Application of a Deep Machine Learning Model for Automatic Measurement of EZ Width in SD-OCT Images of RP

Abstract

We applied a deep convolutional neural network model for automatic identification of ellipsoid zone (EZ) in spectral domain optical coherence tomography B-scans of retinitis pigmentosa (RP). Methods: Midline B-scans having visible EZ from 220 patients with RP and 20 normal subjects were manually segmented for inner limiting membrane, inner nuclear layer, EZ, retinal pigment epithelium, and Bruch's membrane. A total of 2.87 million labeled image patches (33 × 33 pixels) extracted from 480 B-scans were used for training a convolutional neural network model implemented in MATLAB. B-scans from a separate group of 80 patients with RP were used for testing the model. A local connected area searching algorithm was developed to process the model output for reconstructing layer boundaries. Correlation and Bland-Altman analyses were conducted to compare EZ width measured by the model to those by manual segmentation. Results: The accuracy of the trained model to identify inner limiting membrane, inner nuclear layer, EZ, retinal pigment epithelium, and Bruch's membrane patches in the test dataset was 98%, 89%, 91%, 94%, and 96%, respectively. The EZ width measured by the model was highly correlated with that by two graders (r = 0.97; P < 0.0001). Bland-Altman analysis revealed a mean EZ width difference of 0.30 mm (coefficient of repeatability = 0.9 mm) between the model and the graders, comparable to the mean difference of 0.34mm (coefficient of repeatability = 0.8 mm) between two graders. Conclusions: The results demonstrated the capability of a deep machine learningbased method for automatic identification of EZ in RP, suggesting that the method can be used to quantify structural deficits in RP for detecting disease progression and for evaluating treatment effect. Translational Relevance: A deep machine learning model has the potential to replace humans for grading spectral domain optical coherence tomography images in RP.

A Hybrid Model Composed of Two Convolutional Neural Networks (CNNs) for Automatic Retinal Layer Segmentation of OCT Images in Retinitis Pigmentosa (RP)

“…For instance, the general automated OCT image analysis software currently implemented in Heidelberg Spectralis (Heidelberg Engineering, Inc, Heidelberg, Germany) can correctly identify the inner limiting membrane (ILM) for the most cases but often incorrectly identifies the EZ transition zone and the layer boundaries in the region where EZ is missing, thus still requiring a large number of manual corrections by human graders to obtain accurate EZ or OS metrics. 18 …”

“…Recently, we demonstrated the capability of a SW-based deep machine learning method for automatic segmentation of retinal layer boundaries and measurements of EZ width and OS length from SD-OCT B-scan images in RP. 18 However, the SW model is a single pixel classifier 32 and only predicts the class for one pixel at a time. A semantic segmentation CNN model such as U-Net 28 should take much less time than the SW model to segment a B-scan image.…”

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

“… 9 – 14 More recently, machine learning and deep learning methods have been used, including support vector machines, 15 , 16 random forest classifiers, 17 patch-based classification with convolutional neural networks 18 – 22 or recurrent neural networks, 20 , 22 semantic segmentation with fully convolutional (encoder–decoder) networks, 22 – 26 and other deep learning methods. 27 – 30 Importantly, some of these methods have been applied to OCT images from patients with age-related macular degeneration, 18 , 20 , 24 , 27 diabetic retinopathy, 11 , 25 macular telangiectasia type 2, 29 diabetic macular oedema, 13 , 23 , 24 pigment epithelium detachment, 28 glaucoma, 15 , 30 multiple sclerosis 17 , 26 retinitis pigmentosa, 31 and neurodegenerative diseases. 32 These diseases are characterized by variable thinning of the inner retinal layers (e.g., glaucoma and multiple sclerosis), thickening or cystic changes in the nuclear layers (e.g., macular telangiectasia type 2 and diabetic retinopathy) or focal disruption of the retinal pigment epithelium (RPE, e.g., age-related macular degeneration, macular telangiectasia, and pigment epithelium detachment).…”

Deep Learning-Based Automatic Detection of Ellipsoid Zone Loss in Spectral-Domain OCT for Hydroxychloroquine Retinal Toxicity Screening

“…Although multiple previous studies have developed algorithms for retinal layer segmentation of SD OCT images, 13,16e18 deriving surrogate metrics related to EZ loss from the contouring of retinal layers, segmentation often fails in the presence of disease, requiring significant manual adjustments to the algorithm-generated contours. 19,20 When the layers are deteriorating, robustly annotating the entire retinal layer to define ground truth can be both time consuming and challenging. The integrity of the layer segmentation would be compromised in regions with subtle loss with fading levels of image intensity without any signs of frank loss.…”