Classification Of Diabetic Macular Edema Research Articles

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.

Self-supervised category selective attention classifier network for diabetic macular edema classification.

This study aims to develop an advanced model for the classification of Diabetic Macular Edema (DME) using deep learning techniques. Specifically, the objective is to introduce a novel architecture, SSCSAC-Net, that leverages self-supervised learning and category-selective attention mechanisms to improve the precision of DME classification. The proposed SSCSAC-Net integrates self-supervised learning to effectively utilize unlabeled data for learning robust features related to DME. Additionally, it incorporates a category-specific attention mechanism and a domain-specific layer into the ResNet-152 base architecture. The model is trained using an ensemble of unsupervised and supervised learning techniques. Benchmark datasets are utilized for testing the model's performance, ensuring its robustness and generalizability across different data distributions. Evaluation of the SSCSAC-Net on multiple datasets demonstrates its superior performance compared to existing techniques. The model achieves high accuracy, precision, and recall rates, with an accuracy of 98.7%, precision of 98.6%, and recall of 98.8%. Furthermore, the incorporation of self-supervised learning reduces the dependency on extensive labeled data, making the solution more scalable and cost-effective. The proposed SSCSAC-Net represents a significant advancement in automated DME classification. By effectively using self-supervised learning and attention mechanisms, the model offers improved accuracy in identifying DME-related features within retinal images. Its robustness and generalizability across different datasets highlight its potential for clinical applications, providing a valuable tool for clinicians in diagnosing DME effectively.

Visual Outcome after Anti-Vascular Epithelial Growth Factor Therapy Using New Classification of Diabetic Macular Edema by Optical Coherence Tomography.

The aim of the study was to examine alterations in visual acuity in patients with diabetic macular edema (DME), classified according to the TCED-HFV optical coherence tomography (OCT) system, following anti-vascular epithelial growth factor (VEGF) therapy. The medical records of patients with DME receiving anti-VEGF therapy were retrospectively reviewed. Patients were divided into four groups according to the TCED-HFV OCT classification. Patient demographic and clinical characteristics and best-corrected visual acuity (BCVA) before and after treatment were compared among the groups. The BCVA before treatment was 0.49 ± 0.18, 0.81 ± 0.41, 0.83 ± 0.41, and 0.82 ± 0.49 in the early DME, advanced DME, severe DME, and atrophic maculopathy groups, respectively. The BCVA in the early DME group was therefore significantly lower than that in the other three groups (p = 0.042). After treatment, the BCVA improved to 0.15 ± 0.17, 0.52 ± 0.31, 0.62 ± 0.32, and 0.69 ± 0.47 in the early DME, advanced DME, severe DME, and atrophic maculopathy groups, respectively (p < 0.005). There were some differences among patients in the four groups in terms of the duration of diabetes, percentage of hemoglobin A1c, and duration of hypertension. The TCED-HFV OCT classification of patients with DME is exact and functional and can allow the severity of DME, and its response to anti-VEGF therapy, to be estimated.

Detection and Classification of Diabetic Macular Edema with a Desktop-Based Code-Free Machine Learning Tool.

To evaluate the effectiveness of the Lobe application, a machine learning (ML) tool that can be used on a personal computer without requiring coding expertise, in the recognition and classification of diabetic macular edema (DME) in spectral-domain optical coherence tomography (SD-OCT) scans. A total of 695 cross-sectional SD-OCT images from 336 patients with DME and 200 OCT images of 200 healthy controls were included. Images with DME were classified into three main types: diffuse retinal edema (DRE), cystoid macular edema (CME), and cystoid macular degeneration (CMD). To develop the ML model, we used the desktop-based code-free Lobe application, which includes a pre-trained ResNet-50 V2 convolutional neural network and is available free of charge. The performance of the trained model in recognizing and classifying DME was evaluated with 41 DRE, 28 CMD, 70 CME, and 40 normal SD-OCT images that were not used in the training. The developed model showed 99.28% sensitivity and 100% specificity for class-independent detection of DME. Sensitivity and specificity by labels were 87.80% and 98.57% for DRE, 96.43% and 99.29% for CME, and 95.71% and 95.41% for CMD, respectively. To our knowledge, this is the first evaluation of the effectiveness of Lobe with ophthalmological images, and the results indicate that it can be used with high efficiency in the recognition and classification of DME from SD-OCT images by ophthalmologists without coding expertise.

