Skip to content

In this repository, I implement a system for extract blood vessels from DRIVE images.

License

Notifications You must be signed in to change notification settings

farkoo/Retinal-Vessel-Segmentation

Folders and files

NameName
Last commit message
Last commit date

Latest commit

 

History

22 Commits
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 

Repository files navigation

Retinal-Vessel-Segmentation

The DRIVE database has been established to enable comparative studies on segmentation of blood vessels in retinal images. Retinal vessel segmentation and delineation of morphological attributes of retinal blood vessels, such as length, width, tortuosity, branching patterns and angles are utilized for the diagnosis, screening, treatment, and evaluation of various cardiovascular and ophthalmologic diseases such as diabetes, hypertension, arteriosclerosis and chorodial neovascularization.

In this repository, I implement a system for extract blood vessels from DRIVE images.

Steps

Preprocessing:

  • Extract mask image
  • Extract green channel
  • CLAHE contrast enhancement

  • Replace black ring
  • Top-hat transform

Vessel Extraction

  • Otsu thresholding
  • Remove small regions

  • Thick vessel extraction
  • Thin vessel extraction
  • Create the final image using the last two images

Compare my result and ground truth

  • Green: same ture in mr(my result) and gt(ground truth)
  • Red: one in mr and zero in gt
  • Purple: Zero in mr and one in gt

Final Results

My results for 20 test images:

Support

Contact me @:

e-mail:

Telegram id:

License

MIT © Farzaneh Koohestani

About

In this repository, I implement a system for extract blood vessels from DRIVE images.

Topics

Resources

License

Stars

Watchers

Forks

Releases

No releases published

Packages

No packages published

Languages