Performance of an artificial intelligence automated system for diabetic eye screening in a large English population.

AIMS: A diabetic eye screening programme has huge value in reducing avoidable sight loss by identifying diabetic retinopathy at a stage when it can be treated. Artificial intelligence automated systems can be used for diabetic eye screening but are not employed in the national English Diabetic Eye Screening Programme. The aim was to report the performance of a commercially available deep-learning artificial intelligence software in a large English population. METHODS: 9817 anonymised image sets from 10,000 consecutive diabetic eye screening episodes were presented to an artificial intelligence software. The sensitivity and specificity of the artificial intelligence system for detecting diabetic retinopathy were determined using the diabetic eye screening programme manual grade according to national protocols as the reference standard. RESULTS: For no diabetic retinopathy versus any diabetic retinopathy, the sensitivity of the artificial intelligence grading system was 69.7% and specificity 92.2%. The performance of the artificial intelligence system was superior for no or mild diabetic retinopathy versus significant or referrable diabetic retinopathy with a sensitivity of 95.4% and specificity of 92.0%. No cases were identified in which the artificial intelligence grade had missed significant diabetic retinopathy. CONCLUSION: The performance of a commercially available deep-learning artificial intelligence system for identifying diabetic retinopathy in an English national Diabetic Eye Screening Programme is presented. Using the pre-defined settings artificial intelligence performance was highest when identifying diabetic retinopathy which requires an action by the screening programme.

Simultaneous screening and classification of diabetic retinopathy and age-related macular degeneration based on fundus photos-a prospective analysis of the RetCAD system.

AIM: To assess the accuracy of an artificial intelligence (AI) based software (RetCAD, Thirona, The Netherlands) to identify and grade age-related macular degeneration (AMD) and diabetic retinopathy (DR) simultaneously based on fundus photos. METHODS: This prospective study included 1245 eyes of 630 patients attending an ophthalmology day-care clinic. Fundus photos were acquired and parallel graded by the RetCAD AI software and by an expert reference examiner for image quality, and staging of AMD and DR. Adjudication was provided by a second expert examiner in case of disagreement between the AI software and the reference examiner. Statistical analysis was performed on eye-level and on patient-level, by summarizing the individual image level-gradings into and eye-level or patient-level score, respectively. The performance of the RetCAD system was measured using receiver operating characteristics (ROC) analysis and sensitivity and specificity for both AMD and DR were reported. RESULTS: The RetCAD achieved an area under the ROC (Az) of 0.926 with a sensitivity of 84.6% at a specificity of 84.0% for image quality. On image level, the RetCAD software achieved Az values of 0.964 and 0.961 with sensitivity/specificity pairs of 98.2%/79.1% and 83.9%/93.3% for AMD and DR, respectively. On patient level, the RetCAD software achieved Az values of 0.960 and 0.948 with sensitivity/specificity pairs of 97.3%/73.3% and 80.0%/90.1% for AMD and DR, respectively. After adjudication by the second expert examiner sensitivity/specificity increases on patient-level to 98.6%/78.3% and 100.0%/92.3% for AMD and DR, respectively. CONCLUSION: The RetCAD offers very good sensitivity and specificity compared to manual grading by experts and is in line with that obtained by similar automated grading systems. The RetCAD AI software enables simultaneous grading of both AMD and DR based on the same fundus photos. Its sensitivity may be adjusted according to the desired acceptable sensitivity and specificity. Its simplicity cloud base integration allows cost-effective screening where routine expert evaluation may be limited.

Robust total retina thickness segmentation in optical coherence tomography images using convolutional neural networks.

We developed a fully automated system using a convolutional neural network (CNN) for total retina segmentation in optical coherence tomography (OCT) that is robust to the presence of severe retinal pathology. A generalized U-net network architecture was introduced to include the large context needed to account for large retinal changes. The proposed algorithm outperformed qualitative and quantitatively two available algorithms. The algorithm accurately estimated macular thickness with an error of 14.0 ± 22.1 µm, substantially lower than the error obtained using the other algorithms (42.9 ± 116.0 µm and 27.1 ± 69.3 µm, respectively). These results highlighted the proposed algorithm's capability of modeling the wide variability in retinal appearance and obtained a robust and reliable retina segmentation even in severe pathological cases.

