Dataset Information

A self-adaptive deep learning method for automated eye laterality detection based on color fundus photography.

ABSTRACT: PURPOSE:To provide a self-adaptive deep learning (DL) method to automatically detect the eye laterality based on fundus images. METHODS:A total of 18394 fundus images with real-world eye laterality labels were used for model development and internal validation. A separate dataset of 2000 fundus images with eye laterality labeled manually was used for external validation. A DL model was developed based on a fine-tuned Inception-V3 network with self-adaptive strategy. The area under receiver operator characteristic curve (AUC) with sensitivity and specificity and confusion matrix were applied to assess the model performance. The class activation map (CAM) was used for model visualization. RESULTS:In the external validation (N = 2000, 50% labeled as left eye), the AUC of the DL model for overall eye laterality detection was 0.995 (95% CI, 0.993-0.997) with an accuracy of 99.13%. Specifically for left eye detection, the sensitivity was 99.00% (95% CI, 98.11%-99.49%) and the specificity was 99.10% (95% CI, 98.23%-99.56%). Nineteen images were wrongly classified as compared to the human labels: 12 were due to human wrong labelling, while 7 were due to poor image quality. The CAM showed that the region of interest for eye laterality detection was mainly the optic disc and surrounding areas. CONCLUSION:We proposed a self-adaptive DL method with a high performance in detecting eye laterality based on fundus images. Results of our findings were based on real world labels and thus had practical significance in clinical settings.

SUBMITTER: Liu C

PROVIDER: S-EPMC6752776 | biostudies-literature | 2019

REPOSITORIES: biostudies-literature

ACCESS DATA

Publications

A self-adaptive deep learning method for automated eye laterality detection based on color fundus photography.

Liu Chi C Han Xiaotong X Li Zhixi Z Ha Jason J Peng Guankai G Meng Wei W He Mingguang M

PloS one 20190919 9

<h4>Purpose</h4>To provide a self-adaptive deep learning (DL) method to automatically detect the eye laterality based on fundus images.<h4>Methods</h4>A total of 18394 fundus images with real-world eye laterality labels were used for model development and internal validation. A separate dataset of 2000 fundus images with eye laterality labeled manually was used for external validation. A DL model was developed based on a fine-tuned Inception-V3 network with self-adaptive strategy. The area under ...[more]

PMID: 31536537

Similar Datasets

Project description:PURPOSE:To assess the utility of deep learning in the detection of geographic atrophy (GA) from color fundus photographs and to explore potential utility in detecting central GA (CGA). DESIGN:A deep learning model was developed to detect the presence of GA in color fundus photographs, and 2 additional models were developed to detect CGA in different scenarios. PARTICIPANTS:A total of 59?812 color fundus photographs from longitudinal follow-up of 4582 participants in the Age-Related Eye Disease Study (AREDS) dataset. Gold standard labels were from human expert reading center graders using a standardized protocol. METHODS:A deep learning model was trained to use color fundus photographs to predict GA presence from a population of eyes with no AMD to advanced AMD. A second model was trained to predict CGA presence from the same population. A third model was trained to predict CGA presence from the subset of eyes with GA. For training and testing, 5-fold cross-validation was used. For comparison with human clinician performance, model performance was compared with that of 88 retinal specialists. MAIN OUTCOME MEASURES:Area under the curve (AUC), accuracy, sensitivity, specificity, and precision. RESULTS:The deep learning models (GA detection, CGA detection from all eyes, and centrality detection from GA eyes) had AUCs of 0.933-0.976, 0.939-0.976, and 0.827-0.888, respectively. The GA detection model had accuracy, sensitivity, specificity, and precision of 0.965 (95% confidence interval [CI], 0.959-0.971), 0.692 (0.560-0.825), 0.978 (0.970-0.985), and 0.584 (0.491-0.676), respectively, compared with 0.975 (0.971-0.980), 0.588 (0.468-0.707), 0.982 (0.978-0.985), and 0.368 (0.230-0.505) for the retinal specialists. The CGA detection model had values of 0.966 (0.957-0.975), 0.763 (0.641-0.885), 0.971 (0.960-0.982), and 0.394 (0.341-0.448). The centrality detection model had values of 0.762 (0.725-0.799), 0.782 (0.618-0.945), 0.729 (0.543-0.916), and 0.799 (0.710-0.888). CONCLUSIONS:A deep learning model demonstrated high accuracy for the automated detection of GA. The AUC was noninferior to that of human retinal specialists. Deep learning approaches may also be applied to the identification of CGA. The code and pretrained models are publicly available at https://github.com/ncbi-nlp/DeepSeeNet.