A comprehensive computer-aided system for an early-stage diagnosis and classification of diabetic macular edema

Diabetic macular edema (DME) is a condition of retinal swelling due to the accumulation of leaked plasma in the extracellular space in the retina, known as the macula. DME is a chronic progressive retinal disorder that likely results in permanent complete blindness. The early signs of DME are not discernible by merely suspecting the fundus picture with the naked eye. Therefore, a computer-assisted diagnostic system could aid ophthalmologists in screening, diagnosing, and treating DME. This study proposes an efficient and complete model for early diagnosis and staging of DME. To overcome the challenges in precise localization of fovea, blood vessel network extraction, and accurate lesion segmentation, improved image relative subtraction, Gabor wavelet filter, and novel advanced fuzzy c-means clustering algorithms are introduced, respectively. Finally, the Bayesian classifier using the Gaussian function with expectation maximization is used for DME grading. The accurate optic disc and fovea localization, exudates’ segmentation, and classification improved the overall system’s performance. The proposed model achieves an average accuracy of 96.17%, 98.60%, 97.85%, and 98.80% for optic disc detection, fovea localization, exudates segmentation, and DME classification, respectively. The performance of the proposed model compared to the competitive studies illustrates the superiority of the suggested methodology.

Deep semi-supervised multiple instance learning with self-correction for DME classification from OCT images.

Supervised deep learning has achieved prominent success in various diabetic macular edema (DME) recognition tasks from optical coherence tomography (OCT) volumetric images. A common problematic issue that frequently occurs in this field is the shortage of labeled data due to the expensive fine-grained annotations, which increases substantial difficulty in accurate analysis by supervised learning. The morphological changes in the retina caused by DME might be distributed sparsely in B-scan images of the OCT volume, and OCT data is often coarsely labeled at the volume level. Hence, the DME identification task can be formulated as a multiple instance classification problem that could be addressed by multiple instance learning (MIL) techniques. Nevertheless, none of previous studies utilize unlabeled data simultaneously to promote the classification accuracy, which is particularly significant for a high quality of analysis at the minimum annotation cost. To this end, we present a novel deep semi-supervised multiple instance learning framework to explore the feasibility of leveraging a small amount of coarsely labeled data and a large amount of unlabeled data to tackle this problem. Specifically, we come up with several modules to further improve the performance according to the availability and granularity of their labels. To warm up the training, we propagate the bag labels to the corresponding instances as the supervision of training, and propose a self-correction strategy to handle the label noise in the positive bags. This strategy is based on confidence-based pseudo-labeling with consistency regularization. The model uses its prediction to generate the pseudo-label for each weakly augmented input only if it is highly confident about the prediction, which is subsequently used to supervise the same input in a strongly augmented version. This learning scheme is also applicable to unlabeled data. To enhance the discrimination capability of the model, we introduce the Student-Teacher architecture and impose consistency constraints between two models. For demonstration, the proposed approach was evaluated on two large-scale DME OCT image datasets. Extensive results indicate that the proposed method improves DME classification with the incorporation of unlabeled data and outperforms competing MIL methods significantly, which confirm the feasibility of deep semi-supervised multiple instance learning at a low annotation cost.

