Related Experiment Video
Updated: Dec 6, 2025
An In Vitro 3D Model and Computational Pipeline to Quantify the Vasculogenic Potential of iPSC-Derived Endothelial Progenitors
Published on: May 13, 2019
VSSC Net: Vessel Specific Skip chain Convolutional Network for blood vessel segmentation
Pearl Mary Samuel1, Thanikaiselvan Veeramalai1
1School of Electronics Engineering, Vellore Institute of Technology, Vellore, India.
Insights
This study introduces VSSC Net, a deep learning model for accurate blood vessel segmentation in retinal fundus and coronary angiogram images, aiding early disease diagnosis.
Area of Science:
- Medical Imaging
- Computer Vision
- Artificial Intelligence
Background:
- Accurate blood vessel segmentation is crucial for early diagnosis of life-threatening diseases using retinal fundus and coronary angiogram images.
- Deep learning models offer advanced capabilities for medical image analysis and disease detection.
Purpose of the Study:
- To develop and validate a single deep learning model, VSSC Net, for segmenting blood vessels in both coronary angiograms and retinal fundus images.
- To improve the efficiency and accuracy of blood vessel segmentation for diagnostic purposes.
Main Methods:
- Image-specific preprocessing was applied to coronary angiogram and retinal fundus images.
- A novel VSSC Net architecture, built upon VGG-16, incorporated two vessel extraction layers with added supervision.
- These layers featured vessel-specific convolutional blocks, skip-chain convolutional layers, and feature map summation, with weighted fusion of individual loss functions for probability map generation.
Main Results:
- The VSSC Net demonstrated improved accuracy in segmenting blood vessels on standard retinal and coronary angiogram datasets.
- Segmentation was achieved rapidly, with a computational time of 0.2 seconds using GPU.
- The model's vessel extraction layer is efficient, utilizing only 0.4 million parameters.
Conclusions:
- The VSSC Net effectively segments blood vessels from multiple imaging sources, supporting early diagnosis of vascular disorders.
- This technology can assist physicians in analyzing complex blood vessel structures, potentially improving patient outcomes.
Background And Objective:
Deep learning techniques are instrumental in developing network models that aid in the early diagnosis of life-threatening diseases. To screen and diagnose the retinal fundus and coronary blood vessel disorders, the most important step is the proper segmentation of the blood vessels.
Methods:
This paper aims to segment the blood vessels from both the coronary angiogram and the retinal fundus images using a single VSSC Net after performing the image-specific preprocessing. The VSSC Net uses two-vessel extraction layers with added supervision on top of the base VGG-16 network. The vessel extraction layers comprise of the vessel-specific convolutional blocks to localize the blood vessels, skip chain convolutional layers to enable rich feature propagation, and a unique feature map summation. Supervision is associated with the two-vessel extraction layers using separate loss/sigmoid function. Finally, the weighted fusion of the individual loss/sigmoid function produces the desired blood vessel probability map. It is then binary segmented and validated for performance.
Results:
The VSSC Net shows improved accuracy values on the standard retinal and coronary angiogram datasets respectively. The computational time required to segment the blood vessels is 0.2 seconds using GPU. Moreover, the vessel extraction layer uses a lesser parameter count of 0.4 million parameters to accurately segment the blood vessels.
Conclusion:
The proposed VSSC Net that segments blood vessels from both the retinal fundus images and coronary angiogram can be used for the early diagnosis of vessel disorders. Moreover, it could aid the physician to analyze the blood vessel structure of images obtained from multiple imaging sources.
Related Concept Videos
01:07Development of Blood Vessels
The initial formation of this system is facilitated by the small amount of yolk present in the ovum and yolk sac. Blood vessels originate from...
01:15Structure of Blood Vessels
01:20Anatomy of Blood Vessels
Arteries
Arteries circulate oxygenated blood from the heart, except the pulmonary artery, which transports deoxygenated blood to the lungs. Large arteries, such as the aorta,...
01:14Overview of Blood Vessels
Arteries and Arterioles: Arteries are muscular and elastic vessels that primarily carry oxygenated blood from the heart to body tissues, except for the pulmonary artery, which carries deoxygenated blood. They have thick walls to withstand high pressure and contain a layer of muscle tissue, allowing them to expand or contract as...
01:19Imaging Studies VII: Vascular Imaging
01:29Blood Flow