Abstract
We aimed to investigate the detection of idiopathic macular holes (MHs) using ultra-wide-field fundus images (Optos) with deep learning, which is a machine learning technology. The study included 910 Optos color images (715 normal images, 195 MH images). Of these 910 images, 637 were learning images (501 normal images, 136 MH images) and 273 were test images (214 normal images and 59 MH images). We conducted training with a deep convolutional neural network (CNN) using the images and constructed a deep-learning model. The CNN exhibited high sensitivity of 100% (95% confidence interval CI [93.5–100%]) and high specificity of 99.5% (95% CI [97.1–99.9%]). The area under the curve was 0.9993 (95% CI [0.9993–0.9994]). Our findings suggest that MHs could be diagnosed using an approach involving wide angle camera images and deep learning.
Highlights
In 1988, Gass described idiopathic macular holes (MHs) as a retinal break commonly involving the fovea (Gass, 1988), and in 1991 Kelly and Wendel reported that MHs can be successfully repaired through vitreous surgery (Kelly & Wendel, 1991)
How to cite this article Nagasawa et al (2018), Accuracy of deep learning, a machine learning technology, using ultra-wide-field fundus ophthalmoscopy for detecting idiopathic macular holes
The study dataset included 910 Optos color images obtained at the Tsukazaki Hospital (Himeji, Japan) and Tokushima University Hospital (715 normal images and 195 MH images)
Summary
In 1988, Gass described idiopathic macular holes (MHs) as a retinal break commonly involving the fovea (Gass, 1988), and in 1991 Kelly and Wendel reported that MHs can be successfully repaired through vitreous surgery (Kelly & Wendel, 1991). The accepted pathogenesis has macular hole formation proceeding in stages from an impending hole to a full thickness MH, with visual acuity deteriorating to less than 6/60 in 85% of cases (Luckie & Heriot, 1995). The development of optical coherence tomography (OCT) and improvement of image resolution have made the diagnosis of macular diseases substantially easy (Kishi & Takahashi, 2000). How to cite this article Nagasawa et al (2018), Accuracy of deep learning, a machine learning technology, using ultra-wide-field fundus ophthalmoscopy for detecting idiopathic macular holes.
Talk to us
Join us for a 30 min session where you can share your feedback and ask us any queries you have