Diagnosis of central serous chorioretinopathy by deep learning analysis of en face images of choroidal vasculature: A pilot study

• Published in: PloS one Vol. 16; no. 6; p. e0244469
• Main Authors: Aoyama, Yukihiro, Maruko, Ichiro, Kawano, Taizo, Yokoyama, Tatsuro, Ogawa, Yuki, Maruko, Ruka, Iida, Tomohiro
• Format: Journal Article
• Language: English
• Published: San Francisco Public Library of Science 18.06.2021; Public Library of Science (PLoS)
• Subjects: Artificial intelligence; Biology and Life Sciences; Computer and Information Sciences; Computer programs; Deep learning; Diabetic retinopathy; Diagnosis; Drafting software; Evaluation; Eye; Eye (anatomy); Human performance; Learning algorithms; Machine learning; Macular degeneration; Medical diagnosis; Medical imaging; Medicine and Health Sciences; Neural networks; Ophthalmology; Optimization; Photodynamic therapy; Research and Analysis Methods; Retinitis pigmentosa; Software; Japan
• ISSN: 1932-6203; 1932-6203
• DOI: 10.1371/journal.pone.0244469

To diagnose central serous chorioretinopathy (CSC) by deep learning (DL) analyses of en face images of the choroidal vasculature obtained by optical coherence tomography (OCT) and to analyze the regions of interest for the DL from heatmaps. One-hundred eyes were studied; 53 eyes with CSC and 47 normal eyes. Volume scans of 12x12 mm square were obtained at the same time as the OCT angiographic (OCTA) scans (Plex Elite 9000 Swept-Source OCT.sup.®, Zeiss). High-quality en face images of the choroidal vasculature of the segmentation slab of one-half of the subfoveal choroidal thickness were created for the analyses. The 100 en face images were divided into 80 for training and 20 for validation. Thus, we divided it into five groups of 20 eyes each, trained the remaining 80 eyes in each group, and then calculated the correct answer rate for each group by validation with 20 eyes. The Neural Network Console (NNC) developed by Sony and the Keras-Tensorflow backend developed by Google were used as the software for the classification with 16 layers of convolutional neural networks. The active region of the heatmap based on the feature quantity extracted by DL was also evaluated as the percentages with gradient-weighted class activation mapping implemented in Keras. The mean accuracy rate of the validation was 95% for NNC and 88% for Keras. This difference was not significant (P >0.1). The mean active region in the heatmap image was 12.5% in CSC eyes which was significantly lower than the 79.8% in normal eyes (P<0.01). CSC can be automatically diagnosed by DL with high accuracy from en face images of the choroidal vasculature with different programs, convolutional layer structures, and small data sets. Heatmap analyses showed that the DL focused on the area occupied by the choroidal vessels and their uniformity. We conclude that DL can help in the diagnosis of CSC.