DIABETIC MACULAR EDEMA CLASSIFICATION WITH OCT IMAGES USING GENERATIVE ADVERSARIAL NETWORK AND ACTIVE CONTOUR MODEL

The major reason for blindness is diabetic macular edema (DME) and hence detection of DME at early stage using optical coherence tomography (OCT) is commonly employed for diagnosing retinal diseases. An accurate disease identification and classification poses a challenging task due to the difficulty in differentiating the abnormal and healthy regions. To overcome these issues and to accurately classify the DME, an effective DME classification approach named antlion spider monkey optimization-based generative adversarial network (ALSMO-based GAN) is proposed in this research for segmenting the retinal layers and to classify the DME more accurately. With the generator and the discriminator components of GAN, the DME is effectively classified so that the devised ALSMO algorithm can be used to train the process of GAN. The inspiration of the foraging and the hunting behavior enable the optimization to increase the rate of convergence and to achieve global optimal solution by reducing the local optima. With the segmented retinal layer, the classification process is progressed through the extraction of relevant features from the retinal layers. The performance of the developed method is verified using measures like accuracy, sensitivity, and specificity which attained values of 92.5%, 98%, and 92.3%, respectively.

Using Artificial Intelligence for Analyzing Retinal Images (OCT) in People with Diabetes: Detecting Diabetic Macular Edema Using Deep Learning Approach

Medical imaging evolved rapidly to play a vital role in diagnosis and treatment of a disease. Automate analysis of medical image analysis has increased effectively through the use of deep learning techniques to obtain much quicker classifications once trained and learn relevant features for specific tasks, shown to be assessable in clinical practice and valuable tool to support decision making in medical field. Within Opthalmology, Optical Coherence Tomography (OCT) is a volumetric imaging procedure that uses in the diagnosis, monitoring and measuring response to treatment in eyes. Early detection of eyes diseases including Diabetic Macular Edema (DME) is vital process to avoid complications such as blindness. This work employed a deep convolutional neural network (CNN) based method for DME classification task. To demonstrate the impact of convolutional, five models with different Convolutional layers built then the best one selected based on evaluation metrics. The accuracy of model improved while increasing the number of Convolutional Layers and achieved 82% by 5-Convolutional Layer, Precision and Recall of CNN model per DME class was 87%% and 74%, respectively. These results highlighted the potential of deep learning in assisting decision-making in patients with DME.

DFTSA-Net: Deep Feature Transfer-Based Stacked Autoencoder Network for DME Diagnosis

Diabetic macular edema (DME) is the most common cause of irreversible vision loss in diabetes patients. Early diagnosis of DME is necessary for effective treatment of the disease. Visual detection of DME in retinal screening images by ophthalmologists is a time-consuming process. Recently, many computer-aided diagnosis systems have been developed to assist doctors by detecting DME automatically. In this paper, a new deep feature transfer-based stacked autoencoder neural network system is proposed for the automatic diagnosis of DME in fundus images. The proposed system integrates the power of pretrained convolutional neural networks as automatic feature extractors with the power of stacked autoencoders in feature selection and classification. Moreover, the system enables extracting a large set of features from a small input dataset using four standard pretrained deep networks: ResNet-50, SqueezeNet, Inception-v3, and GoogLeNet. The most informative features are then selected by a stacked autoencoder neural network. The stacked network is trained in a semi-supervised manner and is used for the classification of DME. It is found that the introduced system achieves a maximum classification accuracy of 96.8%, sensitivity of 97.5%, and specificity of 95.5%. The proposed system shows a superior performance over the original pretrained network classifiers and state-of-the-art findings.

A Multitask Deep-Learning System to Classify Diabetic Macular Edema for Different Optical Coherence Tomography Devices: A Multicenter Analysis.

