Differences in macular thickness associated with peripheral retinal vessel whitening in diabetic patients.

This study aimed to determine the difference in macular thickness among patients with diabetes mellitus (DM) with and without peripheral retinal vessel whitening (PRVW). PRVW was defined by retinal vessel whitening outside the standard seven ETDRS fields. Subjects were divided into DM with PRVW, DM without PRVW, and normal age-matched controls. Optical coherence tomography scans were divided into total, inner, and outer retinal layer thicknesses and were compared in the macula's central, inner, and outer rings. Forty-seven eyes were included: DM with PRVW = 15, DM without PRVW = 16, and Controls = 16. Overall, the mean retinal thickness in patients with DM with PRVW was lower than in patients with DM without PRVW and controls. In the inner macula, DM patients with PRVW showed a significantly lower mean inner superior, nasal, inferior, and temporal macula compared to DM patients without PRVW (p = 0.014, 0.008, 0.005, < 0.001, respectively). DM patients with PRVW also showed a significantly lower mean outer superior, nasal, inferior, and temporal macula than controls (p = 0.005, 0.005, 0.016, 0.025, respectively). This study demonstrates that PRVW in DM patients may be associated with global structural changes to the macular region, promoting a decrease in inner and outer retinal thickness. Further studies should investigate the functional correlation with PRVW in DM patients in order to better understand its potential implications in diabetic patients.

Evaluating the potential of retinal photography in chronic kidney disease detection: a review.

Background: Chronic kidney disease (CKD) is a significant global health concern, emphasizing the necessity of early detection to facilitate prompt clinical intervention. Leveraging the unique ability of the retina to offer insights into systemic vascular health, it emerges as an interesting, non-invasive option for early CKD detection. Integrating this approach with existing invasive methods could provide a comprehensive understanding of patient health, enhancing diagnostic accuracy and treatment effectiveness. Objectives: The purpose of this review is to critically assess the potential of retinal imaging to serve as a diagnostic tool for CKD detection based on retinal vascular changes. The review tracks the evolution from conventional manual evaluations to the latest state-of-the-art in deep learning. Survey Methodology: A comprehensive examination of the literature was carried out, using targeted database searches and a three-step methodology for article evaluation: identification, screening, and inclusion based on Prisma guidelines. Priority was given to unique and new research concerning the detection of CKD with retinal imaging. A total of 70 publications from 457 that were initially discovered satisfied our inclusion criteria and were thus subjected to analysis. Out of the 70 studies included, 35 investigated the correlation between diabetic retinopathy and CKD, 23 centered on the detection of CKD via retinal imaging, and four attempted to automate the detection through the combination of artificial intelligence and retinal imaging. Results: Significant retinal features such as arteriolar narrowing, venular widening, specific retinopathy markers (like microaneurysms, hemorrhages, and exudates), and changes in arteriovenous ratio (AVR) have shown strong correlations with CKD progression. We also found that the combination of deep learning with retinal imaging for CKD detection could provide a very promising pathway. Accordingly, leveraging retinal imaging through this technique is expected to enhance the precision and prognostic capacity of the CKD detection system, offering a non-invasive diagnostic alternative that could transform patient care practices. Conclusion: In summary, retinal imaging holds high potential as a diagnostic tool for CKD because it is non-invasive, facilitates early detection through observable microvascular changes, offers predictive insights into renal health, and, when paired with deep learning algorithms, enhances the accuracy and effectiveness of CKD screening.

Artificial intelligence-based classification of cardiac autonomic neuropathy from retinal fundus images in patients with diabetes: The Silesia Diabetes Heart Study.