Automated Staging of Age-Related Macular Degeneration Using Optical Coherence Tomography.

Purpose: To evaluate a machine learning algorithm that automatically grades age-related macular degeneration (AMD) severity stages from optical coherence tomography (OCT) scans. Methods: A total of 3265 OCT scans from 1016 patients with either no signs of AMD or with signs of early, intermediate, or advanced AMD were randomly selected from a large European multicenter database. A machine learning system was developed to automatically grade unseen OCT scans into different AMD severity stages without requiring retinal layer segmentation. The ability of the system to identify high-risk AMD stages and to assign the correct severity stage was determined by using receiver operator characteristic (ROC) analysis and Cohen's κ statistics (κ), respectively. The results were compared to those of two human observers. Reproducibility was assessed in an independent, publicly available data set of 384 OCT scans. Results: The system achieved an area under the ROC curve of 0.980 with a sensitivity of 98.2% at a specificity of 91.2%. This compares favorably with the performance of human observers who achieved sensitivities of 97.0% and 99.4% at specificities of 89.7% and 87.2%, respectively. A good level of agreement with the reference was obtained (κ = 0.713) and was in concordance with the human observers (κ = 0.775 and κ = 0.755, respectively). Conclusions: A machine learning system capable of automatically grading OCT scans into AMD severity stages was developed and showed similar performance as human observers. The proposed automatic system allows for a quick and reliable grading of large quantities of OCT scans, which could increase the efficiency of large-scale AMD studies and pave the way for AMD screening using OCT.

Automatic differentiation of color fundus images containing drusen or exudates using a contextual spatial pyramid approach.

We developed an automatic system to identify and differentiate color fundus images containing no lesions, drusen or exudates. Drusen and exudates are lesions with a bright appearance, associated with age-related macular degeneration and diabetic retinopathy, respectively. The system consists of three lesion detectors operating at pixel-level, combining their outputs using spatial pooling and classification with a random forest classifier. System performance was compared with ratings of two independent human observers using human-expert annotations as reference. Kappa agreements of 0.89, 0.97 and 0.92 and accuracies of 0.93, 0.98 and 0.95 were obtained for the system and observers, respectively.

Genetic Association Analysis of Drusen Progression.

PURPOSE: Age-related macular degeneration is a common form of vision loss affecting older adults. The etiology of AMD is multifactorial and is influenced by environmental and genetic risk factors. In this study, we examine how 19 common risk variants contribute to drusen progression, a hallmark of AMD pathogenesis. METHODS: Exome chip data was made available through the International AMD Genomics Consortium (IAMDGC). Drusen quantification was carried out with color fundus photographs using an automated drusen detection and quantification algorithm. A genetic risk score (GRS) was calculated per subject by summing risk allele counts at 19 common genetic risk variants weighted by their respective effect sizes. Pathway analysis of drusen progression was carried out with the software package Pathway Analysis by Randomization Incorporating Structure. RESULTS: We observed significant correlation with drusen baseline area and the GRS in the age-related eye disease study (AREDS) dataset (ρ = 0.175, P = 0.006). Measures of association were not statistically significant between drusen progression and the GRS (P = 0.54). Pathway analysis revealed the cell adhesion molecules pathway as the most highly significant pathway associated with drusen progression (corrected P = 0.02). CONCLUSIONS: In this study, we explored the potential influence of known common AMD genetic risk factors on drusen progression. Our results from the GRS analysis showed association of increasing genetic burden (from 19 AMD associated loci) to baseline drusen load but not drusen progression in the AREDS dataset while pathway analysis suggests additional genetic contributors to AMD risk.

Fast Convolutional Neural Network Training Using Selective Data Sampling: Application to Hemorrhage Detection in Color Fundus Images.

