Jorge Cuadros

Development and Validation of a Deep Learning Algorithm for Detection of Diabetic Retinopathy in Retinal Fundus Photographs.

Importance Deep learning is a family of computational methods that allow an algorithm to program itself by learning from a large set of examples that demonstrate the desired behavior, removing the need to specify rules explicitly. Application of these methods to medical imaging requires further assessment and validation. Objective To apply deep learning to create an algorithm for automated detection of diabetic retinopathy and diabetic macular edema in retinal fundus photographs. Design and Setting A specific type of neural network optimized for image classification called a deep convolutional neural network was trained using a retrospective development data set of 128 175 retinal images, which were graded 3 to 7 times for diabetic retinopathy, diabetic macular edema, and image gradability by a panel of 54 US licensed ophthalmologists and ophthalmology senior residents between May and December 2015. The resultant algorithm was validated in January and February 2016 using 2 separate data sets, both graded by at least 7 US board-certified ophthalmologists with high intragrader consistency. Exposure Deep learning-trained algorithm. Main Outcomes and Measures The sensitivity and specificity of the algorithm for detecting referable diabetic retinopathy (RDR), defined as moderate and worse diabetic retinopathy, referable diabetic macular edema, or both, were generated based on the reference standard of the majority decision of the ophthalmologist panel. The algorithm was evaluated at 2 operating points selected from the development set, one selected for high specificity and another for high sensitivity. Results The EyePACS-1 data set consisted of 9963 images from 4997 patients (mean age, 54.4 years; 62.2% women; prevalence of RDR, 683/8878 fully gradable images [7.8%]); the Messidor-2 data set had 1748 images from 874 patients (mean age, 57.6 years; 42.6% women; prevalence of RDR, 254/1745 fully gradable images [14.6%]). For detecting RDR, the algorithm had an area under the receiver operating curve of 0.991 (95% CI, 0.988-0.993) for EyePACS-1 and 0.990 (95% CI, 0.986-0.995) for Messidor-2. Using the first operating cut point with high specificity, for EyePACS-1, the sensitivity was 90.3% (95% CI, 87.5%-92.7%) and the specificity was 98.1% (95% CI, 97.8%-98.5%). For Messidor-2, the sensitivity was 87.0% (95% CI, 81.1%-91.0%) and the specificity was 98.5% (95% CI, 97.7%-99.1%). Using a second operating point with high sensitivity in the development set, for EyePACS-1 the sensitivity was 97.5% and specificity was 93.4% and for Messidor-2 the sensitivity was 96.1% and specificity was 93.9%. Conclusions and Relevance In this evaluation of retinal fundus photographs from adults with diabetes, an algorithm based on deep machine learning had high sensitivity and specificity for detecting referable diabetic retinopathy. Further research is necessary to determine the feasibility of applying this algorithm in the clinical setting and to determine whether use of the algorithm could lead to improved care and outcomes compared with current ophthalmologic assessment.

EyePACS: An Adaptable Telemedicine System for Diabetic Retinopathy Screening

Background: Annual retinal screening of patients with diabetes is the standard clinical practice to prevent visual impairment and blindness from diabetic retinopathy. Telemedicine-based diabetic retinopathy screening (DRS) in primary care settings can effectively detect sight-threatening retinopathy and significantly increase compliance with annual retinal exams. EyePACS is a license-free Web-based DRS system designed to simplify the process of image capture, transmission, and review. The system provides a flexible platform for collaboration among clinicians about diabetic retinopathy. Methods: Primary clinic personnel (i.e., nursing, technical, or administrative staff) are trained and certified by the EyePACS program to acquire retinal images from standard digital retinal cameras. Relevant clinical data and eight high-resolution images per patient (two external and six retinal images) are encrypted and transmitted to a secure Internet server, using a standard computer and Web browser. Images are then interpreted by certified EyePACS reviewers or local eye care providers who are certified through the EyePACS Retinopathy Grading System. Reports indicating retinopathy level and referral recommendations are transmitted back to primary care providers through the EyePACS Web site or through interfaces between EyePACS and Health Level 7-compliant electronic medical records or chronic disease registries. Results: The pilot phase of the EyePACS DRS program in California (2005–2006) recorded 3562 encounters. Since 2006, EyePACS has been expanded to over 120 primary care sites throughout California and elsewhere recording over 34,000 DRSs. The overall rate of referral is 8.21% for sight-threatening retinopathy and 7.83% for other conditions (e.g., cataract and glaucoma). Conclusion: The use of license-free Web-based software, standard interfaces, and flexible protocols has allowed primary care providers to adopt retinopathy screening with minimal effort and resources.

Automated Diabetic Retinopathy Screening and Monitoring Using Retinal Fundus Image Analysis

Background: Diabetic retinopathy (DR)—a common complication of diabetes—is the leading cause of vision loss among the working-age population in the western world. DR is largely asymptomatic, but if detected at early stages the progression to vision loss can be significantly slowed. With the increasing diabetic population there is an urgent need for automated DR screening and monitoring. To address this growing need, in this article we discuss an automated DR screening tool and extend it for automated estimation of microaneurysm (MA) turnover, a potential biomarker for DR risk. Methods: The DR screening tool automatically analyzes color retinal fundus images from a patient encounter for the various DR pathologies and collates the information from all the images belonging to a patient encounter to generate a patient-level screening recommendation. The MA turnover estimation tool aligns retinal images from multiple encounters of a patient, localizes MAs, and performs MA dynamics analysis to evaluate new, persistent, and disappeared lesion maps and estimate MA turnover rates. Results: The DR screening tool achieves 90% sensitivity at 63.2% specificity on a data set of 40 542 images from 5084 patient encounters obtained from the EyePACS telescreening system. On a subset of 7 longitudinal pairs the MA turnover estimation tool identifies new and disappeared MAs with 100% sensitivity and average false positives of 0.43 and 1.6 respectively. Conclusions: The presented automated tools have the potential to address the growing need for DR screening and monitoring, thereby saving vision of millions of diabetic patients worldwide.

Utility of hard exudates for the screening of macular edema.

Purpose The purpose of this study was to determine whether hard exudates (HEs) within one disc diameter of the foveola is an acceptable criterion for the referral of diabetic patients suspected of clinically significant macular edema (CSME) in a screening setting. Methods One hundred forty-three adults diagnosed as having diabetes mellitus were imaged using a nonmydriatic digital fundus camera at the Alameda County Medical Center in Oakland, CA. Nonstereo fundus images were graded independently for the presence of HE near the center of the macula by two graders according to the EyePACS grading protocol. The patients also received a dilated fundus examination on a separate visit. Clinically significant macular edema was determined during the dilated fundus examination using the criteria set forth by the Early Treatment Diabetic Retinopathy Study. Subsequently, the sensitivity and specificity of HEs within one disc diameter of the foveola in nonstereo digital images used as a surrogate for the detection of CSME diagnosed by live fundus examination were calculated. Results The mean (±SD) age of 103 patients included in the analysis was 56 ± 17 years. Clinically significant macular edema was diagnosed in 15.5% of eyes during the dilated examination. For the right eyes, the sensitivity of HEs within one disc diameter from the foveola as a surrogate for detecting CSME was 93.8% for each of the graders; the specificity values were 88.5 and 85.1%. For the left eyes, the sensitivity values were 93.8 and 75% for each of the two graders, respectively; the specificity was 87.4% for both graders. Conclusions This study supports the use of HE within a disc diameter of the center of the macula in nonstereo digital images for CSME detection in a screening setting.

Comparison of Cysts in Red and Green Images for Diabetic Macular Edema

ABSTRACT Purpose To investigate whether cysts in diabetic macular edema are better visualized in the red channel of color fundus camera images, as compared with the green channel, because color fundus camera screening methods that emphasize short-wavelength light may miss cysts in patients with dark fundi or changes to outer blood retinal barrier. Methods Fundus images for diabetic retinopathy photoscreening were acquired for a study with Aeon Imaging, EyePACS, University of California Berkeley, and Indiana University. There were 2047 underserved, adult diabetic patients, of whom over 90% self-identified as a racial/ethnic identify other than non-Hispanic white. Color fundus images at nominally 45 degrees were acquired with a Canon Cr-DGi non-mydriatic camera (Tokyo, Japan) then graded by an EyePACS certified grader. From the 148 patients graded to have clinically significant macular edema by the presence of hard exudates in the central 1500 μm of the fovea, we evaluated macular cysts in 13 patients with cystoid macular edema. Age ranged from 33 to 68 years. Color fundus images were split into red, green, and blue channels with custom Matlab software (Mathworks, Natick, MA). The diameter of a cyst or confluent cysts was quantified in the red-channel and green-channel images separately. Results Cyst identification gave complete agreement between red-channel images and the standard full-color images. This was not the case for green-channel images, which did not expose cysts visible with standard full-color images in five cases, who had dark fundi. Cysts appeared more numerous and covered a larger area in the red channel (733 ± 604 μm) than in the green channel (349 ± 433 μm, P < .006). Conclusions Cysts may be underdetected with the present fundus camera methods, particularly when short-wavelength light is emphasized or in patients with dark fundi. Longer wavelength techniques may improve the detection of cysts and provide more information concerning the early stages of diabetic macular edema or the outer blood retinal barrier.

Improving Accuracy of Grading and Referral of Diabetic Macular Edema Using Location and Extent of Hard Exudates in Retinal Photography.