BACKGROUND: Cardiac autonomic neuropathy (CAN) in diabetes mellitus (DM) is independently associated with cardiovascular (CV) events and CV death. Diagnosis of this complication of DM is time-consuming and not routinely performed in the clinical practice, in contrast to fundus retinal imaging which is accessible and routinely performed. Whether artificial intelligence (AI) utilizing retinal images collected through diabetic eye screening can provide an efficient diagnostic method for CAN is unknown. METHODS: This was a single center, observational study in a cohort of patients with DM as a part of the Cardiovascular Disease in Patients with Diabetes: The Silesia Diabetes-Heart Project (NCT05626413). To diagnose CAN, we used standard CV autonomic reflex tests. In this analysis we implemented AI-based deep learning techniques with non-mydriatic 5-field color fundus imaging to identify patients with CAN. Two experiments have been developed utilizing Multiple Instance Learning and primarily ResNet 18 as the backbone network. Models underwent training and validation prior to testing on an unseen image set. RESULTS: In an analysis of 2275 retinal images from 229 patients, the ResNet 18 backbone model demonstrated robust diagnostic capabilities in the binary classification of CAN, correctly identifying 93% of CAN cases and 89% of non-CAN cases within the test set. The model achieved an area under the receiver operating characteristic curve (AUCROC) of 0.87 (95% CI 0.74-0.97). For distinguishing between definite or severe stages of CAN (dsCAN), the ResNet 18 model accurately classified 78% of dsCAN cases and 93% of cases without dsCAN, with an AUCROC of 0.94 (95% CI 0.86-1.00). An alternate backbone model, ResWide 50, showed enhanced sensitivity at 89% for dsCAN, but with a marginally lower AUCROC of 0.91 (95% CI 0.73-1.00). CONCLUSIONS: AI-based algorithms utilising retinal images can differentiate with high accuracy patients with CAN. AI analysis of fundus images to detect CAN may be implemented in routine clinical practice to identify patients at the highest CV risk. TRIAL REGISTRATION: This is a part of the Silesia Diabetes-Heart Project (Clinical-Trials.gov Identifier: NCT05626413).

Evaluation of thickness of individual macular retinal layers in diabetic eyes from optical coherence tomography.

The effect of diabetes mellitus (DM) on individual retinal layers remains incompletely understood. We evaluated the intra-retinal layer thickness alterations in 71 DM eyes with no diabetic retinopathy (DR), 90 with mild DR, and 63 with moderate DR without macular edema, using spectral-domain optical coherence tomography (SD-OCT) and the Iowa Reference Algorithm for automated retinal layer segmentation. The average thickness of 10 intra-retinal layers was then corrected for ocular magnification using axial length measurements, and pairwise comparisons were made using multivariable linear regression models adjusted for gender and race. In DM no DR eyes, significant thinning was evident in the ganglion cell layer (GCL; p < 0.001), inner nuclear layer (INL; p = 0.001), and retinal pigment epithelium (RPE; p = 0.014) compared to normal eyes. Additionally, mild DR eyes exhibited a thinner inner plexiform layer (IPL; p = 0.008) than DM no DR eyes. Conversely, moderate DR eyes displayed thickening in the INL, outer nuclear layer, IPL, and retinal nerve fiber layer (all p ≤ 0.002), with notably worse vision. These findings highlight distinctive patterns: early diabetic eyes experience thinning in specific retinal layers, while moderate DR eyes exhibit thickening of certain layers and slightly compromised visual acuity, despite the absence of macular edema. Understanding these structural changes is crucial for comprehending diabetic eye complications.

VMseg: Using spatial variance to automatically segment retinal non-perfusion on OCT-angiography.

