PRIME-FP20: Ultra-Widefield Fundus Photography Vessel Segmentation Dataset

Citation Author(s):
Li
Ding
University of Rochester
Ajay E.
Kuriyan
Retina Service, Wills Eye Hospital
Rajeev S.
Ramchandran
University of Rochester
Charles C.
Wykoff
Houston Methodist Hospital
Gaurav
Sharma
University of Rochester
Submitted by:
Li Ding
Last updated:
Sun, 05/03/2020 - 13:13
DOI:
10.21227/ctgj-1367
Data Format:
License:
0
0 ratings - Please login to submit your rating.

Abstract 

PRIME-FP20 dataset is established for development and evaluation of retinal vessel segmentation algorithms in ultra-widefield fundus photography. PRIME-FP20 provides 15 high-resolution ultra-widefield fundus photography images acquired using the Optos 200Tx camera (Optos plc, Dunfermline, United Kingdom), the corresponding labeled binary vessel maps, and the corresponding binary masks for the FOV of the images.

Instructions: 

Ultra-widefield fundus photography images and the corresponding labeled vessel maps and binary masks are provided where the file names indicate the correspondence between them.

Currently, only a sample low-resolution image is provided. The full set of high-resolution images will be provided upon the publication of the associated paper, which is currently submitted for review.