Project description:PurposeOCT has revealed many details of retinal disease that were not available with older imaging technologies. In eyes of adults older than 60 years with healthy maculas as determined by color fundus photography (CFP) and a validated grading system, we screened for pathologic features using OCT. We also tested visual function to assess potential impact of the observed pathologic features on patients.DesignCross-sectional study.ParticipantsPersons recruited from primary ophthalmology care clinics.MethodsColor fundus photographs were assessed by the 9-step Age-Related Eye Disease Study scale. OCT macular volumes of participants at step 1 on the Age-Related Eye Disease Study scale, considered healthy, were reviewed by a retina specialist masked to other participant characteristics. Participants were tested for 6 different cone- and rod-mediated visual functions.Main outcome measuresPercentage of participants with disorders detected on OCT review and visual function measures.ResultsIn 138 of 984 eyes (14%) considered healthy by CFP, pathologic features were detectable by OCT, with 8.4% having vitreomacular interface disorders. Among the low-prevalence disorders found, 5 eyes (0.5%) showed macular telangiectasia type 2. Relative to eyes lacking detectable chorioretinal pathologic features, eyes with any pathologic features were associated with poorer low-luminance visual acuity and rod-mediated dark adaptation. In eyes with epiretinal membranes, the largest single entity identified (n = 61 [6.2%]), significantly worse visual functions were best-corrected visual acuity (P = 0.0444), low-luminance visual acuity (P = 0.0151), and light sensitivity (central 3° and 9°; P = 0.0035 and P = 0.0097, respectively).ConclusionsMacular pathologic features with functional visual implications not identified by clinical examination or CFP are detectable with OCT. Vitreomacular interface disorders often are visually significant and treatable conditions that are visible on OCT, but are easily missed on CFP and clinical examination. Another such condition best seen on OCT is macular telangiectasia type 2, an untreatable disorder for which a clinical trial is in progress. OCT has a potential role in primary eye care clinics to screen for retinal pathologic features, especially in eyes with decreased visual acuity and otherwise normal examination results.

Project description:PurposeIn assessing the severity of age-related macular degeneration (AMD), the Age-Related Eye Disease Study (AREDS) Simplified Severity Scale predicts the risk of progression to late AMD. However, its manual use requires the time-consuming participation of expert practitioners. Although several automated deep learning systems have been developed for classifying color fundus photographs (CFP) of individual eyes by AREDS severity score, none to date has used a patient-based scoring system that uses images from both eyes to assign a severity score.DesignDeepSeeNet, a deep learning model, was developed to classify patients automatically by the AREDS Simplified Severity Scale (score 0-5) using bilateral CFP.ParticipantsDeepSeeNet was trained on 58 402 and tested on 900 images from the longitudinal follow-up of 4549 participants from AREDS. Gold standard labels were obtained using reading center grades.MethodsDeepSeeNet simulates the human grading process by first detecting individual AMD risk factors (drusen size, pigmentary abnormalities) for each eye and then calculating a patient-based AMD severity score using the AREDS Simplified Severity Scale.Main outcome measuresOverall accuracy, specificity, sensitivity, Cohen's kappa, and area under the curve (AUC). The performance of DeepSeeNet was compared with that of retinal specialists.ResultsDeepSeeNet performed better on patient-based classification (accuracy = 0.671; kappa = 0.558) than retinal specialists (accuracy = 0.599; kappa = 0.467) with high AUC in the detection of large drusen (0.94), pigmentary abnormalities (0.93), and late AMD (0.97). DeepSeeNet also outperformed retinal specialists in the detection of large drusen (accuracy 0.742 vs. 0.696; kappa 0.601 vs. 0.517) and pigmentary abnormalities (accuracy 0.890 vs. 0.813; kappa 0.723 vs. 0.535) but showed lower performance in the detection of late AMD (accuracy 0.967 vs. 0.973; kappa 0.663 vs. 0.754).ConclusionsBy simulating the human grading process, DeepSeeNet demonstrated high accuracy with increased transparency in the automated assignment of individual patients to AMD risk categories based on the AREDS Simplified Severity Scale. These results highlight the potential of deep learning to assist and enhance clinical decision-making in patients with AMD, such as early AMD detection and risk prediction for developing late AMD. DeepSeeNet is publicly available on https://github.com/ncbi-nlp/DeepSeeNet.

Dataset Information

A self-adaptive deep learning method for automated eye laterality detection based on color fundus photography.

Publications

A self-adaptive deep learning method for automated eye laterality detection based on color fundus photography.

Similar Datasets

OmicsDI is part of the ELIXIR infrastructure

Tweets