Automated segmentation of Optical Coherence Tomography images
We propose a fast and accurate automated algorithm to segment retinal pigment epithelium and internal limiting membrane layer from spectral-domain optical coherence tomography (SDOCT) B-scans images. A hybrid algorithm, which combines intensity thresholding and graph-based algorithms, was used to process and analyze SDOCT radial scans (a hundred and twenty B-scans) images obtained from twenty patients. The relative difference in position of the layers segmented by the proposed hybrid algorithm and by clinical expert was 1.49% ± 0.01%. The processing time of the hybrid algorithm was 9.3 s for six B-scans. The Dice’s coefficient of the hybrid algorithm was 96.7%±1.6%. The proposed hybrid algorithm for the segmentation of SDOCT images had good agreement with manual segmentation and reduced processing time.
The University of Hong Kong
Kharmyssov Chingis,Ko Match,Kim Jong R.. Automated segmentation of Optical Coherence Tomography images[J].Chinese Optics Letters,2019,17(1):01.