Comparison between support vector machine and deep learning, machine-learning technologies for detecting epiretinal membrane using 3D-OCT

• Published in: International Ophthalmology Vol. 39; no. 8; pp. 1871 - 1877
• Main Authors: Sonobe, Tomoaki, Tabuchi, Hitoshi, Ohsugi, Hideharu, Masumoto, Hiroki, Ishitobi, Naohumi, Morita, Shoji, Enno, Hiroki, Nagasato, Daisuke
• Format: Journal Article
• Language: English
• Published: Dordrecht Springer Science and Business Media LLC 01.08.2019; Springer Netherlands; Springer Nature B.V
• Subjects: Aged; Artificial neural networks; Confidence intervals; Deep Learning; Early Diagnosis; Epiretinal Membrane; Epiretinal Membrane - diagnosis; Female; Humans; Image detection; Imaging, Three-Dimensional; Imaging, Three-Dimensional - methods; Machine Learning; Male; Medical imaging; Medicine; Medicine & Public Health; Membranes; Neural networks; Ophthalmology; Optical Coherence Tomography; Original Paper; Retina; Retina - diagnostic imaging; Sensitivity analysis; Support Vector Machine; Support vector machines; Three dimensional imaging; Three dimensional models; Tomography; Tomography, Optical Coherence; Tomography, Optical Coherence - methods; Training; Visual Acuity; Deep learning; Support vector machine; Epiretinal membrane; Optical coherence tomography
• ISSN: 0165-5701; 1573-2630; 1573-2630
• DOI: 10.1007/s10792-018-1016-x

Purpose In this study, we compared deep learning (DL) with support vector machine (SVM), both of which use three-dimensional optical coherence tomography (3D-OCT) images for detecting epiretinal membrane (ERM). Methods In total, 529 3D-OCT images from the Tsukazaki hospital ophthalmology database (184 non-ERM subjects and 205 ERM patients) were assessed; 80% of the images were divided for training, and 20% for test as follows: 423 training (non-ERM 245, ERM 178) and 106 test (non-ERM 59, ERM 47) images. Using the 423 training images, a model was created with deep convolutional neural network and SVM, and the test data were evaluated. Results The DL model’s sensitivity was 97.6% [95% confidence interval (CI), 87.7–99.9%] and specificity was 98.0% (95% CI, 89.7–99.9%), and the area under the curve (AUC) was 0.993 (95% CI, 0.993–0.994). In contrast, the SVM model’s sensitivity was 97.6% (95% CI, 87.7–99.9%), specificity was 94.2% (95% CI, 84.0–98.7%), and AUC was 0.988 (95% CI, 0.987–0.988). Conclusion DL model is better than SVM model in detecting ERM by using 3D-OCT images.