A feature agnostic approach for glaucoma detection in OCT volumes

Maetschke, Stefan; Antony, Bhavna J.; Ishikawa, Hiroshi; Wollstein, Gadi; Schuman, Joel S.; Garnavi, Rahil

doi:10.1371/journal.pone.0219126

Cited by 164 publications

(136 citation statements)

References 27 publications

Supporting

Mentioning

128

Contrasting

Unclassified

Order By: Relevance

“…The ability of DL models to use visual cues that are not apparent to the human eye has been previously demonstrated in another study in which retinal angiograms were generated from OCT images [39]. This finding is also consistent with a recent study that used unsegmented OCT scans and reported the involvement of outer retinal layers in a DL model that detects glaucoma [43,77].…”

Section: Discussionsupporting

confidence: 87%

Automated detection of glaucoma with interpretable machine learning using clinical data and multi-modal retinal images

Mehta

Petersen

Wen

et al. 2020

Preprint

View full text Add to dashboard Cite

Glaucoma, the leading cause of irreversible blindness worldwide, is a disease that damages the optic nerve. Current machine learning (ML) approaches for glaucoma detection rely on features such as retinal thickness maps; however, the high rate of segmentation errors when creating these maps increase the likelihood of faulty diagnoses. This paper proposes a new, comprehensive, and more accurate ML-based approach for population-level glaucoma screening. Our contributions include: (1) a multi-modal model built upon a large data set that includes demographic, systemic and ocular data as well as raw image data taken from color fundus photos (CFPs) and macular Optical Coherence Tomography (OCT) scans, (2) model interpretation to identify and explain data features that lead to accurate model performance, and (3) model validation via comparison of model output with clinician interpretation of CFPs. We also validated the model on a cohort that was not diagnosed with glaucoma at the time of imaging but eventually received a glaucoma diagnosis. Results show that our model is highly accurate (AUC 0.97) and interpretable. It validated biological features known to be related to the disease, such as age, intraocular pressure and optic disc morphology. Our model also points to previously unknown or disputed features, such as pulmonary capacity and retinal outer layers.

show abstract

Section: Discussionsupporting

confidence: 87%

Automated detection of glaucoma with interpretable machine learning using clinical data and multi-modal retinal images

Mehta

Petersen

Wen

et al. 2020

Preprint

View full text Add to dashboard Cite

show abstract

“…With surrogate label assignment for VF measurement, the classification module can receive more reliable information from the regression branch. When compared to the pioneering work 3D-CNN [6], our method outperforms it by a large margin, with 4.8%, 5.1%, and 1.6% performance improvement on accuracy, F1 score and AUC at image level. By and large, 3D-CNN has two drawbacks.…”

Section: Experiments and Resultsmentioning

confidence: 82%

“…Hence, several baseline methods, including an existing method as well as three variants of the proposed method, were implemented for comparison: (i). 3D-CNN: the implementation of the approach proposed in [6] which is trained with downsampled 3D volumes. (ii).…”

Section: Experiments and Resultsmentioning

confidence: 99%

“…Differently, Ramzan et al [5] proposed an approach that first segmented inner limiting membrane and retinal pigment epithelium layers in OCT images for cup-to-disc ratio calculation, and then differentiated glaucoma based on the calculated ratio. A pioneering work [6] recently proposed a 3D convolutional neural network (CNN) to directly classify the downsampled OCT volumes into glaucoma or normal, which considerably outperformed various feature-based machine learning algorithms. With respect to modelling the structure-function relationship [7,8], Leite et al utilized locally weighted scatterplot smoothing and regression analysis to evaluate parapapillary RNFL thickness sectors and corresponding topographic standard automated perimetry locations [8].…”

Section: Introductionmentioning

confidence: 99%

See 1 more Smart Citation

Unifying Structure Analysis and Surrogate-Driven Function Regression for Glaucoma OCT Image Screening

Wang

Chen²,

Luo

et al. 2019

Lecture Notes in Computer Science

View full text Add to dashboard Cite

Optical Coherence Tomography (OCT) imaging plays an important role in glaucoma diagnosis in clinical practice. Early detection and timely treatment can prevent glaucoma patients from permanent vision loss. However, only a dearth of automated methods has been developed based on OCT images for glaucoma study. In this paper, we present a novel framework to effectively classify glaucoma OCT images from normal ones. A semi-supervised learning strategy with smoothness assumption is applied for surrogate assignment of missing function regression labels. Besides, the proposed multi-task learning network is capable of exploring the structure and function relationship from the OCT image and visual field measurement simultaneously, which contributes to classification performance boosting. Essentially, we are the first to unify the structure analysis and function regression for glaucoma screening. It is also worth noting that we build the largest glaucoma OCT image dataset involving 4877 volumes to develop and evaluate the proposed method. Extensive experiments demonstrate that our framework outperforms the baseline methods and two glaucoma experts by a large margin, achieving 93.2%, 93.2% and 97.8% on accuracy, F1 score and AUC, respectively.

