13 March 2013 Segmentation of retinal OCT images using a random forest classifier
Author Affiliations +
Proceedings Volume 8669, Medical Imaging 2013: Image Processing; 86690R (2013) https://doi.org/10.1117/12.2006649
Event: SPIE Medical Imaging, 2013, Lake Buena Vista (Orlando Area), Florida, United States
Optical coherence tomography (OCT) has become one of the most common tools for diagnosis of retinal abnormalities. Both retinal morphology and layer thickness can provide important information to aid in the differential diagnosis of these abnormalities. Automatic segmentation methods are essential to providing these thickness measurements since the manual delineation of each layer is cumbersome given the sheer amount of data within each OCT scan. In this work, we propose a new method for retinal layer segmentation using a random forest classifier. A total of seven features are extracted from the OCT data and used to simultaneously classify nine layer boundaries. Taking advantage of the probabilistic nature of random forests, probability maps for each boundary are extracted and used to help refine the classification. We are able to accurately segment eight retinal layers with an average Dice coefficient of 0:79±0:13 and a mean absolute error of 1:21±1:45 pixels for the layer boundaries.
© (2013) COPYRIGHT Society of Photo-Optical Instrumentation Engineers (SPIE). Downloading of the abstract is permitted for personal use only.
Andrew Lang, Andrew Lang, Aaron Carass, Aaron Carass, Elias Sotirchos, Elias Sotirchos, Peter Calabresi, Peter Calabresi, Jerry L. Prince, Jerry L. Prince, "Segmentation of retinal OCT images using a random forest classifier", Proc. SPIE 8669, Medical Imaging 2013: Image Processing, 86690R (13 March 2013); doi: 10.1117/12.2006649; https://doi.org/10.1117/12.2006649

Back to Top