Deep Learning and Glaucoma Specialists

Phene, Sonia; Dunn, R. Carter; Hammel, Naama; Liu, Yun; Krause, Jonathan; Kitade, Naho; Schaekermann, Mike; Sayres, Rory; Wu, Daniel; Bora, Ashish; Semturs, Christopher; Misra, Anita; Huang, Abigail E.; Spitze, Arielle; Medeiros, Felipe A.; Maa, April Y.; Gandhi, Monica; Corrado, Greg S.; Peng, Lily; Webster, Dale R.

doi:10.1016/j.ophtha.2019.07.024

Cited by 134 publications

(65 citation statements)

References 49 publications

(41 reference statements)

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Several studies attempted to explain the deep learning model’s decision in glaucoma classification from fundus images 20 , 23 – 26 , 28 , 31 , 35 . The majority of explainability studies 20 , 24 , 28 employed some form of occlusion 36 , a technique in which parts of the test images are perturbed, and the effect on performance recorded.…”

Section: Introductionmentioning

confidence: 99%

Deep learning on fundus images detects glaucoma beyond the optic disc

Hemelings

Elen

Breda

et al. 2021

Sci Rep

View full text Add to dashboard Cite

Although unprecedented sensitivity and specificity values are reported, recent glaucoma detection deep learning models lack in decision transparency. Here, we propose a methodology that advances explainable deep learning in the field of glaucoma detection and vertical cup-disc ratio (VCDR), an important risk factor. We trained and evaluated deep learning models using fundus images that underwent a certain cropping policy. We defined the crop radius as a percentage of image size, centered on the optic nerve head (ONH), with an equidistant spaced range from 10–60% (ONH crop policy). The inverse of the cropping mask was also applied (periphery crop policy). Trained models using original images resulted in an area under the curve (AUC) of 0.94 [95% CI 0.92–0.96] for glaucoma detection, and a coefficient of determination (R2) equal to 77% [95% CI 0.77–0.79] for VCDR estimation. Models that were trained on images with absence of the ONH are still able to obtain significant performance (0.88 [95% CI 0.85–0.90] AUC for glaucoma detection and 37% [95% CI 0.35–0.40] R2 score for VCDR estimation in the most extreme setup of 60% ONH crop). Our findings provide the first irrefutable evidence that deep learning can detect glaucoma from fundus image regions outside the ONH.

show abstract

Section: Introductionmentioning

confidence: 99%

Deep learning on fundus images detects glaucoma beyond the optic disc

Hemelings

Elen

Breda

et al. 2021

Sci Rep

View full text Add to dashboard Cite

show abstract

“…Artificial intelligence (AI) technology has been employed to diagnose eye diseases, such as age-related macular degeneration, 14 glaucoma 15 and diabetic retinopathy 16 for several years. Nevertheless, so far, the application of big data-based AI in ICL implantation has not been reported yet.…”

Section: Clinical Sciencementioning

confidence: 99%

Big-data and artificial-intelligence-assisted vault prediction and EVO-ICL size selection for myopia correction

et al. 2021

View full text Add to dashboard Cite

AimsTo predict the vault and the EVO-implantable collamer lens (ICL) size by artificial intelligence (AI) and big data analytics.MethodsSix thousand two hundred and ninety-seven eyes implanted with an ICL from 3536 patients were included. The vault values were measured by the anterior segment analyzer (Pentacam HR). Permutation importance and Impurity-based feature importance are used to investigate the importance between the vault and input parameters. Regression models and classification models are applied to predict the vault. The ICL size is set as the target of the prediction, and the vault and the other input features are set as the new inputs for the ICL size prediction. Data were collected from 2015 to 2020. Random Forest, Gradient Boosting and XGBoost were demonstrated satisfying accuracy and mean area under the curve (AUC) scores in vault predicting and ICL sizing.ResultsIn the prediction of the vault, the Random Forest has the best results in the regression model (R2=0.315), then follows the Gradient Boosting (R2=0.291) and XGBoost (R2=0.285). The maximum classification accuracy is 0.828 in Random Forest, and the mean AUC is 0.765. The Random Forest predicts the ICL size with an accuracy of 82.2% and the Gradient Boosting and XGBoost, which are also compatible with 81.5% and 81.8% accuracy, respectively.ConclusionsRandom Forest, Gradient Boosting and XGBoost models are applicable for vault predicting and ICL sizing. AI may assist ophthalmologists in improving ICL surgery safety, designing surgical strategies, and predicting clinical outcomes.

show abstract

“…The system obtained 94% accuracy when tested on a dataset of 1205 images. 22 Likewise in Raghavendra et al, 23 eight layered CNN has been trained using 1426 fundus images. The system attained 98% accuracy.…”

Section: Non-structural Analysismentioning

confidence: 99%

“…The challenge is to detect changes in the ONH region even at an initial level. 14,15,22 5.2 | OCT imaging modality 1. A low quality image with poor visualization of image components is a generic problem in the OCT images with speckle noise.…”

Section: Fundus Imaging Modalitymentioning

confidence: 99%

A study to identify limitations of existing automated systems to detect glaucoma at initial and curable stage

Khalil

Akram

Khalid

et al. 2021

Int J Imaging Syst Tech

View full text Add to dashboard Cite

Glaucoma ocular disease is the second topmost reason for irreversible visual impairment around the world. This malady can be cured and permanent blindness can be prevented by timely diagnosis and treatment. This study is an attempt to analyse the current status of automated glaucoma diagnosis systems.Existing systems have been analysed on the base of ophthalmic imaging technology, capability to detect glaucoma at initial or latter stages, detection strategy and performance. Analysis revealed several research gaps mainly in automated glaucoma detection based on Fundus and Optical Coherence Tomography (OCT) ophthalmic imaging technologies. More accurate diagnosis of glaucoma at early and curable stages is possible by bridging the identified gaps.

show abstract

Deep Learning and Glaucoma Specialists

Cited by 134 publications

References 49 publications

Deep learning on fundus images detects glaucoma beyond the optic disc

Deep learning on fundus images detects glaucoma beyond the optic disc

Big-data and artificial-intelligence-assisted vault prediction and EVO-ICL size selection for myopia correction

A study to identify limitations of existing automated systems to detect glaucoma at initial and curable stage

Contact Info

Product

Resources

About