An Innovative 3D Adaptive Patient-Related Atlas for Automatic Segmentation of Retina Layers from Oct Images

This paper introduces a 3D segmentation approach using an adaptive patient-specific retinal atlas and an appearance model for 3D Optical Coherence Tomography (OCT) data. In order to reconstruct the 3D patient-specific retinal atlas, we started by segmenting the macula central area where the fovea is clearly identified in the data to be segmented. The segmentation of this selected foveal area inside the retina is accomplished by using joint Markov Gibbs Random Field (MGRF) integrating shape, intensity, and spatial information of 12 retinal layers. A 2D shape prior was built using a series of co-registered training OCT images that were collected from 200 different subjects. The shape prior was then adapted to the first order appearance and second order spatial interaction MGRF model of the data to be segmented. Once the middle of the macula “foveal area” had been segmented, its segmented layers' labels and their appearances were used to segment the adjacent slices. The previous step was propagated until the complete 3D OCT patient-data was segmented. The proposed approach was tested on 30 different subjects, with either normal or pathological OCT scans, and then compared with a delineated ground truth and the results were then verified by retina specialists. Performance was measured using the Dice Similarity Coefficient (DSC), agreement coefficient (AC), and average deviation (AD) metrics. The accuracy achieved by the segmentation approach clearly demonstrates the promise of the proposed segmentation approach and shows improvement over a state-of-the-art 3D OCT segmentation approach currently in use.

[1]  Amir Alansary,et al.  Performance evaluation of an automatic MGRF-based lung segmentation approach , 2013 .

[2]  Jelena Novosel,et al.  Loosely coupled level sets for simultaneous 3D retinal layer segmentation in optical coherence tomography , 2015, Medical Image Anal..

[3]  Milan Sonka,et al.  Automated 3-D method for the correction of axial artifacts in spectral-domain optical coherence tomography images , 2011, Biomedical optics express.

[4]  Yalin Zheng,et al.  Reconstruction of 3D surface maps from anterior segment optical coherence tomography images using graph theory and genetic algorithms , 2016, Biomed. Signal Process. Control..

[5]  K. A. Vermeer,et al.  Automated segmentation by pixel classification of retinal layers in ophthalmic OCT images , 2011, Biomedical optics express.

[6]  David A. Clausi,et al.  Automated 3D Reconstruction and Segmentation from Optical Coherence Tomography , 2010, ECCV.

[7]  Jelena Novosel,et al.  Loosely coupled level sets for retinal layer segmentation in optical coherence tomography , 2013, 2013 IEEE 10th International Symposium on Biomedical Imaging.

[8]  Georgy L. Gimel'farb,et al.  High-Order MGRF Models for Contrast/Offset Invariant Texture Retrieval , 2014, IVCNZ '14.

[9]  Ayman El-Baz,et al.  An integrated framework for automatic clinical assessment of diabetic retinopathy grade using spectral domain OCT images , 2018, 2018 IEEE 15th International Symposium on Biomedical Imaging (ISBI 2018).

[10]  Thomas J Wolfensberger,et al.  Macular edema--rationale for therapy. , 2010, Developments in ophthalmology.

[11]  Ayman El-Baz,et al.  A computer‐aided diagnostic system for detecting diabetic retinopathy in optical coherence tomography images , 2017, Medical physics.

[12]  Ming-Hsuan Yang,et al.  A direct method for modeling non-rigid motion with thin plate spline , 2005, 2005 IEEE Computer Society Conference on Computer Vision and Pattern Recognition (CVPR'05).

[13]  Adam Dąbrowski,et al.  Matching 3D OCT retina images into super-resolution dataset , 2016, 2016 Signal Processing: Algorithms, Architectures, Arrangements, and Applications (SPA).

[14]  Xiaodong Wu,et al.  Optimal Surface Segmentation in Volumetric Images-A Graph-Theoretic Approach , 2006, IEEE Transactions on Pattern Analysis and Machine Intelligence.

[15]  Ayman El-Baz,et al.  An automated approach for early detection of diabetic retinopathy using SD-OCT images. , 2018, Frontiers in bioscience.

[16]  Ayman El-Baz,et al.  A novel automated method for the objective quantification of Retinal layers reveals sequential changes that occur in the Normal retina with age , 2016 .

[17]  Ayman El-Baz,et al.  Precise Segmentation of 3-D Magnetic Resonance Angiography , 2012, IEEE Transactions on Biomedical Engineering.

[18]  Qi Yang,et al.  Automated layer segmentation of macular OCT images using dual-scale gradient information. , 2010, Optics express.

[19]  Jonathan Bouchard,et al.  Decreasing incidence of type 2 diabetes mellitus in the United States, 2007-2012: Epidemiologic findings from a large US claims database. , 2016, Diabetes research and clinical practice.

[20]  Mona K. Garvin,et al.  Automated 3D segmentation of intraretinal layers from optic nerve head optical coherence tomography images , 2010, Medical Imaging.

[21]  T. Moon The expectation-maximization algorithm , 1996, IEEE Signal Process. Mag..

[22]  Christoph Schnörr,et al.  Probabilistic intra-retinal layer segmentation in 3-D OCT images using global shape regularization , 2014, Medical Image Anal..

[23]  Shutao Li,et al.  Segmentation Based Sparse Reconstruction of Optical Coherence Tomography Images , 2017, IEEE Transactions on Medical Imaging.

[24]  Aaron Carass,et al.  Multiple-object geometric deformable model for segmentation of macular OCT. , 2014, Biomedical optics express.

[25]  Ayman El-Baz,et al.  A novel automatic segmentation of healthy and diseased retinal layers from OCT scans , 2016, 2016 IEEE International Conference on Image Processing (ICIP).

[26]  Ayman El-Baz,et al.  Accurate Lungs Segmentation on CT Chest Images by Adaptive Appearance-Guided Shape Modeling. , 2017, IEEE transactions on medical imaging.

[27]  Xiaodong Wu,et al.  Automated 3-D Intraretinal Layer Segmentation of Macular Spectral-Domain Optical Coherence Tomography Images , 2009, IEEE Transactions on Medical Imaging.