Evaluation of an AI system for the automated detection of glaucoma from stereoscopic optic disc photographs: the European Optic Disc Assessment Study

Rogers, Thomas W.; Jaccard, Nicolas; Carbonaro, Francis; Lemij, Hans G; Vermeer, Koenraad A.; Reus, Nicolaas J.; Trikha, Sameer

doi:10.1038/s41433-019-0510-3

Cited by 38 publications

(33 citation statements)

References 16 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Only eight studies 14 – 21 used prospectively collected data and 29 (refs. 14 , 15 , 17 , 18 , 21 – 45 ) studies validated algorithms on external datasets. No studies provided a prespecified sample size calculation.…”

Section: Resultsmentioning

confidence: 99%

Diagnostic accuracy of deep learning in medical imaging: a systematic review and meta-analysis

et al. 2021

View full text Add to dashboard Cite

Deep learning (DL) has the potential to transform medical diagnostics. However, the diagnostic accuracy of DL is uncertain. Our aim was to evaluate the diagnostic accuracy of DL algorithms to identify pathology in medical imaging. Searches were conducted in Medline and EMBASE up to January 2020. We identified 11,921 studies, of which 503 were included in the systematic review. Eighty-two studies in ophthalmology, 82 in breast disease and 115 in respiratory disease were included for meta-analysis. Two hundred twenty-four studies in other specialities were included for qualitative review. Peer-reviewed studies that reported on the diagnostic accuracy of DL algorithms to identify pathology using medical imaging were included. Primary outcomes were measures of diagnostic accuracy, study design and reporting standards in the literature. Estimates were pooled using random-effects meta-analysis. In ophthalmology, AUC’s ranged between 0.933 and 1 for diagnosing diabetic retinopathy, age-related macular degeneration and glaucoma on retinal fundus photographs and optical coherence tomography. In respiratory imaging, AUC’s ranged between 0.864 and 0.937 for diagnosing lung nodules or lung cancer on chest X-ray or CT scan. For breast imaging, AUC’s ranged between 0.868 and 0.909 for diagnosing breast cancer on mammogram, ultrasound, MRI and digital breast tomosynthesis. Heterogeneity was high between studies and extensive variation in methodology, terminology and outcome measures was noted. This can lead to an overestimation of the diagnostic accuracy of DL algorithms on medical imaging. There is an immediate need for the development of artificial intelligence-specific EQUATOR guidelines, particularly STARD, in order to provide guidance around key issues in this field.

show abstract

Section: Resultsmentioning

confidence: 99%

Diagnostic accuracy of deep learning in medical imaging: a systematic review and meta-analysis

et al. 2021

View full text Add to dashboard Cite

show abstract

“…Raghavendra et al 27 have achieved the highest accuracy of 98.13% using only 18 layers of CNN. Rogers et al 28 have evaluated the performance of a deep learning-based artificial intelligence software for detection of glaucoma from stereoscopic optic disc photographs in the European Optic Disc Assessment Study, and the system has obtained a diagnostic performance and repeatability comparable to that of a large cohort of ophthalmologists and optometrists. Shibata et al 16 have validated the diagnostic ability of the deep residual learning algorithm in highly myopic eyes which makes the detection of glaucoma a challenging task because of the morphological difference from those of non-highly myopic eyes.…”

Section: Discussionmentioning

confidence: 99%

“…[12][13][14][15][16][17][18][19][27][28][29] Although most of recent studies have been suggested numerous potential and vision in this field, various stages and structure-function correlations of the glaucoma have received little attention. The results of our study show agree with those found in earlier investigations with an accuracy of 83.4-98.1% 13,17,[27][28][29] and an AUROC of 0.887-0.996, 12,[14][15][16][17][18][19] and moreover this study enhanced the research by applying a third classification grade to the glaucoma severity based on functional tests. That third level of diagnostics can provide primary care with greater detail at an earlier stage improving the disease management, reducing the chances of blindness, and ultimately reducing the overall medical costs to the patient.…”

Section: Discussionmentioning

confidence: 99%

“…Weak coordination between structure and function is another limitation of previous studies. Clinical data is often labeled by focusing only on structural tests including fundus photographs 12,[15][16][17][18][19][27][28][29] and OCT scans, 13,19 although, glaucoma is a chronic progressive optic neuropathy with corresponding glaucomatous VF defects. In addition, the results of the current study were not inferior to an attempt to use deep learning for analysis of functional test (AUROC 0.926) that preperimetric glaucomatous VF could be distinguished from normal controls.…”

