SWARM-BASED ALGORITHM FOR RETINAL BLOOD VESSEL DETECTION (2015)
Recent developments in medical imaging offer the possibility to make detailed images of retinal blood vessels. This gives information about the oxygen saturation in the retina, which is in its turn an indicator for diseases such as diabetes. This study looks into a way to automate the evaluation of the images in order to make it more efficient and reliable.
For this I have used Matlab to create an algorithm that is inspired by the swarming behaviour of bird flocks. This is used to cluster data within the image in order to recognize the blood vessels. The result of the algorithm is shown in the second image.
In collaboration with Jaspert de Vries.