Accuracy of a deep convolutional neural network in detection of retinitis pigmentosa on ultrawide-field images

Evaluating the discrimination ability of a deep convolution neural network for ultrawide-field pseudocolor imaging and ultrawide-field autofluorescence of retinitis pigmentosa. In total, the 373 ultrawide-field pseudocolor and ultrawide-field autofluorescence images (150, retinitis pigmentosa; 223,...

Full description

Saved in:
Bibliographic Details
Published in:PeerJ (San Francisco, CA) CA), 2019-05, Vol.7, p.e6900, Article e6900
Main Authors: Masumoto, Hiroki, Tabuchi, Hitoshi, Nakakura, Shunsuke, Ohsugi, Hideharu, Enno, Hiroki, Ishitobi, Naofumi, Ohsugi, Eiko, Mitamura, Yoshinori
Format: Article
Language:English
Subjects:
Artificial intelligence
Artificial neural networks
Blindness
Computational Science
Diabetic retinopathy
FDA approval
Fluorescence
Hospitals
Medical imaging
Neural network
Neural networks
Ophthalmology
Photoreceptors
Quality of life
Retina
Retinal diseases
Retinitis
Retinitis pigmentosa
Screening system
Stem cells
Ultrawide-field autofluorescence
Ultrawide-filed pseudocolor imaging
Voretigene neparvovec
Citations: Items that this one cites
Items that cite this one
Online Access:Get full text
Tags: Add Tag
No Tags, Be the first to tag this record!
Description
Summary:Evaluating the discrimination ability of a deep convolution neural network for ultrawide-field pseudocolor imaging and ultrawide-field autofluorescence of retinitis pigmentosa. In total, the 373 ultrawide-field pseudocolor and ultrawide-field autofluorescence images (150, retinitis pigmentosa; 223, normal) obtained from the patients who visited the Department of Ophthalmology, Tsukazaki Hospital were used. Training with a convolutional neural network on these learning data objects was conducted. We examined the -fold cross validation ( = 5). The mean area under the curve of the ultrawide-field pseudocolor group was 0.998 (95% confidence interval (CI) [0.9953-1.0]) and that of the ultrawide-field autofluorescence group was 1.0 (95% CI [0.9994-1.0]). The sensitivity and specificity of the ultrawide-field pseudocolor group were 99.3% (95% CI [96.3%-100.0%]) and 99.1% (95% CI [96.1%-99.7%]), and those of the ultrawide-field autofluorescence group were 100% (95% CI [97.6%-100%]) and 99.5% (95% CI [96.8%-99.9%]), respectively. Heatmaps were in accordance with the clinician's observations. Using the proposed deep neural network model, retinitis pigmentosa can be distinguished from healthy eyes with high sensitivity and specificity on ultrawide-field pseudocolor and ultrawide-field autofluorescence images.
ISSN:2167-8359
2167-8359
DOI:10.7717/peerj.6900