Abstract
We propose a method for automatic detection of the foveal center in optical coherence tomography (OCT). The method is based on a pixel-wise classification of all pixels in an OCT volume using a fully convolutional neural network (CNN) with dilated convolution filters. The CNN-architecture contains anisotropic dilated filters and a shortcut connection and has been trained using a dynamic training procedure where the network identifies its own relevant training samples. The performance of the proposed method is evaluated on a data set of 400 OCT scans of patients affected by age-related macular degeneration (AMD) at different severity levels. For 391 scans (97.75%) the method identified the foveal center with a distance to a human reference less than 750 μm, with a mean (± SD) distance of 71 μm ± 107 μm. Two independent observers also annotated the foveal center, with a mean distance to the reference of 57 μm ± 84 μm and 56 μm ± 80 μm, respectively. Furthermore, we evaluate variations to the proposed network architecture and training procedure, providing insight in the characteristics that led to the demonstrated performance of the proposed method.
Highlights
The fovea is a region located near the center of the retina with the highest concentration of cones, photoreceptor cells responsible for color vision
We propose a method based on convolutional neural network (CNN) for the automated detection of the foveal center in Optical coherence tomography (OCT) volumes, building upon our previous work described in [31]
The OCT scans in the test set were not always accurately centered on the fovea: in 21 of the 400 test cases (5.25%) the scan-center was not located within 750 μm of the reference annotation
Summary
The fovea is a region located near the center of the retina with the highest concentration of cones, photoreceptor cells responsible for color vision. As a result of this elevated concentration, the fovea is responsible for central vision and high spatial acuity. Optical coherence tomography (OCT) is a non-invasive imaging technology that allows a detailed in-vivo analysis of the interior of the retina and, the fovea. This technique is based on low-coherence interferometry, where differences in back-scattering properties reveal the layered structure of the retina and produce high resolution images of cross sections of the retina. With OCT a more reliable estimation of the exact location of the fovea can be made compared to en-face modalities such as color fundus imaging, especially in retinal pathology [7, 8]
Talk to us
Join us for a 30 min session where you can share your feedback and ask us any queries you have
Disclaimer: All third-party content on this website/platform is and will remain the property of their respective owners and is provided on "as is" basis without any warranties, express or implied. Use of third-party content does not indicate any affiliation, sponsorship with or endorsement by them. Any references to third-party content is to identify the corresponding services and shall be considered fair use under The CopyrightLaw.