Three-dimensional segmentation and reconstruction of the retinal vasculature from spectral-domain optical coherence tomography

摘要: We reconstruct the three-dimensional shape and location of retinal vascular network from commercial spectral-domain (SD) optical coherence tomography (OCT) data. The two-dimensional on eye fundus is obtained through support vector machines classification properly defined images OCT data, taking advantage fact that standard SD-OCT, incident light beam absorbed by hemoglobin, creating a shadow signal below each perfused vessel. depth-wise vessel as beginning shadow. crossovers bifurcations within also addressed. illustrate feasibility method in terms caliber estimation accuracy classification.