Diabetic macular edema (DME) is the primary cause of vision loss among individuals with diabetes mellitus (DM). We developed, validated, and tested a deep learning (DL) system for classifying DME using images from three common commercially available optical coherence tomography (OCT) devices. We trained and validated two versions of a multitask convolution neural network (CNN) to classify DME (center-involved DME [CI-DME], non-CI-DME, or absence of DME) using three-dimensional (3D) volume scans and 2D B-scans, respectively. For both 3D and 2D CNNs, we used the residual network (ResNet) as the backbone. For the 3D CNN, we used a 3D version of ResNet-34 with the last fully connected layer removed as the feature extraction module. A total of 73,746 OCT images were used for training and primary validation. External testing was performed using 26,981 images across seven independent data sets from Singapore, Hong Kong, the U.S., China, and Australia. In classifying the presence or absence of DME, the DL system achieved area under the receiver operating characteristic curves (AUROCs) of 0.937 (95% CI 0.920-0.954), 0.958 (0.930-0.977), and 0.965 (0.948-0.977) for the primary data set obtained from CIRRUS, SPECTRALIS, and Triton OCTs, respectively, in addition to AUROCs >0.906 for the external data sets. For further classification of the CI-DME and non-CI-DME subgroups, the AUROCs were 0.968 (0.940-0.995), 0.951 (0.898-0.982), and 0.975 (0.947-0.991) for the primary data set and >0.894 for the external data sets. We demonstrated excellent performance with a DL system for the automated classification of DME, highlighting its potential as a promising second-line screening tool for patients with DM, which may potentially create a more effective triaging mechanism to eye clinics.

Detection of Diabetic Eye Disease from Retinal Images Using a Deep Learning Based CenterNet Model.

Diabetic retinopathy (DR) is an eye disease that alters the blood vessels of a person suffering from diabetes. Diabetic macular edema (DME) occurs when DR affects the macula, which causes fluid accumulation in the macula. Efficient screening systems require experts to manually analyze images to recognize diseases. However, due to the challenging nature of the screening method and lack of trained human resources, devising effective screening-oriented treatment is an expensive task. Automated systems are trying to cope with these challenges; however, these methods do not generalize well to multiple diseases and real-world scenarios. To solve the aforementioned issues, we propose a new method comprising two main steps. The first involves dataset preparation and feature extraction and the other relates to improving a custom deep learning based CenterNet model trained for eye disease classification. Initially, we generate annotations for suspected samples to locate the precise region of interest, while the other part of the proposed solution trains the Center Net model over annotated images. Specifically, we use DenseNet-100 as a feature extraction method on which the one-stage detector, CenterNet, is employed to localize and classify the disease lesions. We evaluated our method over challenging datasets, namely, APTOS-2019 and IDRiD, and attained average accuracy of 97.93% and 98.10%, respectively. We also performed cross-dataset validation with benchmark EYEPACS and Diaretdb1 datasets. Both qualitative and quantitative results demonstrate that our proposed approach outperforms state-of-the-art methods due to more effective localization power of CenterNet, as it can easily recognize small lesions and deal with over-fitted training data. Our proposed framework is proficient in correctly locating and classifying disease lesions. In comparison to existing DR and DME classification approaches, our method can extract representative key points from low-intensity and noisy images and accurately classify them. Hence our approach can play an important role in automated detection and recognition of DR and DME lesions.

Influence of segmental supply of Cilioretinal artery on morphology of diabetic macular edema

BackgroundThe supply of Cilioretinal artery (CRA) to different layers of the retina influences retinal pathologies such as diabetic retinopathy (DR). Since the supply of CRA is segmental, our aim was to analyze the location of CRA with respect to non – center involving diabetic macular edema (DME) differentiated by various segments and center involving DME based on Early Treatment of Diabetic Retinopathy Study (ETDRS) scale using optical coherence tomography (OCT).MethodsA retrospective study was conducted in which forty-three patients with various stages of DR and the presence of CRA were identified. Presence and location of CRA was recognized using fundus fluorescein angiography. Classification of DME was based on ETDRS subfields on OCT.ResultsEvaluation of 26 men and 17 women with varying degrees of severity involving DR revealed the presence of unilateral CRA in 40 subjects and bilateral CRA in 3 subjects. When CRA supplied the central area, maximum retinal thickness was noted at the temporal quadrant (271.67 ± 164.02 μm) along with non - center involving DME (194.87 ± 121.06 μm); when CRA supplied the lower area, maximum retinal thickness was noted at the superior quadrant (293.64 ± 159.36 μm) along with center involving DME (395 ± 285.75 μm) and when it supplied the upper area, maximum retinal thickness was noted at the nasal quadrant (293.49 ± 176.18 μm) along with center involving DME (292 ± 192.79 μm).ConclusionThe presence of CRA seems to influence the morphology of the retina amongst patients diagnosed with DR by altering the segments involved in DME based on its supply location. However, further studies with a larger sample size are warranted to strenghten this association.

