Artificial intelligence (AI) can detect diabetic macular edema (DME) from optical coherence tomography (OCT) images. We aimed to evaluate the performance of deep learning neural networks in DME detection.
Methods
Embase, Pubmed, the Cochrane Library, and IEEE Xplore were searched up to August 14, 2021. We included studies using deep learning algorithms to detect DME from OCT images. Two reviewers extracted the data independently, and the Quality Assessment of Diagnostic Accuracy Studies-2 (QUADAS-2) tool was applied to assess the risk of bias. The study is reported according to Preferred Reporting Items for a Systematic Review and Meta-analysis of Diagnostic Test Accuracy Studies (PRISMA-DTA).
Results
Ninteen studies involving 41005 subjects were included. The pooled sensitivity and specificity were 96.0% (95% confidence interval (CI): 93.9% to 97.3%) and 99.3% (95% CI: 98.2% to 99.7%), respectively. Subgroup analyses found that data set selection, sample size of training set and the choice of OCT devices contributed to the heterogeneity (all P < 0.05). While there was no association between the diagnostic accuracy and transfer learning adoption or image management (all P > 0.05).
Conclusions
Deep learning methods, particularly the convolutional neural networks (CNNs) could effectively detect clinically significant DME, which can provide referral suggestions to the patients.
YuKHBeamALKohaneIS. Artificial intelligence in healthcare. Nat. Biomed. Eng.2018; 2: 719–731.
6.
AbràmoffMDLavinPTBirchM, et al.Pivotal trial of an autonomous AI-based diagnostic system for detection of diabetic retinopathy in primary care offices. npj Digit. Med.2018; 1.
7.
GrassmannF, et al.A deep learning Algorithm for prediction of age-related eye disease study severity scale for age-related macular degeneration from color Fundus photography. Ophthalmology2018; 125: 1410–1420.
8.
SudhaSSrinivasanA. Unravelling diabetic retinopathy through image processing, neural networks, and fuzzy logic: a review. Asian J. Pharm. Clin. Res2017; 10: 32–37.
9.
MacaskillPGatsonisC, DeeksJ, et al.Handbook for DTA reviews. London: Cochrane Collaboration, 2011.
10.
SalamehJP, et al.Preferred reporting items for systematic review and meta-analysis of diagnostic test accuracy studies (PRISMA-DTA): explanation, elaboration, and checklistBr Med J2020; 370.
11.
Diabetic Retinopathy Clinical Research Network Web site. http:// public.drcr.net/Accessed on February 20, 2007.
12.
AlqudahAM. AOCT-NET : a convolutional network automated classification of multiclass retinal diseases using spectral-ddomain optical coherence tomography images. Medical & biological engineering & computing2020;; 58: 41–53.
13.
BhatiaKK, et al.Disease classification of macular optical coherence tomography scans using deep learning software. Retina2020; 40: 1549–1557.
14.
ChanGCY, et al.Transfer learning for diabetic macular edema (DME) detection on optical coherence tomography (OCT) images. Proc. 2017 IEEE Int. Conf. Signal Image Process. Appl. ICSIPA 20172017: 493–496. doi:10.1109/ICSIPA.2017.8120662
15.
DasVDandapatSBoraPK. Multi-scale deep feature fusion for automated classification of macular pathologies from OCT images. Biomed. Signal Process. Control2019; 54: 101605.
16.
HwangDK, et al.Optical coherence tomography-based diabetic macula edema screening with artificial intelligence. J. Chinese Med. Assoc2020; 83: 1034–1038.
17.
KambleRM, et al.Automated diabetic macular edema (DME) analysis using fine tuning with inception-resnet-v2 on oct images. 2018 IEEE EMBS Conf. Biomed. Eng. Sci. IECBES 2018 - Proc.2019, cl, 442–446.
18.
KaymakSSerenerA. Automated age-related macular degeneration and diabetic macular edema detection on OCT images using deep learning. Proc. - 2018 IEEE 14th Int. Conf. Intell. Comput. Commun. Process. ICCP 20182018, 265–269 doi:10.1109/ICCP.2018.8516635.
