Aineistot 1-2 / 2
Fusion of semi-synthetic retinal image segmentations
The aim of this thesis was to get acquainted with and compare the performances of several label fusion algorithms experimentally using retinal image segmentations. Because the initial retinal image data could not be used ...
Improving the performance of Bayesian deep model training for artery-vein segmentation
Retinal images are an important tool for diagnosis of ocular diseases. Automating the process of screening the retinal images would allow wider screening and make diagnosing of patients’ swifter. The possibility of performing ...