OctNET: A Lightweight CNN for Retinal Disease Classification from Optical Coherence Tomography Images

Background and ObjectiveRetinal diseases are becoming a major health problem in recent years. Their early detection and ensuing treatment are essential to prevent visual damage, as the number of people affected by diabetes is expected to grow exponentially. Retinal diseases progress slowly, without any discernible symptoms. Optical Coherence Tomography (OCT) is a diagnostic tool capable of analyzing and identifying the quantitative discrimination in the disease affected retinal layers with high resolution. This paper proposes a deep neural network-based classifier for the computer-aided classification of Diabetic Macular Edema (DME), drusen, Choroidal NeoVascularization (CNV) from normal OCT images of the retina. MethodsIn the proposed method, we demonstrate the feasibility of classifying and detecting severe retinal pathologies from OCT images using a deep convolutional neural network having six convolutional blocks. The classification results are explained using a gradient-based class activation mapping algorithm. ResultsTraining and validation of the model are performed on a public dataset of 83,484 images with expert-level disease grading of CNV, DME, and drusen, in addition to normal retinal image. We achieved a precision of 99.69%, recall of 99.69%, and accuracy of 99.69% with only three misclassifications out of 968 test cases. ConclusionIn the proposed work, downsampling and weight sharing were introduced to improve the training efficiency and were found to reduce the trainable parameters significantly. The class activation mapping was also performed, and the output image was similar to the retina’s actual color OCT images. The proposed network used only 6.9% of learnable parameters compared to the existing ResNet-50 model and yet outperformed it in classification. The proposed work can be potentially employed in real-time applications due to reduced complexity and fewer learnable parameters over other models.

HyCAD-OCT: A Hybrid Computer-Aided Diagnosis of Retinopathy by Optical Coherence Tomography Integrating Machine Learning and Feature Maps Localization

Optical Coherence Tomography (OCT) imaging has major advantages in effectively identifying the presence of various ocular pathologies and detecting a wide range of macular diseases. OCT examinations can aid in the detection of many retina disorders in early stages that could not be detected in traditional retina images. In this paper, a new hybrid computer-aided OCT diagnostic system (HyCAD) is proposed for classification of Diabetic Macular Edema (DME), Choroidal Neovascularization (CNV) and drusen disorders, while separating them from Normal OCT images. The proposed HyCAD hybrid learning system integrates the segmentation of Region of Interest (RoI), based on central serious chorioretinopathy (CSC) in Spectral Domain Optical Coherence Tomography (SD-OCT) images, with deep learning architectures for effective diagnosis of retinal disorders. The proposed system assimilates a range of techniques including RoI localization and feature extraction, followed by classification and diagnosis. An efficient feature fusion phase has been introduced for combining the OCT image features, extracted by Deep Convolutional Neural Network (CNN), with the features extracted from the RoI segmentation phase. This fused feature set is used to predict multiclass OCT retina disorders. The proposed segmentation phase of retinal RoI regions adds substantial contribution as it draws attention to the most significant areas that are candidate for diagnosis. A new modified deep learning architecture (Norm-VGG16) is introduced integrating a kernel regularizer. Norm-VGG16 is trained from scratch on a large benchmark dataset and used in RoI localization and segmentation. Various experiments have been carried out to illustrate the performance of the proposed system. Large Dataset of Labeled Optical Coherence Tomography (OCT) v3 benchmark is used to validate the efficiency of the model compared with others in literature. The experimental results show that the proposed model achieves relatively high-performance in terms of accuracy, sensitivity and specificity. An average accuracy, sensitivity and specificity of 98.8%, 99.4% and 98.2% is achieved, respectively. The remarkable performance achieved reflects that the fusion phase can effectively improve the identification ratio of the urgent patients’ diagnostic images and clinical data. In addition, an outstanding performance is achieved compared to others in literature.

