RT Journal Article
SR Electronic
T1 Deep-Learning Based, Automated Segmentation of Macular Edema in Optical Coherence Tomography
JF bioRxiv
FD Cold Spring Harbor Laboratory
SP 135640
DO 10.1101/135640
A1 Cecilia S. Lee, MD MS
A1 Ariel J. Tyring MD
A1 Nicolaas P. Deruyter, BA
A1 Yue Wu, PHD
A1 Ariel Rokem, PHD
A1 Aaron Y. Lee, MD MSCI
YR 2017
UL http://biorxiv.org/content/early/2017/05/09/135640.abstract
AB Evaluation of clinical images is essential for diagnosis in many specialties and the development of computer vision algorithms to 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.