110
a significant dependence between the proposed
features and the RNFL thickness measured by
OCT. We showed, that a standard linear regression
model can be sufficiently utilized for prediction of
the RFNL thickness. In the further research, sta-
tistical evaluation using larger dataset should be
performed as well as testing of additional possible
models to combine the proposed features.
ACKNOWLEDGEMENT
Department of Biomedical Engineering, FEEC,
Brno University of Technology: This work has
been supported by European Regional Devel-
opment Fund—Project FNUSA-ICRC (No.
CZ.1.05/1.1.00/02.0123) and by Czech-German
project no. 7 AMB12DE002 under Ministry of
Education, Youth and Sports.
Pattern Recognition Lab and Erlangen Gradu-
ate School in Advanced ...