Automatic Cone Photoreceptor Localisation in Healthy and Stargardt Afflicted Retinas Using Deep Learning

Abstract

We present a robust deep learning framework for the automatic localisation of cone photoreceptor cells in Adaptive Optics Scanning Light Ophthalmoscope (AOSLO) split-detection images. Monitoring cone photoreceptors with AOSLO imaging grants an excellent view into retinal structure and health, provides new perspectives into well known pathologies, and allows clinicians to monitor the effectiveness of experimental treatments. The MultiDimensional Recurrent Neural Network (MDRNN) approach developed in this paper is the first method capable of reliably and automatically identifying cones in both healthy retinas and retinas afflicted with Stargardt disease. Therefore, it represents a leap forward in the computational image processing of AOSLO images, and can provide clinical support in on-going longitudinal studies of disease progression and therapy. We validate our method using images from healthy subjects and subjects with the inherited retinal pathology Stargardt disease, which significantly alters image quality and cone density. We conduct a thorough comparison of our method with current state-of-the-art methods, and demonstrate that the proposed approach is both more accurate and appreciably faster in localizing cones. As further validation to the method’s robustness, we demonstrate it can be successfully applied to images of retinas with pathologies not present in the training data: achromatopsia, and retinitis pigmentosa.

Cone Photoreceptor Cell Segmentation and Diameter Measurement on Adaptive Optics Images Using Circularly Constrained Active Contour Model

“…Nevertheless, the smaller size of cones and higher density near the fovea meant that a similar number of cones could still be selected for the normal database even with a higher exclusion rate. While we do not expect that exclusion of cones with weak boundaries will affect the accuracy of the normal database, in the future, further enhancement of segmentation accuracy of crowded cones could be achieved by training the cone boundary classifier through deep learning 54 , 55 and applying the classifier to separate touching cells. 56 Fourth, in addition to cone diameter, second-order metrics based on cone segmentation might lead to additional insights about diseases such as Best disease, in which cones have been reported to be noncircular.…”

Cone Identification in Choroideremia: Repeatability, Reliability, and Automation Through Use of a Convolutional Neural Network

“…CNNs have shown promise for automatically identifying cones in AOSLO images of normal retina 27 and images from patients with achromatopsia 28 and Stargardts. 29 In the present study, we used the open source split-detection CNN developed by Cunefare et al 27 and showed that the Dice coefficient for the CHM-trained split-detection CNN selections in comparison to manual selections ranged from 0.78 to 0.85 for different graders (see Table 4). This is comparable to results using the same split-detection CNN retrained for achromatopsia (Dice coefficient, 0.867) 28 and for Stargardt's (Dice coefficient, 0.8797).…”

“…28 In addition, a multidimensional recurrent neural network has been shown to yield automatic cone identifications in Stargardt disease in good agreement with manual identifications. 29 However, it remains to be determined to what extent these techniques can be applied to patients with other retinal diseases as different diseases present with varying phenotypes in AOSLO images. 2 In the present study, we address the issues described above for translating quantifications of cone metrics for CHM into ones that can be readily applied to longitudinal clinical trials.…”

Retinal Boundary Segmentation in Stargardt Disease Optical Coherence Tomography Images Using Automated Deep Learning

“…Therefore, there is an opportunity to apply machine learning to address this clinical need. Currently, the only application of machine learning to Stargardt disease image analysis is limited to cone detection in adaptive optics scanning light ophthalmoscope split-detection images, as described by Davidson et al 40 …”