bi-ConvLSTM) is utilized in skip connections to fuse features across stages and propagate information.
  • This architecture enables the capture of both detailed and semantic information for enhanced segmentation performance.

Main Results:

  • Curv-Net demonstrated strong performance on public datasets, including DRIVE, CHASE_DB1 (retinal images), and CCM-2 (corneal nerve fibers).
  • On the DRIVE dataset, Curv-Net achieved an Accuracy (ACC) of 0.9629, Sensitivity (SE) of 0.8175, Specificity (SP) of 0.9858, Dice similarity coefficient (Dice) of 0.8352, and Area Under the Curve (AUC) of 0.9810.
  • For the CHASE_DB1 dataset, results included ACC: 0.9810, SE: 0.8564, SP: 0.9899, Dice: 0.8143, and AUC: 0.9832. On the CCM-2 dataset, Dice, SE, and False Discovery Rate (FDR) were 0.8114 ± 0.0062, 0.8903 ± 0.0113, and 0.2547 ± 0.0104, respectively.

Conclusions:

  • Curv-Net effectively segments curvilinear structures in medical images, outperforming existing superior methods.
  • The network's architecture facilitates detailed feature extraction and information fusion, leading to robust segmentation.
  • Experimental validation on multiple datasets confirms the reliability and superiority of Curv-Net for clinical applications.