In this work, we proposed to conduct the self-fusion algorithm on the neighboring depth images of 3D retinal OCT-A to create an auxiliary modality with cleaner vessels. Subsequently, we implement a dual-Unet architecture to map each en-face slide to its self-fusion counterpart. The latent image turns out to be a well-enhanced angiography that can be binarized with Otsu method.
-
Notifications
You must be signed in to change notification settings - Fork 0
DeweiHu/LIFE
Folders and files
| Name | Name | Last commit message | Last commit date | |
|---|---|---|---|---|
Repository files navigation
About
self-supervised volumetric vessel segmentation on OCT angriography
Resources
Stars
Watchers
Forks
Releases
No releases published
Packages 0
No packages published