Readmore_vessel_segmentation.md

Vessel segmentation for fundus images

Segment the blood vessels in a fundus image using an ensemble of FR-U-Nets trained on the FIVES dataset.

See the usage_vessel-segmentation.ipynb.

[ x ] Works on tensor images
[(x)] Has batch support: Yes, you can pass batches, but internally, certain image preprocessing steps are performed sequentially.

Ref

This is a wrapper for code from Köhler et al., "Efficiently correcting patch-based segmentation errors to control image-level performance in retinal images" (2024). This package clones the official repository and provides an interface to the segmentation task.

Cite

@inproceedings{koehler_2024_efficiently,
    title={Efficiently correcting patch-based segmentation errors to control image-level performance},
    author={Patrick K{\"o}hler and Jeremiah Fadugba and Philipp Berens and Lisa M. Koch},
    booktitle={Submitted to Medical Imaging with Deep Learning},
    year={2024},
    url={https://openreview.net/forum?id=DDHRGHfwji}
}