TY - JOUR
AU - Lee, Aaron Y.
AB - Vol. 8, No. 7 | 1 Jul 2017 | BIOMEDICAL OPTICS EXPRESS 3440 Deep-learning based, automated segmentation of macular edema in optical coherence tomography 1 1 3 1 CECILIA S. LEE, ARIEL J. TYRING, NICOLAAS P. DERUYTER, YUE WU, 4 1,2,4,* ARIEL ROKEM, AND AARON Y. LEE Department of Ophthalmology, University of Washington, Seattle, Washington, USA Department of Ophthalmology, Puget Sound Veteran Affairs, Seattle Washington, USA University of Washington School of Medicine, Seattle, Washington, USA eScience Institute, University of Washington, Seattle, Washington, USA leeay@uw.edu Abstract: Evaluation of clinical images is essential for diagnosis in many specialties. Therefore the development of computer vision algorithms to help analyze biomedical images will be important. In ophthalmology, optical coherence tomography (OCT) is critical for managing retinal conditions. We developed a convolutional neural network (CNN) that detects intraretinal fluid (IRF) on OCT in a manner indistinguishable from clinicians. Using 1,289 OCT images, the CNN segmented images with a 0.911 cross-validated Dice coefficient, compared with segmentations by experts. Additionally, the agreement between experts and between experts and CNN were similar. Our results reveal that CNN can be trained to perform automated segmentations of clinically relevant image features. © 2017 Optical Society of America OCIS codes: 
TI - Deep-learning based, automated segmentation of macular edema in optical coherence tomography
JF - Biomedical Optics Express
DO - 10.1364/boe.8.003440
DA - 2017-06-23
UR - https://www.deepdyve.com/lp/unpaywall/deep-learning-based-automated-segmentation-of-macular-edema-in-optical-ff0GzdELTn
DP - DeepDyve
ER -