Convolutional neural networks (CNNs) are deep learning network architectures that have pushed forward the state-of-the-art in a range of computer vision applications and are increasingly popular in medical image analysis. However, training of CNNs is time-consuming and challenging. In medical image analysis tasks, the majority of training examples are easy to classify and therefore contribute little to the CNN learning process. In this paper, we propose a method to improve and speed-up the CNN training for medical image analysis tasks by dynamically selecting misclassified negative samples during training. Training samples are heuristically sampled based on classification by the current status of the CNN. Weights are assigned to the training samples and informative samples are more likely to be included in the next CNN training iteration. We evaluated and compared our proposed method by training a CNN with (SeS) and without (NSeS) the selective sampling method. We focus on the detection of hemorrhages in color fundus images. A decreased training time from 170 epochs to 60 epochs with an increased performance-on par with two human experts-was achieved with areas under the receiver operating characteristics curve of 0.894 and 0.972 on two data sets. The SeS CNN statistically outperformed the NSeS CNN on an independent test set.

OCT Angiography Compared to Fluorescein and Indocyanine Green Angiography in Chronic Central Serous Chorioretinopathy.

PURPOSE: Abnormal choroidal blood flow is considered important in the pathogenesis of chronic central serous chorioretinopathy (CSC). Optical coherence tomography (OCT) angiography can image ocular blood cell flow and could thus provide novel insights in disease mechanisms of CSC. We evaluated depth-resolved flow in chronic CSC by OCT angiography compared to fluorescein angiography (FA) and indocyanine green angiography (ICGA). METHODS: Eighteen eyes with chronic CSC, and six healthy controls, were included. Two human observers annotated areas of staining, hypofluorescence, and hotspots on FA and ICGA, and areas of abnormal flow on OCT angiography. Interobserver agreement in annotating OCT angiography and FA/ICGA was measured by Jaccard indices (JIs). We assessed colocation of flow abnormalities and subretinal fluid visible on OCT, and the distance between hotspots on ICGA from flow abnormalities. RESULTS: Abnormal areas were most frequently annotated in late-phase ICGA and choriocapillary OCT angiography, with moderately high (median JI, 0.74) and moderate (median JI, 0.52) interobserver agreement, respectively. Abnormalities on late-phase ICGA and FA colocated with those on OCT angiography. Aberrant choriocapillary OCT angiography presented as foci of reduced flow surrounded by hyperperfused areas. Hotspots on ICGA were located near hypoperfused spots on OCT angiography (mean distance, 168 µm). Areas with current or former subretinal fluid were colocated with flow abnormalities. CONCLUSIONS: On OCT angiography, chronic CSC showed irregular choriocapillary flow patterns, corresponding to ICGA abnormalities. These results suggest focal choriocapillary ischemia with surrounding hyperperfusion that may lead to subretinal fluid leakage.

Impact of motion-associated noise on intrinsic optical signal imaging in humans with optical coherence tomography.

A growing body of evidence suggests that phototransduction can be studied in the human eye in vivo by imaging of fast intrinsic optical signals (IOS). There is consensus concerning the limiting influence of motion-associated imaging noise on the reproducibility of IOS-measurements, especially in those employing spectral-domain optical coherence tomography (SD-OCT). However, no study to date has conducted a comprehensive analysis of this noise in the context of IOS-imaging. In this study, we discuss biophysical correlates of IOS, and we address motion-associated imaging noise by providing correctional post-processing methods. In order to avoid cross-talk of adjacent IOS of opposite signal polarity, cellular resolution and stability of imaging to the level of individual cones is likely needed. The optical Stiles-Crawford effect can be a source of significant IOS-imaging noise if alignment with the peak of the Stiles-Crawford function cannot be maintained. Therefore, complete head stabilization by implementation of a bite-bar may be critical to maintain a constant pupil entry position of the OCT beam. Due to depth-dependent sensitivity fall-off, heartbeat and breathing associated axial movements can cause tissue reflectivity to vary by 29% over time, although known methods can be implemented to null these effects. Substantial variations in reflectivity can be caused by variable illumination due to changes in the beam pupil entry position and angle, which can be reduced by an adaptive algorithm based on slope-fitting of optical attenuation in the choriocapillary lamina.

Automatic identification of reticular pseudodrusen using multimodal retinal image analysis.

