Scale-Space Vessel Tracing implementation of Lindeberg's algorithms

Tracing of the centrelines of microvasculature using a scale-space algorithm
212 Downloads
Aktualisiert 10. Jul 2018

The analysis of the vasculature of a tumour can be based on the some of the geometric parameters of the vessels, such as diameter of the vessels, number of branching points, length between branching points, or density of vessels in a given area. The following example illustrates how to perform the geometric analysis using MATLAB and some specifically designed funcions. The analysis is based on a technique called "Scale Space" which progressively blurs an image to observe its characteristics at different "scales": fine details will be observed at the first scales and then will be erased as the image is filtered, whilst larger characteristics will dominate the lower scales.
This work was was accepted for publication in Microvascular Research:
Online chromatic and scale-space microvessel-tracing analysis for transmitted light optical images CC Reyes-Aldasoro, MA Björndahl, S Akerman, J Ibrahim, MK Griffiths, GM Tozer, Microvascular research 84 (3), 330-339

For more detail on Scale-Space, the paper by Lindeberg explains the technique: (http://www.nada.kth.se/~tony/earlyvision.html)

Zitieren als

Constantino Carlos Reyes-Aldasoro (2025). Scale-Space Vessel Tracing implementation of Lindeberg's algorithms (https://github.com/reyesaldasoro/Scale-Space-Vessel-Tracing), GitHub. Abgerufen.

Kompatibilität der MATLAB-Version
Erstellt mit R2017a
Kompatibel mit allen Versionen
Plattform-Kompatibilität
Windows macOS Linux

Community Treasure Hunt

Find the treasures in MATLAB Central and discover how the community can help you!

Start Hunting!

Versionen, die den GitHub-Standardzweig verwenden, können nicht heruntergeladen werden

Version Veröffentlicht Versionshinweise
1.1.0.0

Changed title

1.0.0.0

Um Probleme in diesem GitHub Add-On anzuzeigen oder zu melden, besuchen Sie das GitHub Repository.
Um Probleme in diesem GitHub Add-On anzuzeigen oder zu melden, besuchen Sie das GitHub Repository.