Automated macular pathology diagnosis in retinal OCT images using multi-scale spatial pyramid and local binary patterns in texture and shape encoding

We address a novel problem domain in the analysis of optical coherence tomography (OCT) images: the diagnosis of multiple macular pathologies in retinal OCT images. The goal is to identify the presence of normal macula and each of three types of macular pathologies, namely, macular edema, macular hole, and age-related macular degeneration, in the OCT slice centered at the fovea. We use a machine learning approach based on global image descriptors formed from a multi-scale spatial pyramid. Our local features are dimension-reduced local binary pattern histograms, which are capable of encoding texture and shape information in retinal OCT images and their edge maps, respectively. Our representation operates at multiple spatial scales and granularities, leading to robust performance. We use 2-class support vector machine classifiers to identify the presence of normal macula and each of the three pathologies. To further discriminate sub-types within a pathology, we also build a classifier to differentiate full-thickness holes from pseudo-holes within the macular hole category. We conduct extensive experiments on a large dataset of 326 OCT scans from 136 subjects. The results show that the proposed method is very effective (all AUC > 0.93).

Stages of our approach:
• Align the retina to reduce the appearance variations
• Construct a global image descriptor formed from a multi-scale spatial pyramid to preserve the geometry
• The local features are dimension-reduced local binary pattern histograms for encoding texture and shape
• Train 2-class support vector machine classifiers to identify each pathology.Figure optionsDownload high-quality image (178 K)Download as PowerPoint slideHighlights
► The first work in computer-aided diagnosis of macular pathologies in retinal OCT images.
► The presence of normal macula and three pathologies (ME, MH, AMD) are identified.
► A novel descriptor to encode geometry, texture, and shape of the retinal structures.
► Extensive testing on large dataset of 326 scans with all AUC > 0.93.
► Machine learning based framework applicable to other pathologies.