Vessel-Based Fovea Localization (VBFL)

 

Vessel-Based Fovea Localization (VBFL)

Aurélie Calabrèse, Vincent Fournet, Séverine Dours, Frédéric Matonti, Eric Castet, Pierre Kornprobst, A new vessel-based method to estimate automatically the position of the non-functional fovea on altered retinography from maculopathies, Translational vision science & technology, Vol 12, 2023

Downloads

Paper | Source Code (zip) | README (pdf)

Bibtex

@article{calabrese:hal-04159981,
TITLE = {{A New Vessel-Based Method to Estimate Automatically the Position of the Nonfunctional Fovea on Altered Retinography From Maculopathies}},
AUTHOR = {Calabr{\`e}se, Aur{\'e}lie and Fournet, Vincent and Dours, S{\'e}verine and Matonti, Fr{\'e}d{\'e}ric and Castet, Eric and Kornprobst, Pierre},
URL = {https://inria.hal.science/hal-04159981},
JOURNAL = {{Translational vision science \& technology}},
PUBLISHER = {{Association for Research in Vision and Ophthalmology (ARVO)}},
VOLUME = {12},
YEAR = {2023},
MONTH = Jul,
DOI = {10.1167/tvst.12.7.9},
KEYWORDS = {maculopathy fovea detection image processing macular lesion fundus image ; maculopathy ; fovea detection ; image processing ; macular lesion ; fundus image},
PDF = {https://inria.hal.science/hal-04159981/file/2023-calabrese-tvst-vbfl.pdf},
HAL_ID = {hal-04159981},
HAL_VERSION = {v1} }

Latest news:

  • March 22, 2024:  If you are using Apple Silicon chips (first manufactured in 2021 when they moved away from Intel GPUs and now the standard in all new Macs sold), you should use this environment.yml. The reason is that Tensorflow does not yet give GPU support to Apple Silicon chips. Whereas PyTorch does. Thanks to Rijul Soans for proposing this workaround!
  • December 19, 2023: Source code updated. File environment.yml cleaned.

Comments are closed.