BACKGROUND AND OBJECTIVES: To develop and test VMseg, a new image processing algorithm performing automatic segmentation of retinal non-perfusion in widefield OCT-Angiography images, in order to estimate the non-perfusion index in diabetic patients. METHODS: We included diabetic patients with severe non-proliferative or proliferative diabetic retinopathy. We acquired images using the PlexElite 9000 OCT-A device with a photomontage of 5 images of size 12 x 12 mm. We then developed VMseg, a Python algorithm for non-perfusion detection, which binarizes a variance map calculated through convolution and morphological operations. We used 70% of our data set (development set) to fine-tune the algorithm parameters (convolution and morphological parameters, binarization thresholds) and evaluated the algorithm performance on the remaining 30% (test set). The obtained automatic segmentations were compared to a ground truth corresponding to manual segmentation from a retina expert and the inference processing time was estimated. RESULTS: We included 51 eyes of 30 patients (27 severe non-proliferative, 24 proliferative diabetic retinopathy). Using the optimal parameters found on the development set to tune the algorithm, the mean dice for the test set was 0.683 (sd = 0.175). We found a higher dice coefficient for images with a higher area of retinal non-perfusion (rs = 0.722, p < 10-4). There was a strong correlation (rs = 0.877, p < 10-4) between VMseg estimated non-perfusion indexes and indexes estimated using the ground truth segmentation. The Bland-Altman plot revealed that 3 eyes (5.9%) were significantly under-segmented by VMseg. CONCLUSION: We developed VMseg, an automatic algorithm for retinal non-perfusion segmentation on 12 x 12 mm OCT-A widefield photomontages. This simple algorithm was fast at inference time, segmented images in full-resolution and for the OCT-A format, was accurate enough for automatic estimation of retinal non-perfusion index in diabetic patients with diabetic retinopathy.

Differential Capillary and Large Vessel Analysis Improves OCTA Classification of Diabetic Retinopathy.

Purpose: This study aimed to investigate the impact of distinctive capillary-large vessel (CLV) analysis in optical coherence tomography angiography (OCTA) on the classification performance of diabetic retinopathy (DR). Methods: This multicenter study analyzed 212 OCTA images from 146 patients, including 28 controls, 36 diabetic patients without DR (NoDR), 31 with mild non-proliferative DR (NPDR), 28 with moderate NPDR, and 23 with severe NPDR. Quantitative features were derived from the whole image as well as the parafovea and perifovea regions. A support vector machine classifier was employed for DR classification. The accuracy and area under the receiver operating characteristic curve were used to evaluate the classification performance, utilizing features derived from the whole image and specific regions, both before and after CLV analysis. Results: Differential CLV analysis significantly improved OCTA classification of DR. In binary classifications, accuracy improved by 11.81%, rising from 77.45% to 89.26%, when utilizing whole image features. For multiclass classifications, accuracy increased by 7.55%, from 78.68% to 86.23%. Incorporating features from the whole image, parafovea, and perifovea further improved binary classification accuracy from 83.07% to 93.80%, and multiclass accuracy from 82.64% to 87.92%. Conclusions: This study demonstrated that feature changes in capillaries are more sensitive during DR progression, and CLV analysis can significantly improve DR classification performance by extracting features that are specific to large vessels and capillaries in OCTA. Incorporating regional features further improves DR classification accuracy. Differential CLV analysis promises better disease screening, diagnosis, and treatment outcome assessment.

Application of smartphone-based infrared thermography devices for ocular surface thermal imaging.

Infrared thermography (IRT) is a well-known imaging technique that provides a non-invasive displaying of the ocular surface temperature distribution. Currently, compact smartphone-based IRT devices, as well as special software for processing thermal images, have become available. The study aimed to determine the possible use of smartphone-based IRT devices for real-time ocular surface thermal imaging. This study involved 32 healthy individuals (64 eyes); 10 patients (10 eyes) with proliferative diabetic retinopathy (PDR) and absolute glaucoma; 10 patients (10 eyes) with PDR, who underwent vitreoretinal surgery. In all cases, simultaneous ocular surface IRT of both eyes was performed. In healthy individuals, the ocular surface temperature (OST) averaged 34.6 ± 0.8 °C and did not differ substantially between the paired eyes, in different age groups, and after pupil dilation. In our study, high intraocular pressure was accompanied by a decrease in OST in all cases. After vitreoretinal surgery in cases with confirmed subclinical inflammation, the OST was higher than the baseline and differed from that of the paired eye by more than 1.0 °C. These results highlight that smartphone-based IRT imaging could be useful for the non-invasive detection of OST asymmetry between paired eyes due to increased intraocular pressure or subclinical inflammation.

Evaluating Ocular Blood Flow in Diabetic Macular Edema using Three-dimensional Pseudocontinuous Arterial Spin Labeling.