19.
KermanyDS, et al.Identifying medical diagnoses and treatable diseases by image-based deep learning. Cell2018; 172: 1122–1131. e9.
20.
LiFChenHLiuZ, et al.Fully automated detection of retinal disorders by image-based deep learning. Graefe's Arch. Clin. Exp. Ophthalmol2019; 257: 495–505.
21.
PaulDTewariAGhoshS, et al.OCTx: ensembled deep learning model to detect retinal disorders. Proc. - IEEE Symp. Comput. Med. Syst2020; 2020: 526–531.
22.
PerdomoOOtaloraSGonzalezFA, et al.OCT-NET: a convolutional network for automatic classification of normal and diabetic macular edema using sd-oct volumes. Proc. - Int. Symp. Biomed. Imaging2018; 2018: 1423–1426.
23.
RastogiDPadhyRPSaPK. Detection of retinal disorders in optical coherence tomography using deep learning. 2019 10th Int. Conf. Comput. Commun. Netw. Technol. ICCCNT 2019, doi:10.1109/ICCCNT45670.2019.8944406.
24.
SertkayaMEErgenBTogacarM. Diagnosis of Eye Retinal Diseases Based on Convolutional Neural Networks Using Optical Coherence Images. Proc. 23rd Int. Conf. Electron. 2019, Electron. 2019, doi:10.1109/ELECTRONICS.2019.8765579.
25.
TsujiT, et al.Classification of optical coherence tomography images using a capsule network. BMC Ophthalmol2020; 20: 1–9.
26.
WangDWangL. On OCT image classification via deep learning. IEEE Photonics J2019; 11: 1–14.
27.
WuQ, et al.Detection of morphologic patterns of diabetic macular edema using a deep learning approach based on optical coherence tomography images. Retina2021; 41: 1110–1117.
28.
ReitsmaJB, et al.Research and reporting methods accuracy studies. Ann. Intern. Med2011; 155: 529–536.
29.
DeeksJJMacaskillPIrwigL. The performance of tests of publication bias and other sample size effects in systematic reviews of diagnostic test accuracy was assessed. J. Clin. Epidemiol2005; 58: 882–893.
30.
WongTYSabanayagamC. Strategies to tackle the global burden of diabetic retinopathy: from epidemiology to artificial intelligence. Ophthalmologica2020; 243: 9–20.
31.
WangYTTadaratiMWolfsonY, et al.Comparison of prevalence of diabetic macular edema based on monocular fundus photography vs optical coherence tomography. JAMA Ophthalmol2016; 134: 222–228.
32.
PoplinR, et al.Prediction of cardiovascular risk factors from retinal fundus photographs via deep learning. Nat. Biomed. Eng2018; 2: 158–164.
33.
CheungCYLIkramMKChenC, et al.Imaging retina to study dementia and stroke. Prog. Retin. Eye Res2017; 57: 89–107.
34.
GulshanV, et al.Development and validation of a deep learning algorithm for detection of diabetic retinopathy in retinal fundus photographs. JAMA - J. Am. Med. Assoc2016; 316: 2402–2410.
35.
HassanBHassanT and LiB. Deep ensemble learning based objective grading of macular edema by extracting clinically significant findings from fused retinal imaging modalities. Sensors (Switzerland)2019; 19: 1736.
36.
LecunYBengioYHintonG. Deep learning. Nature2015; 521: 436–444.
37.
ShinHC, et al.Deep convolutional neural networks for computer-aided detection: CNN architectures, dataset characteristics and transfer learning. IEEE Trans Med Imaging2016; 35: 1285–1298.
38.
SchmittJMXiangSHYungKM. Speckle in optical coherence tomography. J. Biomed. Opt1999; 4: 95–105.
39.
NiuY, et al.Pathological evidence exploration in deep retinal image diagnosis. AAAI-19, 2018.
