Abstract:
Many distinguished methods for vascular network detection in fundus images were proposed to help the diagnosis of clinical diseases. The vascular bifurcation sample in OC...Show MoreMetadata
Abstract:
Many distinguished methods for vascular network detection in fundus images were proposed to help the diagnosis of clinical diseases. The vascular bifurcation sample in OCT projection images is quite limited while it is sufficient in the corresponding fundus images. In this paper, we proposed a transfer learning-based method to detect the vascular bifurcations in OCT projection images using supervised transfer learning method. The samples from fundus images are utilized with transfer learning technique for vascular bifurcations detection in OCT projection images. The experimental results show the accuracy of vascular bifurcations detection can be improved by the proposed method.
Published in: 2016 9th International Congress on Image and Signal Processing, BioMedical Engineering and Informatics (CISP-BMEI)
Date of Conference: 15-17 October 2016
Date Added to IEEE Xplore: 16 February 2017
ISBN Information: