Dataset Information

Automated Identification of Referable Retinal Pathology in Teleophthalmology Setting.

ABSTRACT:

Purpose

This study aims to meet a growing need for a fully automated, learning-based interpretation tool for retinal images obtained remotely (e.g. teleophthalmology) through different imaging modalities that may include imperfect (uninterpretable) images.

Methods

A retrospective study of 1148 optical coherence tomography (OCT) and color fundus photography (CFP) retinal images obtained using Topcon's Maestro care unit on 647 patients with diabetes. To identify retinal pathology, a Convolutional Neural Network (CNN) with dual-modal inputs (i.e. CFP and OCT images) was developed. We developed a novel alternate gradient descent algorithm to train the CNN, which allows for the use of uninterpretable CFP/OCT images (i.e. ungradable images that do not contain sufficient image biomarkers for the reviewer to conclude absence or presence of retinal pathology). Specifically, a 9:1 ratio to split the training and testing dataset was used for training and validating the CNN. Paired CFP/OCT inputs (obtained from a single eye of a patient) were grouped as retinal pathology negative (RPN; 924 images) in the absence of retinal pathology in both imaging modalities, or if one of the imaging modalities was uninterpretable and the other without retinal pathology. If any imaging modality exhibited referable retinal pathology, the corresponding CFP/OCT inputs were deemed retinal pathology positive (RPP; 224 images) if any imaging modality exhibited referable retinal pathology.

Results

Our approach achieved 88.60% (95% confidence interval [CI] = 82.76% to 94.43%) accuracy in identifying pathology, along with the false negative rate (FNR) of 12.28% (95% CI = 6.26% to 18.31%), recall (sensitivity) of 87.72% (95% CI = 81.69% to 93.74%), specificity of 89.47% (95% CI = 83.84% to 95.11%), and area under the curve of receiver operating characteristic (AUC-ROC) was 92.74% (95% CI = 87.71% to 97.76%).

Conclusions

Our model can be successfully deployed in clinical practice to facilitate automated remote retinal pathology identification.

Translational relevance

A fully automated tool for early diagnosis of retinal pathology might allow for earlier treatment and improved visual outcomes.

SUBMITTER: Gao Q

PROVIDER: S-EPMC8161696 | biostudies-literature |

REPOSITORIES: biostudies-literature

ACCESS DATA

Similar Datasets

Project description:Purpose: To assess the accuracy and efficacy of a semi-automated deep learning algorithm (DLA) assisted approach to detect vision-threatening diabetic retinopathy (DR). Methods: We developed a two-step semi-automated DLA-assisted approach to grade fundus photographs for vision-threatening referable DR. Study images were obtained from the Lingtou Cohort Study, and captured at participant enrollment in 2009-2010 ("baseline images") and annual follow-up between 2011 and 2017. To begin, a validated DLA automatically graded baseline images for referable DR and classified them as positive, negative, or ungradable. Following, each positive image, all other available images from patients who had a positive image, and a 5% random sample of all negative images were selected and regraded by trained human graders. A reference standard diagnosis was assigned once all graders achieved consistent grading outcomes or with a senior ophthalmologist's final diagnosis. The semi-automated DLA assisted approach combined initial DLA screening and subsequent human grading for images identified as high-risk. This approach was further validated within the follow-up image datasets and its time and economic costs evaluated against fully human grading. Results: For evaluation of baseline images, a total of 33,115 images were included and automatically graded by the DLA. 2,604 images (480 positive results, 624 available other images from participants with a positive result, and 1500 random negative samples) were selected and regraded by graders. The DLA achieved an area under the receiver operating characteristic curve (AUC), sensitivity, specificity, and accuracy of 0.953, 0.970, 0.879, and 88.6%, respectively. In further validation within the follow-up image datasets, a total of 88,363 images were graded using this semi-automated approach and human grading was performed on 8975 selected images. The DLA achieved an AUC, sensitivity, and specificity of 0.914, 0.852, 0.853, respectively. Compared against fully human grading, the semi-automated DLA-assisted approach achieved an estimated 75.6% time and 90.1% economic cost saving. Conclusions: The DLA described in this study was able to achieve high accuracy, sensitivity, and specificity in grading fundus images for referable DR. Validated against long-term follow-up datasets, a semi-automated DLA-assisted approach was able to accurately identify suspect cases, and minimize misdiagnosis whilst balancing safety, time, and economic cost.

Project description:BackgroundDiabetic eye complications are the leading cause of visual loss among working-aged people. Pharmacy-based teleophthalmology has emerged as a possible alternative to in-person examination that may facilitate compliance with evidence-based recommendations and reduce barriers to specialized eye care. The objective of this study was to estimate the cost-effectiveness of mobile teleophthalmology screening compared with in-person examination (primary care) for the diabetic population residing in semiurban areas of southwestern Ontario.MethodsA decision tree was constructed to compare in-person examination (comparator program) versus pharmacy-based teleophthalmology (intervention program). The economic model was designed to identify patients with more than minimal diabetic retinopathy, manifested by at least 1 microaneurysm at examination (modified Airlie House classification grade of ≥ 20). Cost-effectiveness was assessed as cost per case detected (true-positive result) and cost per case correctly diagnosed (including true-positive and true-negative results).ResultsThe cost per case detected was $510 with in-person examination and $478 with teleophthalmology, and the cost per case correctly diagnosed was $107 and $102 respectively. The incremental cost-effectiveness ratio was $314 per additional case detected and $73 per additional case correctly diagnosed. Use of pharmacologic dilation and health care specialists' fees were the most important cost drivers.InterpretationThe study showed that a compound teleophthalmology program in a semiurban community would be more effective but more costly than in-person examination. The findings raise the question of whether the benefits of pharmacy-based teleophthalmology in semiurban areas, where in-person examination is still available, are equivalent to those observed in remote communities. Further study is needed to investigate the impact of this program on the prevention of severe vision loss and quality of life in a semiurban setting.