Deep Learning for Accurate Diagnosis of Glaucomatous Optic Neuropathy Using Digital Fundus Image: A Meta-Analysis

Mohaimenul Islam; Tahmina Nasrin Poly; Hsuan Chia Yang; Suleman Atique; Yu Chuan Jack Li

doi:10.3233/SHTI200141

Deep Learning for Accurate Diagnosis of Glaucomatous Optic Neuropathy Using Digital Fundus Image: A Meta-Analysis

Mohaimenul Islam, Tahmina Nasrin Poly, Hsuan Chia Yang, Suleman Atique, Yu Chuan Jack Li

Research output: Contribution to journal › Article › peer-review

7 Citations (Scopus)

Abstract

We conducted a study to evaluate the algorithms based on deep learning to automatically diagnosis of GON from digital fundus images. A systematic articles search was conducted in PubMed, EMBASE, Google Scholar for the study that investigated the performance of deep learning algorithms for the detection of GON. A total of eight studies were included in this study, of which 5 studies were used to conduct our meta-analysis. The pooled AUROC for detecting GON was 0.98. However, the sensitivity and specificity of deep learning to detect GON were 0.90 (95% CI: 0.90-0.91), and 0.94 (95%CI: 0.93-0.94), respectively.

Original language	English
Pages (from-to)	153-157
Number of pages	5
Journal	Studies in Health Technology and Informatics
Volume	270
DOIs	https://doi.org/10.3233/SHTI200141
Publication status	Published - Jun 16 2020

Keywords

artificial intelligence
deep learning
fundus image
Glaucoma
glaucomatous optic neuropathy

ASJC Scopus subject areas

Biomedical Engineering
Health Informatics
Health Information Management

Access to Document

10.3233/SHTI200141

Cite this

@article{1c329c9789aa4b0b84056bfa15f0d6e3,

title = "Deep Learning for Accurate Diagnosis of Glaucomatous Optic Neuropathy Using Digital Fundus Image: A Meta-Analysis",

abstract = "We conducted a study to evaluate the algorithms based on deep learning to automatically diagnosis of GON from digital fundus images. A systematic articles search was conducted in PubMed, EMBASE, Google Scholar for the study that investigated the performance of deep learning algorithms for the detection of GON. A total of eight studies were included in this study, of which 5 studies were used to conduct our meta-analysis. The pooled AUROC for detecting GON was 0.98. However, the sensitivity and specificity of deep learning to detect GON were 0.90 (95% CI: 0.90-0.91), and 0.94 (95%CI: 0.93-0.94), respectively.",

keywords = "artificial intelligence, deep learning, fundus image, Glaucoma, glaucomatous optic neuropathy",

author = "Mohaimenul Islam and Poly, {Tahmina Nasrin} and Yang, {Hsuan Chia} and Suleman Atique and Li, {Yu Chuan Jack}",

year = "2020",

month = jun,

day = "16",

doi = "10.3233/SHTI200141",

language = "English",

volume = "270",

pages = "153--157",

journal = "Studies in Health Technology and Informatics",

issn = "0926-9630",

publisher = "IOS Press BV",

}

TY - JOUR

T1 - Deep Learning for Accurate Diagnosis of Glaucomatous Optic Neuropathy Using Digital Fundus Image

T2 - A Meta-Analysis

AU - Islam, Mohaimenul

AU - Poly, Tahmina Nasrin

AU - Yang, Hsuan Chia

AU - Atique, Suleman

AU - Li, Yu Chuan Jack

PY - 2020/6/16

Y1 - 2020/6/16

N2 - We conducted a study to evaluate the algorithms based on deep learning to automatically diagnosis of GON from digital fundus images. A systematic articles search was conducted in PubMed, EMBASE, Google Scholar for the study that investigated the performance of deep learning algorithms for the detection of GON. A total of eight studies were included in this study, of which 5 studies were used to conduct our meta-analysis. The pooled AUROC for detecting GON was 0.98. However, the sensitivity and specificity of deep learning to detect GON were 0.90 (95% CI: 0.90-0.91), and 0.94 (95%CI: 0.93-0.94), respectively.

AB - We conducted a study to evaluate the algorithms based on deep learning to automatically diagnosis of GON from digital fundus images. A systematic articles search was conducted in PubMed, EMBASE, Google Scholar for the study that investigated the performance of deep learning algorithms for the detection of GON. A total of eight studies were included in this study, of which 5 studies were used to conduct our meta-analysis. The pooled AUROC for detecting GON was 0.98. However, the sensitivity and specificity of deep learning to detect GON were 0.90 (95% CI: 0.90-0.91), and 0.94 (95%CI: 0.93-0.94), respectively.

KW - artificial intelligence

KW - deep learning

KW - fundus image

KW - Glaucoma

KW - glaucomatous optic neuropathy

UR - http://www.scopus.com/inward/record.url?scp=85086886309&partnerID=8YFLogxK

UR - http://www.scopus.com/inward/citedby.url?scp=85086886309&partnerID=8YFLogxK

U2 - 10.3233/SHTI200141

DO - 10.3233/SHTI200141

M3 - Article

C2 - 32570365

AN - SCOPUS:85086886309

SN - 0926-9630

VL - 270

SP - 153

EP - 157

JO - Studies in Health Technology and Informatics

JF - Studies in Health Technology and Informatics

ER -

Deep Learning for Accurate Diagnosis of Glaucomatous Optic Neuropathy Using Digital Fundus Image: A Meta-Analysis

Abstract

Keywords

ASJC Scopus subject areas

Access to Document

Other files and links

Fingerprint

Cite this