Cargando…

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,...

Descripción completa

Detalles Bibliográficos
Autores principales: Masumoto, Hiroki, Tabuchi, Hitoshi, Nakakura, Shunsuke, Ohsugi, Hideharu, Enno, Hiroki, Ishitobi, Naofumi, Ohsugi, Eiko, Mitamura, Yoshinori
Formato: Online Artículo Texto
Lenguaje:English
Publicado: PeerJ Inc. 2019
Materias:
Acceso en línea:https://www.ncbi.nlm.nih.gov/pmc/articles/PMC6510218/
https://www.ncbi.nlm.nih.gov/pubmed/31119087
http://dx.doi.org/10.7717/peerj.6900
_version_ 1783417392653664256
author Masumoto, Hiroki
Tabuchi, Hitoshi
Nakakura, Shunsuke
Ohsugi, Hideharu
Enno, Hiroki
Ishitobi, Naofumi
Ohsugi, Eiko
Mitamura, Yoshinori
author_facet Masumoto, Hiroki
Tabuchi, Hitoshi
Nakakura, Shunsuke
Ohsugi, Hideharu
Enno, Hiroki
Ishitobi, Naofumi
Ohsugi, Eiko
Mitamura, Yoshinori
author_sort Masumoto, Hiroki
collection PubMed
description 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 K-fold cross validation (K = 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.
format Online
Article
Text
id pubmed-6510218
institution National Center for Biotechnology Information
language English
publishDate 2019
publisher PeerJ Inc.
record_format MEDLINE/PubMed
spelling pubmed-65102182019-05-22 Accuracy of a deep convolutional neural network in detection of retinitis pigmentosa on ultrawide-field images Masumoto, Hiroki Tabuchi, Hitoshi Nakakura, Shunsuke Ohsugi, Hideharu Enno, Hiroki Ishitobi, Naofumi Ohsugi, Eiko Mitamura, Yoshinori PeerJ Ophthalmology 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 K-fold cross validation (K = 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. PeerJ Inc. 2019-05-07 /pmc/articles/PMC6510218/ /pubmed/31119087 http://dx.doi.org/10.7717/peerj.6900 Text en © 2019 Masumoto et al. http://creativecommons.org/licenses/by/4.0/ This is an open access article distributed under the terms of the Creative Commons Attribution License (http://creativecommons.org/licenses/by/4.0/) , which permits unrestricted use, distribution, reproduction and adaptation in any medium and for any purpose provided that it is properly attributed. For attribution, the original author(s), title, publication source (PeerJ) and either DOI or URL of the article must be cited.
spellingShingle Ophthalmology
Masumoto, Hiroki
Tabuchi, Hitoshi
Nakakura, Shunsuke
Ohsugi, Hideharu
Enno, Hiroki
Ishitobi, Naofumi
Ohsugi, Eiko
Mitamura, Yoshinori
Accuracy of a deep convolutional neural network in detection of retinitis pigmentosa on ultrawide-field images
title Accuracy of a deep convolutional neural network in detection of retinitis pigmentosa on ultrawide-field images
title_full Accuracy of a deep convolutional neural network in detection of retinitis pigmentosa on ultrawide-field images
title_fullStr Accuracy of a deep convolutional neural network in detection of retinitis pigmentosa on ultrawide-field images
title_full_unstemmed Accuracy of a deep convolutional neural network in detection of retinitis pigmentosa on ultrawide-field images
title_short Accuracy of a deep convolutional neural network in detection of retinitis pigmentosa on ultrawide-field images
title_sort accuracy of a deep convolutional neural network in detection of retinitis pigmentosa on ultrawide-field images
topic Ophthalmology
url https://www.ncbi.nlm.nih.gov/pmc/articles/PMC6510218/
https://www.ncbi.nlm.nih.gov/pubmed/31119087
http://dx.doi.org/10.7717/peerj.6900
work_keys_str_mv AT masumotohiroki accuracyofadeepconvolutionalneuralnetworkindetectionofretinitispigmentosaonultrawidefieldimages
AT tabuchihitoshi accuracyofadeepconvolutionalneuralnetworkindetectionofretinitispigmentosaonultrawidefieldimages
AT nakakurashunsuke accuracyofadeepconvolutionalneuralnetworkindetectionofretinitispigmentosaonultrawidefieldimages
AT ohsugihideharu accuracyofadeepconvolutionalneuralnetworkindetectionofretinitispigmentosaonultrawidefieldimages
AT ennohiroki accuracyofadeepconvolutionalneuralnetworkindetectionofretinitispigmentosaonultrawidefieldimages
AT ishitobinaofumi accuracyofadeepconvolutionalneuralnetworkindetectionofretinitispigmentosaonultrawidefieldimages
AT ohsugieiko accuracyofadeepconvolutionalneuralnetworkindetectionofretinitispigmentosaonultrawidefieldimages
AT mitamurayoshinori accuracyofadeepconvolutionalneuralnetworkindetectionofretinitispigmentosaonultrawidefieldimages