Section: Discussionmentioning

confidence: 99%

See 1 more Smart Citation

Deep Learning Ensemble Method for Classifying Glaucoma Stages Using Fundus Photographs and Convolutional Neural Networks

Cho

Hwang

Chung

et al. 2021

Current Eye Research

View full text Add to dashboard Cite

Purpose: This study developed and evaluated a deep learning ensemble method to automatically grade the stages of glaucoma depending on its severity. Materials and Methods: After cross-validation of three glaucoma specialists, the final dataset comprised of 3,460 fundus photographs taken from 2,204 patients were divided into three classes: unaffected controls, early-stage glaucoma, and late-stage glaucoma. The mean deviation value of standard automated perimetry was used to classify the glaucoma cases. We modeled 56 convolutional neural networks (CNN) with different characteristics and developed an ensemble system to derive the best performance by combining several modeling results. Results: The proposed method with an accuracy of 88.1% and an average area under the receiver operating characteristic of 0.975 demonstrates significantly better performance to classify glaucoma stages compared to the best single CNN model that has an accuracy of 85.2% and an average area under the receiver operating characteristic of 0.950. The false negative is the least adjacent misprediction, and it is less in the proposed method than in the best single CNN model. Conclusions: The method of averaging multiple CNN models can better classify glaucoma stages by using fundus photographs than a single CNN model. The ensemble method would be useful as a clinical decision support system in glaucoma screening for primary care because it provides high and stable performance with a relatively small amount of data.

show abstract

“…The system is designed to generalize to any fundus photograph that contains the optic disc, by first using a CNN to find and extract the optic nerve and then feeding a standardized image to another CNN that performs the classification. In a study by Rogers and colleagues, 55 the Pegasus AI system was compared to 243 European Ophthalmologists and 208 British optometrists in grading photographs for the presence of glaucomatous damage, achieving an overall accuracy of 83.4% and an area under the receive operating characteristic curve of 0.871, which was comparable to that of average ophthalmologists and optometrists.…”

Section: Introductionmentioning

confidence: 96%

A Review of Deep Learning for Screening, Diagnosis, and Detection of Glaucoma Progression

Thompson

Jammal

Medeiros

2020

Trans. Vis. Sci. Tech.

130

View full text Add to dashboard Cite

Because of recent advances in computing technology and the availability of large datasets, deep learning has risen to the forefront of artificial intelligence, with performances that often equal, or sometimes even exceed, those of human subjects on a variety of tasks, especially those related to image classification and pattern recognition. As one of the medical fields that is highly dependent on ancillary imaging tests, ophthalmology has been in a prime position to witness the application of deep learning algorithms that can help analyze the vast amount of data coming from those tests. In particular, glaucoma stands as one of the conditions where application of deep learning algorithms could potentially lead to better use of the vast amount of information coming from structural and functional tests evaluating the optic nerve and macula. The purpose of this article is to critically review recent applications of deep learning models in glaucoma, discussing their advantages but also focusing on the challenges inherent to the development of such models for screening, diagnosis and detection of progression. After a brief general overview of deep learning and how it compares to traditional machine learning classifiers, we discuss issues related to the training and validation of deep learning models and how they specifically apply to glaucoma. We then discuss specific scenarios where deep learning has been proposed for use in glaucoma, such as screening with fundus photography, and diagnosis and detection of glaucoma progression with optical coherence tomography and standard automated perimetry. Translational Relevance Deep learning algorithms have the potential to significantly improve diagnostic capabilities in glaucoma, but their application in clinical practice requires careful validation, with consideration of the target population, the reference standards used to build the models, and potential sources of bias.

show abstract

Evaluation of an AI system for the automated detection of glaucoma from stereoscopic optic disc photographs: the European Optic Disc Assessment Study

Cited by 38 publications

References 16 publications

Diagnostic accuracy of deep learning in medical imaging: a systematic review and meta-analysis

Diagnostic accuracy of deep learning in medical imaging: a systematic review and meta-analysis

Deep Learning Ensemble Method for Classifying Glaucoma Stages Using Fundus Photographs and Convolutional Neural Networks

A Review of Deep Learning for Screening, Diagnosis, and Detection of Glaucoma Progression

Contact Info

Product

Resources

About