BACKGROUND: Alterations in ocular blood flow play an important role in the pathogenesis of diabetic macular edema; however, this remains unclear. OBJECTIVES: This study aimed to investigate ocular blood flow in eyes with or without diabetic macular edema using arterial spin labeling. METHODS: This cross-sectional study included 118 eyes of 65 patients with diabetic retinopathy analyzed between November 2018 and December 2019. We included a total of 53 eyes without diabetic macular edema (mean [SD] age, 57.83 [7.23] years; 29 men [54.7%]) and 65 eyes with diabetic macular edema (mean [SD] age, 60.11 [7.63] years; 38 men [58.5%]). Using a 3.0-T magnetic resonance imaging, participants were imaged with arterial spin labeling with multiple post-labeling delays. RESULTS: The mean ocular blood flow at post-labeling delays of 1.5 and 2.5 s was significantly lower in eyes with diabetic macular edema among patients with diabetic retinopathy compared with the remaining subgroups (P=0.022 and P <0.001, respectively). The mean ocular blood flow exhibited a significant decrease in eyes with diabetic macular edema when the post-labeling delay was set at 2.5 s in the nonproliferative and proliferative diabetic retinopathy groups, compared with the remaining subgroups (P=0.005 and P=0.002, respectively). The cutoff points of ocular blood flow at post-labeling delays of 1.5 s and 2.5 s were 9.40 and 11.10 mL/100 g/min, respectively. CONCLUSION: Three-dimensional pseudocontinuous arterial spin labeling can identify differences in the ocular blood flow of patients with diabetic eyes with and without diabetic macular edema.

MAPLES-DR: MESSIDOR Anatomical and Pathological Labels for Explainable Screening of Diabetic Retinopathy.

Reliable automatic diagnosis of Diabetic Retinopathy (DR) and Macular Edema (ME) is an invaluable asset in improving the rate of monitored patients among at-risk populations and in enabling earlier treatments before the pathology progresses and threatens vision. However, the explainability of screening models is still an open question, and specifically designed datasets are required to support the research. We present MAPLES-DR (MESSIDOR Anatomical and Pathological Labels for Explainable Screening of Diabetic Retinopathy), which contains, for 198 images of the MESSIDOR public fundus dataset, new diagnoses for DR and ME as well as new pixel-wise segmentation maps for 10 anatomical and pathological biomarkers related to DR. This paper documents the design choices and the annotation procedure that produced MAPLES-DR, discusses the interobserver variability and the overall quality of the annotations, and provides guidelines on using the dataset in a machine learning context.

A novel approach for automatic classification of macular degeneration OCT images.

Age-related macular degeneration (AMD) and diabetic macular edema (DME) are significant causes of blindness worldwide. The prevalence of these diseases is steadily increasing due to population aging. Therefore, early diagnosis and prevention are crucial for effective treatment. Classification of Macular Degeneration OCT Images is a widely used method for assessing retinal lesions. However, there are two main challenges in OCT image classification: incomplete image feature extraction and lack of prominence in important positional features. To address these challenges, we proposed a deep learning neural network model called MSA-Net, which incorporates our proposed multi-scale architecture and spatial attention mechanism. Our multi-scale architecture is based on depthwise separable convolution, which ensures comprehensive feature extraction from multiple scales while minimizing the growth of model parameters. The spatial attention mechanism is aim to highlight the important positional features in the images, which emphasizes the representation of macular region features in OCT images. We test MSA-NET on the NEH dataset and the UCSD dataset, performing three-class (CNV, DURSEN, and NORMAL) and four-class (CNV, DURSEN, DME, and NORMAL) classification tasks. On the NEH dataset, the accuracy, sensitivity, and specificity are 98.1%, 97.9%, and 98.0%, respectively. After fine-tuning on the UCSD dataset, the accuracy, sensitivity, and specificity are 96.7%, 96.7%, and 98.9%, respectively. Experimental results demonstrate the excellent classification performance and generalization ability of our model compared to previous models and recent well-known OCT classification models, establishing it as a highly competitive intelligence classification approach in the field of macular degeneration.

