MS Thesis of Shawn Miller Title: Enabling a Real-time Solution to Retinal Vascular Tracing Using FPGAs Abstract: There is a need in the biomedical field for a method of tracing blood vessels in retinal fundus images. The speed of motion of the human eye and the desire for these traces to be available to assist during laser surgery require these traces to be available immediately after the retinal image is acquired. A retinal vascular tracing (RVT) algorithm exists and is currently implemented in software, however it is not fast enough to return traced images in real-time. One computationally intensive part of the algorithm is the two-dimensional filtering of the frames with sixteen different templates. A general purpose microprocessor cannot take full advantage of the parallelism inherent to the filter calculations. To speed up the RVT algorithm, and to enable a real-time solution, we mapped the filtering operation to the reconfigurable, customizable logic of a Field-programmable Gate Array (FPGA). We take the image data directly from the camera, compute the filter responses for every pixel in real-time, and send the results to memory on the host PC. Instead of the RVT algorithm computing filter responses in software, it simply looks up the results from memory, speeding up the overall solution. In order for the hardware to make results available in real-time with a minimized delay, a complex memory interface was designed.