Classification of dry age‐related macular degeneration and diabetic macular oedema from optical coherence tomography images using dictionary learning

Age-related Macular Degeneration (AMD) and Diabetic Macular Edema (DME) are the major causes of vision loss in developed countries. Alteration of retinal layer structure and appearance of exudates are the most significant signs of these diseases. In this paper, with the aim of automatic classification of DME, AMD, and normal subjects using Optical Coherence Tomography (OCT) images, a dictionary-learning based classification is proposed. The two important issues intended in this approach are avoiding retinal layer segmentation and attempting to mimic the authors' understanding based on normal and abnormal region identifications, considering that the signs of diseases appear in a small fraction of B-Scans. The histogram of oriented gradients feature descriptor was utilized to characterize the distribution of local intensity gradients and edge directions. To capture the structure of extracted features, different dictionary learning-based classifiers are employed. The dataset consists of 45 subjects: 15 patients with AMD, 15 patients with DME, and 15 normal subjects. The proposed classifier leads to an accuracy of 95.13, 100.00, and 100.00% for DME, AMD, and normal OCT images, respectively, only by considering 4% of all B-Scans of a volume, which outperforms the state-of-the-art methods.

Spectral domain optical coherence tomography classification of diabetic macular edema: a new proposal to clinical practice.

To classify the types of diabetic macular edema (DME) and evaluate its morphological features on spectral domain optical coherence tomography (SD-OCT) and determine correlations between visual acuity and OCT findings. We assessed 406 eyes of 309 patients with a diagnosis of DME retrospectively. Three types based on SD-OCT were identified: diffuse macular edema, cystoid macular edema, and cystoid degeneration. Morphological features such as serous macular detachment (SMD), vitreomacular interface abnormalities (VMAI), hard exudates, photoreceptor status, and correlations between visual acuity and those morphological features were also evaluated by SD-OCT. The most common type of DME was cystoid edema (68.5%). No statistically significant difference was found between groups in sex (P = 0.40), type of diabetes (P = 0.50), or diabetic retinopathy (P=0.78). However, the duration of symptoms and BCVA was significantly lower in the group with cystoid degeneration compared with the group with cystoid edema (P < 0.001) and the group with diffuse macular edema (P < 0.001). In the group with cystoid degeneration compared with the groups with cystoid and diffuse edema, the central fovea and central subfield were significantly thicker (both (P < 0.001), the subfoveal choroid was significantly thinner (P = 0.049), rate of serous macular detachment was significantly lower (P < 0.001), and the rate of outer retinal damage was significantly higher (P < 0.001). Cystoid macular degeneration, which is consistent with poor functional and morphological outcomes, should be differentiated from cystoid macular edema. Serous macular detachment, which is mostly seen in eyes with early stages of DME, should be evaluated as an accompanying morphological finding rather than a type of DME.

Optical coherence tomography image for automatic classification of diabetic macular edema

Diabetic macular edema (DME) is the dominant reason of diabetic visual loss, so early detection and treatment of DME is of great significance for the treatment of diabetes. Based on transfer learning, an automatic classification method is proposed to distinguish DME images from normal images in optical coherence tomography (OCT) retinal fundus images. Features of the DME are automatically identified and extracted by the pre-trained convolutional neural network (CNN), which only involves fine-tuning the VGGNet-16 network without any user intervention. An accuracy of 97.9% and a sensitivity of 98.0% are acquired with the OCT images in the Duke data set from experimental results. The proposed method, a core part of an automated diagnosis system of the DME, revealed the ability of fine-tuning models to train non-medical images, allowing them can be classified with limited training data. Moreover, it can be developed to assist early diagnosis of the disease, effectively delaying (or avoiding) the progression of the disease, consequently.

