Deep learning for retinal image segmentation
Garifullin, Azat (2017)
Diplomityö
Garifullin, Azat
2017
Julkaisun pysyvä osoite on
https://urn.fi/URN:NBN:fi-fe201705236828
https://urn.fi/URN:NBN:fi-fe201705236828
Tiivistelmä
A lot of eye diseases can be diagnosed through the characterization of the retinal blood vessels. The characterization can be done using proper imaging techniques and data analysis methods. The spectral fundus imaging is an approach providing hyperspectral images, where each channel corresponds to a certain wavelength. The spectral information gives additional information compared to the colour images which might be more useful for automatic data analysis since it contains more accurate information about reflectance spectra of the sample. This work studies the application of deep convolutional network for the retinal blood vessels segmentation, the comparison of the system for the ordinary colour and hyperspectral images is given, the experiments with the uncertainty estimation are provided.