The detection of venous beading in retinal images provides an early sign of
diabetic retinopathy and plays an important role as a preprocessing step i
n diagnosing ocular diseases. We present a computer-aided diagnostic system
to automatically detect venous beading of blood vessels. It comprises of t
wo modules, referred to as the blood vessel extraction module (BVEM) and th
e venus beading detection module (VBDM). The former uses a bell-shaped Gaus
sian kernel with 12 azimuths to extract blood vessels while the latter appl
ies a neural network-based shape cognitron to detect venous beading among t
he extracted blood vessels for diagnosis. Both modules are fully computer-a
utomated. To evaluate the proposed system, 61 retinal images (32 beaded and
29 normal images) are used for performance evaluation. (C) 2000 Society of
Photo-Optical Instrumentation Engineers.