Format

Send to

Choose Destination
PeerJ. 2018 Oct 22;6:e5696. doi: 10.7717/peerj.5696. eCollection 2018.

Accuracy of deep learning, a machine learning technology, using ultra-wide-field fundus ophthalmoscopy for detecting idiopathic macular holes.

Author information

1
Department of Ophthalmology, Tsukazaki Hospital, Himeji City, Hyogo Prefecture, Japan.
2
Rist Inc., Tokyo, Japan.
3
Department of Ophthalmology, Institute of Biomedical Sciences, Tokushima University, Tokushima City, Tokushima Prefecture, Japan.
#
Contributed equally

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.

KEYWORDS:

Algorithm; Convolutional neural network; Deep learning; Macular holes; Optos; Wide- angle camera; Wide-angle ocular fundus camera

Supplemental Content

Full text links

Icon for PeerJ, Inc. Icon for PubMed Central
Loading ...
Support Center