[OCT biomarkers in diabetic maculopathy and artificial intelligence]. / OCT-Biomarker bei diabetischer Makulopathie und künstliche Intelligenz.

Diabetes mellitus is a chronic disease the microvascular complications of which include diabetic retinopathy and maculopathy. Diabetic macular edema, proliferative diabetic retinopathy, and diabetic macular ischemia pose a threat to visual acuity. Artificial intelligence can play an increasingly more important role in making the diagnosis and the treatment regimen of maculopathies in everyday clinical practice in the future. It can be used to automatically detect and quantify pathological parameters of the retina. The aim is to improve patient care in the clinical routine using so-called clinical decision support systems with personalized treatment algorithms. This review article outlines the current research regarding new biomarkers in diabetic maculopathy using optical coherence tomography (OCT) and OCT angiography (OCT-A).

Prediction of Long-Term Treatment Outcomes for Diabetic Macular Edema Using a Generative Adversarial Network.

Purpose: The purpose of this study was to analyze optical coherence tomography (OCT) images of generative adversarial networks (GANs) for the prediction of diabetic macular edema after long-term treatment. Methods: Diabetic macular edema (DME) eyes (n = 327) underwent anti-vascular endothelial growth factor (VEGF) treatments every 4 weeks for 52 weeks from a randomized controlled trial (CRTH258B2305, KINGFISHER) were included. OCT B-scan images through the foveal center at weeks 0, 4, 12, and 52, fundus photography, and retinal thickness (RT) maps were collected. GAN models were trained to generate probable OCT images after treatment. Input for each model were comprised of either the baseline B-scan alone or combined with additional OCT, thickness map, or fundus images. Generated OCT B-scan images were compared with real week 52 images. Results: For 30 test images, 28, 29, 15, and 30 gradable OCT images were generated by CycleGAN, UNIT, Pix2PixHD, and RegGAN, respectively. In comparison with the real week 52, these GAN models showed positive predictive value (PPV), sensitivity, specificity, and kappa for residual fluid ranging from 0.500 to 0.889, 0.455 to 1.000, 0.357 to 0.857, and 0.537 to 0.929, respectively. For hard exudate (HE), they were ranging from 0.500 to 1.000, 0.545 to 0.900, 0.600 to 1.000, and 0.642 to 0.894, respectively. Models trained with week 4 and 12 B-scans as additional inputs to the baseline B-scan showed improved performance. Conclusions: GAN models could predict residual fluid and HE after long-term anti-VEGF treatment of DME. Translational Relevance: The implementation of this tool may help identify potential nonresponders after long-term treatment, thereby facilitating management planning for these eyes.

Multi-Plexus Nonperfusion Area Segmentation in Widefield OCT Angiography Using a Deep Convolutional Neural Network.

Purpose: To train and validate a convolutional neural network to segment nonperfusion areas (NPAs) in multiple retinal vascular plexuses on widefield optical coherence tomography angiography (OCTA). Methods: This cross-sectional study included 202 participants with a full range of diabetic retinopathy (DR) severities (diabetes mellitus without retinopathy, mild to moderate non-proliferative DR, severe non-proliferative DR, and proliferative DR) and 39 healthy participants. Consecutive 6 × 6-mm OCTA scans at the central macula, optic disc, and temporal region in one eye from 202 participants in a clinical DR study were acquired with a 70-kHz OCT commercial system (RTVue-XR). Widefield OCTA en face images were generated by montaging the scans from these three regions. A projection-resolved OCTA algorithm was applied to remove projection artifacts at the voxel scale. A deep convolutional neural network with a parallel U-Net module was designed to detect NPAs and distinguish signal reduction artifacts from flow deficits in the superficial vascular complex (SVC), intermediate capillary plexus (ICP), and deep capillary plexus (DCP). Expert graders manually labeled NPAs and signal reduction artifacts for the ground truth. Sixfold cross-validation was used to evaluate the proposed algorithm on the entire dataset. Results: The proposed algorithm showed high agreement with the manually delineated ground truth for NPA detection in three retinal vascular plexuses on widefield OCTA (mean ± SD F-score: SVC, 0.84 ± 0.05; ICP, 0.87 ± 0.04; DCP, 0.83 ± 0.07). The extrafoveal avascular area in the DCP showed the best sensitivity for differentiating eyes with diabetes but no retinopathy (77%) from healthy controls and for differentiating DR by severity: DR versus no DR, 77%; referable DR (rDR) versus non-referable DR (nrDR), 79%; vision-threatening DR (vtDR) versus non-vision-threatening DR (nvtDR), 60%. The DCP also showed the best area under the receiver operating characteristic curve for distinguishing diabetes from healthy controls (96%), DR versus no DR (95%), and rDR versus nrDR (96%). The three-plexus-combined OCTA achieved the best result in differentiating vtDR and nvtDR (81.0%). Conclusions: A deep learning network can accurately segment NPAs in individual retinal vascular plexuses and improve DR diagnostic accuracy. Translational Relevance: Using a deep learning method to segment nonperfusion areas in widefield OCTA can potentially improve the diagnostic accuracy of diabetic retinopathy by OCT/OCTA systems.

