Extraction Method of Retinal Border Lines for Optical Coherence Tomography by Using One Directional Active Net
Yamakawa, Ai Kodama, Dai Tsuruoka, Shinji Kawanaka, Hiroharu Takase, Haruhiko Uji, Yukitaka Matsubara, Hisashi Okuyama, Fumio
Graduate School of Engineering, Mie University Graduate School of Engineering, Mie University Graduate School of Regional Innovation Studies, Mie University Graduate School of Engineering, Mie University Graduate School of Engineering, Mie University Graduate School of Medicine, Mie University Graduate School of Medicine, Mie University Graduate School of Health Science, Suzuka University of Medical Science
Graduate School of Regional Innovation Studies, Mie University
Proceedings of the Second International Workshop on Regional Innovation Studies : (IWRIS2010)
inner limiting membrane / retinal pigment epi-thelium / optical coherence tomography / active net
In ophthalmology, the needs of retina diagnosis using optical coherence tomography (OCT) have been growing and the automatic measurement of a retinal thickness and its quantitative evaluation are desired for the diagnosis of retinal diseases. Previously, the automatic measurement methods of the retinal thickness have been reported for retinal OCT im-ages. However, the conventional methods have a disadvantage that the methods extracted the retinal border lines intermit-tently for OCT images with any damages. In this paper, we propose a new automatic measurement method of a retinal thickness in OCT image. The method employs a new dynamic contour model (“One Directional Active Net (ODAN)”) to extract two retinal border lines, and the thickness is defined from Inner Limiting Membrane (ILM) to Retinal Pigment Epithelium (RPE). ODAN employs a new energy function to extract the retinal border lines exactly and the energy function moves all nodes of ODAN to one direction only to minimize the total energy repeatedly. The energy function consists of the conformity characteristics energy of image to fit a border and the internal strain energy between the two dimensional nodes to arrange smoothly the position of each node. We confirmed the usefulness of the ODAN by the experimental results for normal and retinal disease OCT images. The proposed method is useful as the basic method for the detection of retinal diseas-es.