Locating Blood vessel in Retinal Images by Piecewise Threshold Probing of a Matched Filter Response

Abstract

we describe an automated method to locate and outline blood vessels in images of the ocular fundus. Such a
tool should prove useful to eye care specialist for purpose of patient screening, treatment evaluation, and clinical study.
Our method differs from previously known methods in that it use local and global vessel feature cooperatively to segment
the vessel network. We evaluate our method using hand labeled ground truth segmentations of 20 images. A plot of the
operating characteristic shows that our method reduces false positives by as much as 15 times over basic thresholding of
a matched filter response (MFR), at up to a 75% true positive rate. For a baseline, we also compared the ground truth
against a second hand – labeling, yielding a 90% true positive and a 4% false positive detection rate, on average. These
numbers suggest there there is still room for a 15% true positive rate improvement, with the same false positive rate,
over our method. We are making all our images and hand labeling publicly available for interested researchers to use in
evaluating related methods