pone.0238958.g002.tif (799.63 kB)

Sample results of vessel detection in UWFFA images using our automated algorithm show that the algorithm is able to detect vessels that are difficult to identify manually in low-contrast images.

Download (799.63 kB)
posted on 2020-09-11, 17:45 authored by Mohammad H. Bawany, Li Ding, Rajeev S. Ramchandran, Gaurav Sharma, Charles C. Wykoff, Ajay E. Kuriyan

From left to right: original ultra-widefield fluorescein angiography (UWFFA) image, enlarged views of rectangular regions that have low contrast, and the corresponding automatically detected vessel maps, and contrast-enhanced views. Our automated detection algorithm detects fine vessels that are difficult to manually identify in low contrast views and are verified as actual vessels by the contrast enhanced views.