Artificial intelligence-based detection of epimacular membrane from color fundus photographs.
Ontology highlight
ABSTRACT:
SUBMITTER: Shao E
PROVIDER: S-EPMC8481557 | biostudies-literature |
REPOSITORIES: biostudies-literature
Similar Datasets
Project description:PurposeTo develop deep learning models based on color fundus photographs that can automatically grade myopic maculopathy, diagnose pathologic myopia, and identify and segment myopia-related lesions.MethodsPhotographs were graded and annotated by four ophthalmologists and were then divided into a high-consistency subgroup or a low-consistency subgroup according to the consistency between the results of the graders. ResNet-50 network was used to develop the classification model, and DeepLabv3+ network was used to develop the segmentation model for lesion identification. The two models were then combined to develop the classification-and-segmentation-based co-decision model.ResultsThis study included 1395 color fundus photographs from 895 patients. The grading accuracy of the co-decision model was 0.9370, and the quadratic-weighted κ coefficient was 0.9651; the co-decision model achieved an area under the receiver operating characteristic curve of 0.9980 in diagnosing pathologic myopia. The photograph-level F1 values of the segmentation model identifying optic disc, peripapillary atrophy, diffuse atrophy, patchy atrophy, and macular atrophy were all >0.95; the pixel-level F1 values for segmenting optic disc and peripapillary atrophy were both >0.9; the pixel-level F1 values for segmenting diffuse atrophy, patchy atrophy, and macular atrophy were all >0.8; and the photograph-level recall/sensitivity for detecting lacquer cracks was 0.9230.ConclusionsThe models could accurately and automatically grade myopic maculopathy, diagnose pathologic myopia, and identify and monitor progression of the lesions.Translational relevanceThe models can potentially help with the diagnosis, screening, and follow-up for pathologic myopic in clinical practice.
| S-EPMC9206390 | biostudies-literature
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.
| S-EPMC6810830 | biostudies-literature
Project description:Color fundus photographs are the most common type of image used for automatic diagnosis of retinal diseases and abnormalities. As all color photographs, these images contain information about three primary colors, i.e., red, green, and blue, in three separate color channels. This work aims to understand the impact of each channel in the automatic diagnosis of retinal diseases and abnormalities. To this end, the existing works are surveyed extensively to explore which color channel is used most commonly for automatically detecting four leading causes of blindness and one retinal abnormality along with segmenting three retinal landmarks. From this survey, it is clear that all channels together are typically used for neural network-based systems, whereas for non-neural network-based systems, the green channel is most commonly used. However, from the previous works, no conclusion can be drawn regarding the importance of the different channels. Therefore, systematic experiments are conducted to analyse this. A well-known U-shaped deep neural network (U-Net) is used to investigate which color channel is best for segmenting one retinal abnormality and three retinal landmarks.
| S-EPMC9321111 | biostudies-literature
Project description:IntroductionThe maculopathy in highly myopic eyes is complex. Its clinical diagnosis is a huge workload and subjective. To simply and quickly classify pathologic myopia (PM), a deep learning algorithm was developed and assessed to screen myopic maculopathy lesions based on color fundus photographs.MethodsThis study included 10,347 ocular fundus photographs from 7606 participants. Of these photographs, 8210 were used for training and validation, and 2137 for external testing. A deep learning algorithm was trained, validated, and externally tested to screen myopic maculopathy which was classified into four categories: normal or mild tessellated fundus, severe tessellated fundus, early-stage PM, and advanced-stage PM. The area under the precision-recall curve, the area under the receiver operating characteristic curve (AUC), sensitivity, specificity, accuracy, and Cohen's kappa were calculated and compared with those of retina specialists.ResultsIn the validation data set, the model detected normal or mild tessellated fundus, severe tessellated fundus, early-stage PM, and advanced-stage PM with AUCs of 0.98, 0.95, 0.99, and 1.00, respectively; while in the external-testing data set of 2137 photographs, the model had AUCs of 0.99, 0.96, 0.98, and 1.00, respectively.ConclusionsWe developed a deep learning model for detection and classification of myopic maculopathy based on fundus photographs. Our model achieved high sensitivities, specificities, and reliable Cohen's kappa, compared with those of attending ophthalmologists.
| S-EPMC9735275 | biostudies-literature
Project description:Retinal vasculature provides an opportunity for direct observation of vessel morphology, which is linked to multiple clinical conditions. However, objective and quantitative interpretation of the retinal vasculature relies on precise vessel segmentation, which is time consuming and labor intensive. Artificial intelligence (AI) has demonstrated great promise in retinal vessel segmentation. The development and evaluation of AI-based models require large numbers of annotated retinal images. However, the public datasets that are usable for this task are scarce. In this paper, we collected a color fundus image vessel segmentation (FIVES) dataset. The FIVES dataset consists of 800 high-resolution multi-disease color fundus photographs with pixelwise manual annotation. The annotation process was standardized through crowdsourcing among medical experts. The quality of each image was also evaluated. To the best of our knowledge, this is the largest retinal vessel segmentation dataset for which we believe this work will be beneficial to the further development of retinal vessel segmentation.
| S-EPMC9352679 | biostudies-literature
Project description:ImportanceAdherence to screening for vision-threatening proliferative sickle cell retinopathy is limited among patients with sickle cell hemoglobinopathy despite guidelines recommending dilated fundus examinations beginning in childhood. An automated algorithm for detecting sea fan neovascularization from ultra-widefield color fundus photographs could expand access to rapid retinal evaluations to identify patients at risk of vision loss from proliferative sickle cell retinopathy.ObjectiveTo develop a deep learning system for detecting sea fan neovascularization from ultra-widefield color fundus photographs from patients with sickle cell hemoglobinopathy.Design, setting, and participantsIn a cross-sectional study conducted at a single-institution, tertiary academic referral center, deidentified, retrospectively collected, ultra-widefield color fundus photographs from 190 adults with sickle cell hemoglobinopathy were independently graded by 2 masked retinal specialists for presence or absence of sea fan neovascularization. A third masked retinal specialist regraded images with discordant or indeterminate grades. Consensus retinal specialist reference standard grades were used to train a convolutional neural network to classify images for presence or absence of sea fan neovascularization. Participants included nondiabetic adults with sickle cell hemoglobinopathy receiving care from a Wilmer Eye Institute retinal specialist; the patients had received no previous laser or surgical treatment for sickle cell retinopathy and underwent imaging with ultra-widefield color fundus photographs between January 1, 2012, and January 30, 2019.InterventionsDeidentified ultra-widefield color fundus photographs were retrospectively collected.Main outcomes and measuresSensitivity, specificity, and area under the receiver operating characteristic curve of the convolutional neural network for sea fan detection.ResultsA total of 1182 images from 190 patients were included. Of the 190 patients, 101 were women (53.2%), and the mean (SD) age at baseline was 36.2 (12.3) years; 119 patients (62.6%) had hemoglobin SS disease and 46 (24.2%) had hemoglobin SC disease. One hundred seventy-nine patients (94.2%) were of Black or African descent. Images with sea fan neovascularization were obtained in 57 patients (30.0%). The convolutional neural network had an area under the curve of 0.988 (95% CI, 0.969-0.999), with sensitivity of 97.4% (95% CI, 86.5%-99.9%) and specificity of 97.0% (95% CI, 93.5%-98.9%) for detecting sea fan neovascularization from ultra-widefield color fundus photographs.Conclusions and relevanceThis study reports an automated system with high sensitivity and specificity for detecting sea fan neovascularization from ultra-widefield color fundus photographs from patients with sickle cell hemoglobinopathy, with potential applications for improving screening for vision-threatening proliferative sickle cell retinopathy.
| S-EPMC7774049 | biostudies-literature
Project description:PurposeSpectral domain-optical coherence tomography (SD-OCT) may be useful for efficient measurement of drusen in patients with age-related macular degeneration (AMD). Areas identified as drusen from semiautomated segmentation of drusen on SD-OCT were compared to those identified from review of digital color fundus photographs (CFPs).MethodsTwelve eyes with nonneovascular AMD were prospectively imaged with digital CFP and SD-OCT. For each eye, areas on CFP in which at least two of three retina specialists agreed on drusen presence produced the composite CFP drusen map. Automated image analysis produced another CFP map. Areas identified as drusen by segmentation on SD-OCT B-scans were plotted as the SD-OCT drusen map. The CFP and SD-OCT maps were compared and agreement was quantified. Disagreement was characterized into distinct types, and the frequency of each type was quantified.ResultsThere was general agreement between CFP and SD-OCT in identifying presence and absence of drusen, with mean agreement in 82% ± 9% of total image pixels. Most disagreement (80% ± 15%) occurred at drusen margins. There was a trend toward greater detection of drusen with SD-OCT in eyes with larger drusen and with hyperpigmentation. There was a trend toward greater detection of smaller drusen by CFP.ConclusionsGood agreement was demonstrated in drusen detection between CFP and SD-OCT. Areas of disagreement underscore limitations of CFP-based measurement of drusen, particularly in the sizing of large, soft drusen. SD-OCT shows great promise as an adjunctive tool for assessing drusen burden in AMD. (ClinicalTrials.gov number, NCT00734487.).
| S-EPMC2939301 | biostudies-literature
Project description:ObjectivesTo present and validate a deep ensemble algorithm to detect diabetic retinopathy (DR) and diabetic macular oedema (DMO) using retinal fundus images.MethodsA total of 8739 retinal fundus images were collected from a retrospective cohort of 3285 patients. For detecting DR and DMO, a multiple improved Inception-v4 ensembling approach was developed. We measured the algorithm's performance and made a comparison with that of human experts on our primary dataset, while its generalization was assessed on the publicly available Messidor-2 dataset. Also, we investigated systematically the impact of the size and number of input images used in training on model's performance, respectively. Further, the time budget of training/inference versus model performance was analyzed.ResultsOn our primary test dataset, the model achieved an 0.992 (95% CI, 0.989-0.995) AUC corresponding to 0.925 (95% CI, 0.916-0.936) sensitivity and 0.961 (95% CI, 0.950-0.972) specificity for referable DR, while the sensitivity and specificity for ophthalmologists ranged from 0.845 to 0.936, and from 0.912 to 0.971, respectively. For referable DMO, our model generated an AUC of 0.994 (95% CI, 0.992-0.996) with a 0.930 (95% CI, 0.919-0.941) sensitivity and 0.971 (95% CI, 0.965-0.978) specificity, whereas ophthalmologists obtained sensitivities ranging between 0.852 and 0.946, and specificities ranging between 0.926 and 0.985.ConclusionThis study showed that the deep ensemble model exhibited excellent performance in detecting DR and DMO, and had good robustness and generalization, which could potentially help support and expand DR/DMO screening programs.
| S-EPMC9232645 | biostudies-literature
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.
| S-EPMC6435402 | biostudies-literature
Project description:BackgroundThis study developed a diagnostic tool to automatically detect normal, unclear and tumor images from colonoscopy videos using artificial intelligence.MethodsFor the creation of training and validation sets, 47,555 images in the jpg format were extracted from colonoscopy videos for 24 patients in Korea University Anam Hospital. A gastroenterologist with the clinical experience of 15 years divided the 47,555 images into three classes of Normal (25,895), Unclear (2038) and Tumor (19,622). A single shot detector, a deep learning framework designed for object detection, was trained using the 47,255 images and validated with two sets of 300 images-each validation set included 150 images (50 normal, 50 unclear and 50 tumor cases). Half of the 47,255 images were used for building the model and the other half were used for testing the model. The learning rate of the model was 0.0001 during 250 epochs (training cycles).ResultsThe average accuracy, precision, recall, and F1 score over the category were 0.9067, 0.9744, 0.9067 and 0.9393, respectively. These performance measures had no change with respect to the intersection-over-union threshold (0.45, 0.50, and 0.55). This finding suggests the stability of the model.ConclusionAutomated detection of normal, unclear and tumor images from colonoscopy videos is possible by using a deep learning framework. This is expected to provide an invaluable decision supporting system for clinical experts.
| S-EPMC7849081 | biostudies-literature