show abstract

“…14 Deep learning methods, such as convolutional neural networks (CNNs), directly operate on OCT volumes without any human-designed disease markers and can be considered feature-agnostic. 14,15 Most of the recent studies [15][16][17] have looked into optic nerve head OCT scans to detect glaucoma in well curated datasets, which exclude the challenging cases, such as glaucoma suspects, cases with high refractive error, or low signal strength. In this work, we include raw OCT macula scans from real-world scenarios for CNN training, and attempt to differentiate between high-risk cases, which require referral and evaluation by a glaucoma specialist and low-risk cases (split across referable vs. nonreferable disease) that can be observed without frequent testing.…”

Section: Introductionmentioning

confidence: 99%

A 3D Deep Learning System for Detecting Referable Glaucoma Using Full OCT Macular Cube Scans

Russakoff¹,

Mannil

Oakley³

et al. 2020

Trans. Vis. Sci. Tech.

View full text Add to dashboard Cite

Citation: Russakoff DB, Mannil SS, Oakley JD, Ran AR, Cheung CY, Dasari S, Riyazzuddin M, Nagaraj S, Rao HL, Chang D, Chang RT. A 3D deep learning system for detecting referable glaucoma using full OCT macular cube scans. Trans Vis Sci Tech. 2020;9(2):12, https://doi.org/10. 1167/tvst.9.2.12 Purpose: The purpose of this study was to develop a 3D deep learning system from spectral domain optical coherence tomography (SD-OCT) macular cubes to differentiate between referable and nonreferable cases for glaucoma applied to real-world datasets to understand how this would affect the performance.Methods: There were 2805 Cirrus optical coherence tomography (OCT) macula volumes (Macula protocol 512 × 128) of 1095 eyes from 586 patients at a single site that were used to train a fully 3D convolutional neural network (CNN). Referable glaucoma included true glaucoma, pre-perimetric glaucoma, and high-risk suspects, based on qualitative fundus photographs, visual fields, OCT reports, and clinical examinations, including intraocular pressure (IOP) and treatment history as the binary (two class) ground truth. The curated real-world dataset did not include eyes with retinal disease or nonglaucomatous optic neuropathies. The cubes were first homogenized using layer segmentation with the Orion Software (Voxeleron) to achieve standardization. The algorithm was tested on two separate external validation sets from different glaucoma studies, comprised of Cirrus macular cube scans of 505 and 336 eyes, respectively. Results:The area under the receiver operating characteristic (AUROC) curve for the development dataset for distinguishing referable glaucoma was 0.88 for our CNN using homogenization, 0.82 without homogenization, and 0.81 for a CNN architecture from the existing literature. For the external validation datasets, which had different glaucoma definitions, the AUCs were 0.78 and 0.95, respectively. The performance of the model across myopia severity distribution has been assessed in the dataset from the United States and was found to have an AUC of 0.85, 0.92, and 0.95 in the severe, moderate, and mild myopia, respectively. Conclusions:A 3D deep learning algorithm trained on macular OCT volumes without retinal disease to detect referable glaucoma performs better with retinal segmentation preprocessing and performs reasonably well across all levels of myopia.Translational Relevance: Interpretation of OCT macula volumes based on normative data color distributions is highly influenced by population demographics and characteristics, such as refractive error, as well as the size of the normative database. Referable glaucoma, in this study, was chosen to include cases that should be seen by a specialist. This study is unique because it uses multimodal patient data for the glaucoma definition, and includes all severities of myopia as well as validates the algorithm with international data to understand generalizability potential.

show abstract

A feature agnostic approach for glaucoma detection in OCT volumes

Cited by 164 publications

References 27 publications

Automated detection of glaucoma with interpretable machine learning using clinical data and multi-modal retinal images

Automated detection of glaucoma with interpretable machine learning using clinical data and multi-modal retinal images

Unifying Structure Analysis and Surrogate-Driven Function Regression for Glaucoma OCT Image Screening

A 3D Deep Learning System for Detecting Referable Glaucoma Using Full OCT Macular Cube Scans

Contact Info

Product

Resources

About