A deep learning framework for the early detection of multi-retinal diseases.

Retinal images play a pivotal contribution to the diagnosis of various ocular conditions by ophthalmologists. Extensive research was conducted to enable early detection and timely treatment using deep learning algorithms for retinal fundus images. Quick diagnosis and treatment planning can be facilitated by deep learning models' ability to process images rapidly and deliver outcomes instantly. Our research aims to provide a non-invasive method for early detection and timely eye disease treatment using a Convolutional Neural Network (CNN). We used a dataset Retinal Fundus Multi-disease Image Dataset (RFMiD), which contains various categories of fundus images representing different eye diseases, including Media Haze (MH), Optic Disc Cupping (ODC), Diabetic Retinopathy (DR), and healthy images (WNL). Several pre-processing techniques were applied to improve the model's performance, such as data augmentation, cropping, resizing, dataset splitting, converting images to arrays, and one-hot encoding. CNNs have extracted extract pertinent features from the input color fundus images. These extracted features are employed to make predictive diagnostic decisions. In this article three CNN models were used to perform experiments. The model's performance is assessed utilizing statistical metrics such as accuracy, F1 score, recall, and precision. Based on the results, the developed framework demonstrates promising performance with accuracy rates of up to 89.81% for validation and 88.72% for testing using 12-layer CNN after Data Augmentation. The accuracy rate obtained from 20-layer CNN is 90.34% for validation and 89.59% for testing with Augmented data. The accuracy obtained from 20-layer CNN is greater but this model shows overfitting. These accuracy rates suggested that the deep learning model has learned to distinguish between different eye disease categories and healthy images effectively. This study's contribution lies in providing a reliable and efficient diagnostic system for the simultaneous detection of multiple eye diseases through the analysis of color fundus images.

Long-Term Effects of Intravitreal Ranibizumab Compared With Panretinal Photocoagulation on Optical Coherence Tomography Measured Choroidal Thickness and Vascularity.

Purpose: Compare choroidal changes in ranibizumab versus panretinal photocoagulation (PRP)-treated eyes with proliferative diabetic retinopathy (PDR). Methods: DRCR Retina Network Protocol S post hoc analysis evaluated optical coherence tomography change in choroidal thickness (subfoveal and 3mm superior and inferior to the fovea) through five years; choroidal vascularity index (CVI) was assessed at baseline and one year. Mixed linear models for choroidal change included adjustments for the baseline choroidal value and age. Results: This study included 328 eyes (158 ranibizumab and 170 PRP) from 256 participants (88 ranibizumab and 95 PRP eyes at five years). Mean change in choroidal thickness from baseline to five years at the fovea was -12 µm in ranibizumab versus -8 µm in PRP (difference [95% confidence interval]: -4 [-18 to 10], P = 0.57), superior was -14 µm versus -19 µm (difference: 5 [-8 to 17], P = 0.45) and inferior was -26 µm versus -32 µm [difference: 5 (-9 to 20), P = 0.45]; change at all three points within the ranibizumab group, and the superior and inferior points for PRP, were statistically significant (P < .05). Mean change in CVI at one year was -0.02% in ranibizumab versus -0.95% in PRP (difference: 0.93 [-0.35 to 2.21], P = 0.14). Conclusions: In patients with PDR, treatment with ranibizumab versus PRP did not result in statistically significant differences in five-year choroidal thickness or one-year CVI change. Both groups had significant decreases in choroidal thickness at five years. Translational Relevance: Ranibizumab treatment for PDR did not statistically significantly affect choroidal thickness or vascularity differently than PRP.