A Multi-Task Deep-Learning System to Classify Diabetic Macular Edema for Different Optical Coherence Tomography Devices: A Multi-Centre Analysis

Background: Diabetic macular edema (DME) is the primary cause of irreversible vision loss among individuals with diabetes mellitus (DM). We developed, validated, and tested a deep-learning (DL) system for classifying DME using images from three common commercially available optical coherence tomography (OCT) devices. Methods: We trained and validated two versions of a multi-task network to classify DME (centre-involved DME [CI-DME], non-CI-DME, or absence of DME) using three-dimensional (3D) volume-scans and two-dimensional (2D) B-scans respectively. A total of 73,746 OCT images were used for training and primary validation. External testing was performed using 26,981 images across seven independent datasets from Singapore, Hong Kong, the US, China, and Australia. Findings: In classifying the presence or absence of DME, the DL system achieved area under the receiver operating characteristic curves (AUROCs) of 0.937 (95% CI 0.920–0.954), 0.958 (0.930–0.977), and 0.965 (0.948–0.977) for primary datasets obtained from Cirrus, Spectralis, and Triton OCTs respectively, in addition to AUROCs greater than 0.906 for the external datasets. For the further classification of the CI-DME and non-CI-DME subgroups, the AUROCs were 0.968 (0.940–0.995), 0.951 (0.898–0.982), and 0.975 (0.947–0.991) for the primary datasets and greater than 0.894 for the external datasets. Interpretation: We demonstrated excellent performance with a DL system for the automated classification of DME, highlighting its potential as a promising second-line screening tool for patients with DM, which will create a more effective triaging mechanism to tertiary eye clinics. Funding: Research Grants Council General Research Fund, Hong Kong; Research to Prevent Blindness; and National Institutes of Health Grant. Conflict of Interest: We report no potential conflicts of interest relevant to this article. Ethical Approval: The current study presented here was conducted in accordance with the 1964 Declaration of Helsinki and was approved by local research ethics committees. Because the study is a retrospective analysis of fully anonymized OCT images, the ethics committees waived the requirements for informed consent.

Role of Inflammation in Classification of Diabetic Macular Edema by Optical Coherence Tomography.

Diabetic macular edema (DME) is the abnormal accumulation of fluid in the subretinal or intraretinal spaces in the macula in patients with diabetic retinopathy and leads to severely impaired central vision. Technical developments in retinal imaging systems have led to many advances in the study of DME. In particular, optical coherence tomography (OCT) can provide longitudinal and microstructural analysis of the macula. A comprehensive review was provided regarding the role of inflammation using OCT-based classification of DME and current and ongoing therapeutic approaches. In this review, we first describe the pathogenesis of DME, then discuss the classification of DME based on OCT findings and the association of different types of DME with inflammation, and finally describe current and ongoing therapeutic approaches using OCT-based classification of DME. Inflammation has an important role in the pathogenesis of DME, but its role appears to differ among the DME phenotypes, as determined by OCT. It is important to determine how the different DME subtypes respond to intravitreal injections of steroids, antivascular endothelial growth factor agents, and other drugs to improve prognosis and responsiveness to treatment.

Multi-scale deep feature fusion for automated classification of macular pathologies from OCT images

Identification of the macular pathologies at an early stage can prevent vision loss. Similarity in the pathological manifestations of common macular disorders like age related macular degeneration (AMD) and diabetic macular edema (DME) can make manual screening fallible. There is a growing interest among researchers for reliable automated detection of macular pathologies using computer methods. Therefore, in this paper we present a novel method for classification of DME and two stages of AMD namely the drusens (early stage) and the choroidal neo vascularization (CNV) (late stage) from healthy optical coherence tomography (OCT) images. The proposed method introduces a multi-scale deep feature fusion (MDFF) based classification approach using convolutional neural network (CNN) for reliable diagnosis. The MDFF captures the inter-scale variations in images to introduce discriminative and complementary information to the classifier. The proposed method is evaluated on an OCT dataset containing 84,484 images with different class distributions. The imbalance in the dataset is handled by introducing the cost sensitive loss function during the learning of the classifier. The proposed method achieves an average sensitivity, specificity and accuracy of 99.6%, 99.87% and 99.6% on the test set. The promising classification results make the proposed method highly suitable for preliminary automated diagnosis of macular pathologies in health care centres and eye clinics.