Background: Hard exudates (HE) are used as a surrogate marker for sight-threatening diabetic macular edema (DME) in most telemedicine-based screening programs in the world. This study investigates whether proximity of HE to the center of the macula, and extent of HE are associated with greater clinically significant macular edema (CSME) severity. A novel method for associating optical coherence tomography (OCT) scans with CSME was developed. Methods: Eligible subjects were recruited from a DRS program in a community clinic in Oakland, California. Ocular fundus of each subject was imaged using 3-field 45-degree digital retinal photography and scanned using central 7-line spectral domain OCT. Two certified graders separated subjects into 2 groups, those with and without HE within 500 microns from the center of the macula. A modified DME severity scale, developed from Early Treatment Diabetic Retinopathy Study data and adapted to OCT thickness measurements, was used to stratify CSME into severe and nonsevere levels for all subjects. Results: The probabilities of severe CSME in groups 1 and 2 were 14.4% (95% CI: 8.2%-23.8%) and 9% (95% CI: 2.4%-25.5%), respectively (P = .556). In post hoc analysis, increase in the number of sectors affected by HE within the central zone of the macula was associated with the increase in the probability of being diagnosed with severe CSME. Conclusion: We have proposed OCT-based classification of DME into severe and nonsevere CSME. Based on this limited analysis, severity of CSME is related more to extent of HE rather than proximity to the center of the macula.

Diabetic Retinopathy and the Cascade Into Vision Loss

ABSTRACT Vision loss from diabetic retinopathy should be unnecessary for patients with access to diabetic retinopathy screening, yet it still occurs at high rates and in varied contexts. Precisely because vision loss is only one of many late-stage complications of diabetes, interfering with the management of diabetes and making self-care more difficult, Vision Threatening Diabetic Retinopathy (VTDR) is considered a “high stakes” diagnosis. Our mixed-methods research addressed the contexts of care and treatment seeking in a sample of people with VTDR using safety-net clinic services and eye specialist referrals. We point to conceptual weaknesses in the single disease framework of health care by diagnosis, and we use the framework of “cascades” to clarify why and how certain non-clinical factors come to bear on long-term experiences of complex chronic diseases.

Telemedicine-based diabetic retinopathy screening programs: an evaluation of utility and cost-effectiveness

License. The full terms of the License are available at http://creativecommons.org/licenses/by-nc/3.0/. Non-commercial uses of the work are permitted without any further permission from Dove Medical Press Limited, provided the work is properly attributed. Permissions beyond the scope of the License are administered by Dove Medical Press Limited. Information on how to request permission may be found at: http://www.dovepress.com/permissions.php Smart Homecare Technology and TeleHealth 2015:3 119–127 Smart Homecare Technology and TeleHealth Dovepress

Vessel network detection using contour evolution and color components

Automated retinal screening relies on vasculature segmentation before the identification of other anatomical structures of the retina. Vasculature extraction can also be input to image quality ranking, neovascularization detection and image registration. An extensive related literature often excludes the inherent heterogeneity of ophthalmic clinical images. The contribution of this paper consists in an algorithm using front propagation to segment the vessel network, including a penalty on the wait queue to the fast marching method, which minimizes leakage of the evolving boundary. The algorithm requires no manual labeling of seeds, a minimum number of parameters and it is capable of segmenting color ocular fundus images in real scenarios, where multi-ethnicity and brightness variations are parts of the problem.

Blind spots in telemedicine: a qualitative study of staff workarounds to resolve gaps in diabetes management

BackgroundNovel telemedicine platforms have expanded access to critical retinal screening into primary care settings. This increased access has contributed to improved retinal screening uptake for diabetic patients, particularly those treated in Federally Qualified Health Centers (‘safety net’ clinics). The aim of this study was to understand how the implementation of telemedical screening for diabetic retinopathy within primary care settings is improving the delivery of critical preventative services, while also introducing changes into clinic workflows and creating additional tasks and responsibilities within resource-constrained clinics.MethodsA qualitative approach was employed to track workflows and perspectives from a range of medical personnel involved in the telemedicine platform for diabetic retinopathy screening and subsequent follow-up treatment. Data were collected through semi-structured interviews and participant observation at three geographically-dispersed Federally Qualified Health Centers in California. Qualitative analysis was performed using standard thematic analytic approaches within a qualitative data analysis software program.ResultsThe introduction of telemedicine platforms, such as diabetic retinopathy screening, into primary care settings is creating additional strain on medical personnel across the diabetes eye care management spectrum. Central issues are related to scheduling patients, issuing referrals for follow-up care and treatment, and challenges to improving adherence to treatment and diabetes management. These issues are overcome in many cases through workarounds, or when medical staff work outside of their job descriptions, purview, and permission to move patients through the diabetes management continuum.ConclusionsThis study demonstrates how the implementation of a novel telemedical platform for diabetic retinopathy screening contributes to the phenomenon of workarounds that account for additional tasks and patient volume. These workarounds should not be considered a sustainable model of health care delivery, but rather as an initial step to understanding where issues are and how clinics can adapt to the inclusion of telemedicine and ultimately increase access to care. The presence of workarounds suggests that as telemedicine is expanded, adequate resources, as well as collaborative, cross-sectoral co-design of new workflows must be simultaneously provided. Systematic bolstering of resources would contribute to more consistent success of telemedicine screening platforms and improved treatment and prevention of disease-related complications.