A health economic pilot study comparing two diabetic retinopathy screening strategies.

To compare two screening strategies for diabetic retinopathy (DR), and to determine the health-economic impact of including optical coherence tomography (OCT) in a regular DR screening. This cross-sectional study included a cohort of patients (≥ 18 years) with type 1 or 2 diabetes mellitus (T1D or T2D) from a pilot DR screening program at Oslo University Hospital, Norway. A combined screening strategy where OCT was performed in addition to fundus photography for all patients, was conducted on this cohort and compared to our existing sequential screening strategy. In the sequential screening strategy, OCT was performed on a separate day only if fundus photography indicated diabetic macular edema (DME). The presence of diabetic maculopathy on fundus photography and DME on OCT was determined by two medical retina specialists. Based on the prevalence rate of diabetic maculopathy and DME from the pilot, we determined the health-economic impact of the two screening strategies. The study included 180 eyes of 90 patients. Twenty-seven eyes of 18 patients had diabetic maculopathy, and of these, 7 eyes of 6 patients revealed DME on OCT. When diabetic maculopathy was absent on fundus photographs, OCT could not reveal DME. Accordingly, 18 patients (20%) with diabetic maculopathy would have needed an additional examination with OCT in the sequential screening strategy, 6 (33%) of whom would have had DME on OCT. In an extended healthcare perspective analysis, the cost of the sequential screening strategy was higher than the cost of the combined screening strategy. There was a weak association between diabetic maculopathy on fundus photography and DME on OCT. The health economic analysis suggests that including OCT as a standard test in DR screening could potentially be cost-saving.

A hybrid model for the detection of retinal disorders using artificial intelligence techniques.

The prevalence of vision impairment is increasing at an alarming rate. The goal of the study was to create an automated method that uses optical coherence tomography (OCT) to classify retinal disorders into four categories: choroidal neovascularization, diabetic macular edema, drusen, and normal cases. This study proposed a new framework that combines machine learning and deep learning-based techniques. The utilized classifiers were support vector machine (SVM), K-nearest neighbor (K-NN), decision tree (DT), and ensemble model (EM). A feature extractor, the InceptionV3 convolutional neural network, was also employed. The performance of the models was evaluated against nine criteria using a dataset of 18000 OCT images. For the SVM, K-NN, DT, and EM classifiers, the analysis exhibited state-of-the-art performance, with classification accuracies of 99.43%, 99.54%, 97.98%, and 99.31%, respectively. A promising methodology has been introduced for the automatic identification and classification of retinal disorders, leading to reduced human error and saved time.

A deep learning approach to hard exudates detection and disorganization of retinal inner layers identification on OCT images.

The purpose of the study was to detect Hard Exudates (HE) and classify Disorganization of Retinal Inner Layers (DRIL) implementing a Deep Learning (DL) system on optical coherence tomography (OCT) images of eyes with diabetic macular edema (DME). We collected a dataset composed of 442 OCT images on which we annotated 6847 HE and the presence of DRIL. A complex operational pipeline was defined to implement data cleaning and image transformations, and train two DL models. The state-of-the-art neural network architectures (Yolov7, ConvNeXt, RegNetX) and advanced techniques were exploited to aggregate the results (Ensemble learning, Edge detection) and obtain a final model. The DL approach reached good performance in detecting HE and classifying DRIL. Regarding HE detection the model got an AP@0.5 score equal to 34.4% with Precision of 48.7% and Recall of 43.1%; while for DRIL classification an Accuracy of 91.1% with Sensitivity and Specificity both of 91.1% and AUC and AUPR values equal to 91% were obtained. The P-value was lower than 0.05 and the Kappa coefficient was 0.82. The DL models proved to be able to identify HE and DRIL in eyes with DME with a very good accuracy and all the metrics calculated confirmed the system performance. Our DL approach demonstrated to be a good candidate as a supporting tool for ophthalmologists in OCT images analysis.

