Abstract:
Diabetic Retinopathy DR is one of the commonly existing disease in diabetic pa-
tients that may cause vision impairment. DR has ve stages of severity, wherein the
last stage is one of the major cause of blindness worldwide. In most of the cases, DR
does not show any symptoms until it reaches the last stage. If a mean is available
to timely detect DR during the early stages, it can be cured properly. An easy and
accurate system therefore is required to detect DR at very minute level. Patients
seeking help and doctors providing medical support both will be the immediate
bene ciary of this detection system. Doctors will greatly augment their diagnostic,
supportive or corrective decisions, as the system will support their decision with
certainty of DR severity stage. In this paper, we designed and compared multiple
automated systems for classi cation of DR using colored eye fundus images. The
main focus was to design a system that detects the presence of DR and classi es
the disease (if present) based on severity with best accuracy possible. We proposed
three frame works, Frame Work 1: was designed a cascaded classi er using more
than one combinations of Convolution Neural Networks (CNN) for feature extrac-
tion and comparaed best conventional classi er RFT for classi cation. It provided
improved accuracy of 75% with Sensitivity/Speci city 89%/76.8% and dealt with
over- tting and complexity of knowing minor details.Frame Work 2: we applied
multiple pre-processing techniques and reviewed their results we also infused re-
sults of multiple CNNs to get better accuracy of 78.6% with Sensitivity/Speci city
of 96%/75.14%. Frame Work 3: we added LSTM layer to our CNN for getting
better Accuracy of 76.9% with Sensitivity/Speci city 96.08%/73.81%. Using these
multiple Frame works we achieved best using ensemble systems. This research con-
cludes that by selecting right kind of pre-processing, data set management and
architecture working accuracy can be improved.
