Microcystic macular edema (MME) manifests as small, hyporeflective cystic areas within the retina. For reasons that are still largely unknown, a small proportion of patients with multiple sclerosis (MS) develop MME-predominantly in the inner nuclear layer. These cystoid spaces, denoted pseudocysts, can be imaged using optical coherence tomography (OCT) where they appear as small, discrete, low intensity areas with high contrast to the surrounding tissue. The ability to automatically segment these pseudocysts would enable a more detailed study of MME than has been previously possible. Although larger pseudocysts often appear quite clearly in the OCT images, the multi-frame averaging performed by the Spectralis scanner adds a significant amount of variability to the appearance of smaller pseudocysts. Thus, simple segmentation methods only incorporating intensity information do not perform well. In this work, we propose to use a random forest classifier to classify the MME pixels. An assortment of both intensity and spatial features are used to aid the classification. Using a cross-validation evaluation strategy with manual delineation as ground truth, our method is able to correctly identify 79% of pseudocysts with a precision of 85%. Finally, we constructed a classifier from the output of our algorithm to distinguish clinically identified MME from non-MME subjects yielding an accuracy of 92%.
Keywords: (100.0100) Image processing; (170.4470) Ophthalmology; (170.4500) Optical coherence tomography.