Hybrid deep learning models for the screening of Diabetic Macular Edema in optical coherence tomography volumes.

Several studies published so far used highly selective image datasets from unclear sources to train computer vision models and that may lead to overestimated results, while those studies conducted in real-life remain scarce. To avoid image selection bias, we stacked convolutional and recurrent neural networks (CNN-RNN) to analyze complete optical coherence tomography (OCT) cubes in a row and predict diabetic macular edema (DME), in a real-world diabetic retinopathy screening program. A retrospective cohort study was carried out. Throughout 4-years, 5314 OCT cubes from 4408 subjects who attended to the diabetic retinopathy (DR) screening program were included. We arranged twenty-two (22) pre-trained CNNs in parallel with a bidirectional RNN layer stacked at the bottom, allowing the model to make a prediction for the whole OCT cube. The staff of retina experts built a ground truth of DME later used to train a set of these CNN-RNN models with different configurations. For each trained CNN-RNN model, we performed threshold tuning to find the optimal cut-off point for binary classification of DME. Finally, the best models were selected according to sensitivity, specificity, and area under the receiver operating characteristics curve (AUROC) with their 95% confidence intervals (95%CI). An ensemble of the best models was also explored. 5188 cubes were non-DME and 126 were DME. Three models achieved an AUROC of 0.94. Among these, sensitivity, and specificity (95%CI) ranged from 84.1-90.5 and 89.7-93.3, respectively, at threshold 1, from 89.7-92.1 and 80-83.1 at threshold 2, and from 80.2-81 and 93.8-97, at threshold 3. The ensemble model improved these results, and lower specificity was observed among subjects with sight-threatening DR. Analysis by age, gender, or grade of DME did not vary the performance of the models. CNN-RNN models showed high diagnostic accuracy for detecting DME in a real-world setting. This engine allowed us to detect extra-foveal DMEs commonly overlooked in other studies, and showed potential for application as the first filter of non-referable patients in an outpatient center within a population-based DR screening program, otherwise ended up in specialized care.

A Retinal Vessel Segmentation Method Based on the Sharpness-Aware Minimization Model.

Retinal vessel segmentation is crucial for diagnosing and monitoring various eye diseases such as diabetic retinopathy, glaucoma, and hypertension. In this study, we examine how sharpness-aware minimization (SAM) can improve RF-UNet's generalization performance. RF-UNet is a novel model for retinal vessel segmentation. We focused our experiments on the digital retinal images for vessel extraction (DRIVE) dataset, which is a benchmark for retinal vessel segmentation, and our test results show that adding SAM to the training procedure leads to notable improvements. Compared to the non-SAM model (training loss of 0.45709 and validation loss of 0.40266), the SAM-trained RF-UNet model achieved a significant reduction in both training loss (0.094225) and validation loss (0.08053). Furthermore, compared to the non-SAM model (training accuracy of 0.90169 and validation accuracy of 0.93999), the SAM-trained model demonstrated higher training accuracy (0.96225) and validation accuracy (0.96821). Additionally, the model performed better in terms of sensitivity, specificity, AUC, and F1 score, indicating improved generalization to unseen data. Our results corroborate the notion that SAM facilitates the learning of flatter minima, thereby improving generalization, and are consistent with other research highlighting the advantages of advanced optimization methods. With wider implications for other medical imaging tasks, these results imply that SAM can successfully reduce overfitting and enhance the robustness of retinal vessel segmentation models. Prospective research avenues encompass verifying the model on vaster and more diverse datasets and investigating its practical implementation in real-world clinical situations.