Efficient edge detection method for anatomic feature extraction of neuro-sensory tissue image based on optical coherence tomography

In this work, we propose a reliable and detailed edge detection method customized on characteristics of optical coherence tomography images for stable feature extraction. Using a local window holding many pixels for tracking structural tendencies, edges are detected on reliably limited areas in reduced noise effect. For detailed pixel separation between structures, the edge detection is also achieved through clustering based on Gaussian mixture model. As results, the detected edges showed less than 3-μm of average distant differences compared to edges on manually recognized images. We believe this feature extraction method will provide improved quantitative analyses in wide OCT research areas.