PURPOSE: To examine human performance and agreement on reticular pseudodrusen (RPD) detection and quantification by using single- and multimodality grading protocols and to describe and evaluate a machine learning system for the automatic detection and quantification of reticular pseudodrusen by using single- and multimodality information. METHODS: Color fundus, fundus autofluoresence, and near-infrared images of 278 eyes from 230 patients with or without presence of RPD were used in this study. All eyes were scored for presence of RPD during single- and multimodality setups by two experienced observers and a developed machine learning system. Furthermore, automatic quantification of RPD area was performed by the proposed system and compared with human delineations. RESULTS: Observers obtained a higher performance and better interobserver agreement for RPD detection with multimodality grading, achieving areas under the receiver operating characteristic (ROC) curve of 0.940 and 0.958, and a κ agreement of 0.911. The proposed automatic system achieved an area under the ROC of 0.941 with a multimodality setup. Automatic RPD quantification resulted in an intraclass correlation (ICC) value of 0.704, which was comparable with ICC values obtained between single-modality manual delineations. CONCLUSIONS: Observer performance and agreement for RPD identification improved significantly by using a multimodality grading approach. The developed automatic system showed similar performance as observers, and automatic RPD area quantification was in concordance with manual delineations. The proposed automatic system allows for a fast and accurate identification and quantification of RPD, opening the way for efficient quantitative imaging biomarkers in large data set analysis.

Clinical characteristics of familial and sporadic age-related macular degeneration: differences and similarities.

PURPOSE: We describe the differences and similarities in clinical characteristics and phenotype of familial and sporadic patients with age-related macular degeneration (AMD). METHODS: We evaluated data of 1828 AMD patients and 1715 controls enrolled in the European Genetic Database. All subjects underwent ophthalmologic examination, including visual acuity testing and fundus photography. Images were graded and fundus photographs were used for automatic drusen quantification by a machine learning algorithm. Data on disease characteristics, family history, medical history, and lifestyle habits were obtained by a questionnaire. RESULTS: The age at first symptoms was significantly lower in AMD patients with a positive family history (68.5 years) than in those with no family history (71.6 years, P = 1.9 × 10(-5)). Risk factors identified in sporadic and familial subjects were increasing age (odds ratio [OR], 1.08 per year; P = 3.0 × 10(-51), and OR, 1.15; P = 5.3 × 10(-36), respectively) and smoking (OR, 1.01 per pack year; P = 1.1 × 10(-6) and OR, 1.02; P = 0.005). Physical activity and daily red meat consumption were significantly associated with AMD in sporadic subjects only (OR, 0.49; P = 3.7 × 10(-10) and OR, 1.81; P = 0.001). With regard to the phenotype, geographic atrophy and cuticular drusen were significantly more prevalent in familial AMD (17.5% and 21.7%, respectively) compared to sporadic AMD (9.8% and 12.1%). CONCLUSIONS: Familial AMD patients become symptomatic at a younger age. The higher prevalence of geographic atrophy and cuticular drusen in the familial AMD cases may be explained by the contribution of additional genetic factors segregating within families.

Automatic drusen quantification and risk assessment of age-related macular degeneration on color fundus images.

PURPOSE: To evaluate a machine learning algorithm that allows for computer-aided diagnosis (CAD) of nonadvanced age-related macular degeneration (AMD) by providing an accurate detection and quantification of drusen location, area, and size. METHODS: Color fundus photographs of 407 eyes without AMD or with early to moderate AMD were randomly selected from a large European multicenter database. A machine learning system was developed to automatically detect and quantify drusen on each image. Based on detected drusen, the CAD software provided a risk assessment to develop advanced AMD. Evaluation of the CAD system was performed using annotations made by two blinded human graders. RESULTS: Free-response receiver operating characteristics (FROC) analysis showed that the proposed system approaches the performance of human observers in detecting drusen. The estimated drusen area showed excellent agreement with both observers, with mean intraclass correlation coefficients (ICC) larger than 0.85. Maximum druse diameter agreement was lower, with a maximum ICC of 0.69, but comparable to the interobserver agreement (ICC = 0.79). For automatic AMD risk assessment, the system achieved areas under the receiver operating characteristic (ROC) curve of 0.948 and 0.954, reaching similar performance as human observers. CONCLUSIONS: A machine learning system capable of separating high-risk from low-risk patients with nonadvanced AMD by providing accurate detection and quantification of drusen, was developed. The proposed method allows for quick and reliable diagnosis of AMD, opening the way for large dataset analysis within population studies and genotype-phenotype correlation analysis.