Coarse-to-fine classification for diabetic retinopathy grading using convolutional neural network

Recognition of diabetic retinopathy and macular edema using deep learning

Diabetic retinopathy (DR) and diabetic macular edema (DME) are both serious eye conditions associated with diabetes and if left untreated, and they can lead to permanent blindness. Traditional methods for screening these conditions rely on manual image analysis by experts, which can be time-consuming and costly due to the scarcity of such experts. To overcome the aforementioned challenges, we present the Modified CornerNet approach with DenseNet-100. This system aims to localize and classify lesions associated with DR and DME. To train our model, we first generate annotations for input samples. These annotations likely include information about the location and type of lesions within the retinal images. DenseNet-100 is a deep CNN used for feature extraction, and CornerNet is a one-stage object detection model. CornerNet is known for its ability to accurately localize small objects, which makes it suitable for detecting lesions in retinal images. We assessed our technique on two challenging datasets, EyePACS and IDRiD. These datasets contain a diverse range of retinal images, which is important to estimate the performance of our model. Further, the proposed model is also tested in the cross-corpus scenario on two challenging datasets named APTOS-2019 and Diaretdb1 to assess the generalizability of our system. According to the accomplished analysis, our method outperformed the latest approaches in terms of both qualitative and quantitative results. The ability to effectively localize small abnormalities and handle over-fitted challenges is highlighted as a key strength of the suggested framework which can assist the practitioners in the timely recognition of such eye ailments.

HCGAN: hierarchical contrast generative adversarial network for unpaired sketch face synthesis

Transforming optical facial images into sketches while preserving realism and facial features poses a significant challenge. The current methods that rely on paired training data are costly and resource-intensive. Furthermore, they often fail to capture the intricate features of faces, resulting in substandard sketch generation. To address these challenges, we propose the novel hierarchical contrast generative adversarial network (HCGAN). Firstly, HCGAN consists of a global sketch synthesis module that generates sketches with well-defined global features and a local sketch refinement module that enhances the ability to extract features in critical areas. Secondly, we introduce local refinement loss based on the local sketch refinement module, refining sketches at a granular level. Finally, we propose an association strategy called "warmup-epoch" and local consistency loss between the two modules to ensure HCGAN is effectively optimized. Evaluations of the CUFS and SKSF-A datasets demonstrate that our method produces high-quality sketches and outperforms existing state-of-the-art methods in terms of fidelity and realism. Compared to the current state-of-the-art methods, HCGAN reduces FID by 12.6941, 4.9124, and 9.0316 on three datasets of CUFS, respectively, and by 7.4679 on the SKSF-A dataset. Additionally, it obtained optimal scores for content fidelity (CF), global effects (GE), and local patterns (LP). The proposed HCGAN model provides a promising solution for realistic sketch synthesis under unpaired data training.

Localization and grading of NPDR lesions using ResNet-18-YOLOv8 model and informative features selection for DR classification based on transfer learning

Complications in diabetes lead to diabetic retinopathy (DR) hence affecting the vision. Computerized methods performed a significant role in DR detection at the initial phase to cure vision loss. Therefore, a method is proposed in this study that consists of three models for localization, segmentation, and classification. A novel technique is designed with the combination of pre-trained ResNet-18 and YOLOv8 models based on the selection of optimum layers for the localization of DR lesions. The localized images are passed to the designed semantic segmentation model on selected layers and trained on optimized learning hyperparameters. The segmentation model performance is evaluated on the Grand-challenge IDRID segmentation dataset. The achieved results are computed in terms of mean IoU 0.95,0.94, 0.96, 0.94, and 0.95 on OD, SoftExs, HardExs, HAE, and MAs respectively. Another classification model is developed in which deep features are derived from the pre-trained Efficientnet-b0 model and optimized using a Genetic algorithm (GA) based on the selected parameters for grading of NPDR lesions. The proposed model achieved greater than 98 % accuracy which is superior to previous methods.

Multi-scale multi-attention network for diabetic retinopathy grading

Objective.Diabetic retinopathy (DR) grading plays an important role in clinical diagnosis. However, automatic grading of DR is challenging due to the presence of intra-class variation and small lesions. On the one hand, deep features learned by convolutional neural networks often lose valid information about these small lesions. On the other hand, the great variability of lesion features, including differences in type and quantity, can exhibit considerable divergence even among fundus images of the same grade. To address these issues, we propose a novel multi-scale multi-attention network (MMNet).Approach.Firstly, to focus on different lesion features of fundus images, we propose a lesion attention module, which aims to encode multiple different lesion attention feature maps by combining channel attention and spatial attention, thus extracting global feature information and preserving diverse lesion features. Secondly, we propose a multi-scale feature fusion module to learn more feature information for small lesion regions, which combines complementary relationships between different convolutional layers to capture more detailed feature information. Furthermore, we introduce a Cross-layer Consistency Constraint Loss to overcome semantic differences between multi-scale features.Main results.The proposed MMNet obtains a high accuracy of 86.4% and a high kappa score of 88.4% for multi-class DR grading tasks on the EyePACS dataset, while 98.6% AUC, 95.3% accuracy, 92.7% recall, 95.0% precision, and 93.3% F1-score for referral and non-referral classification on the Messidor-1 dataset. Extensive experiments on two challenging benchmarks demonstrate that our MMNet achieves significant improvements and outperforms other state-of-the-art DR grading methods.Significance.MMNet has improved the diagnostic efficiency and accuracy of diabetes retinopathy and promoted the application of computer-aided medical diagnosis in DR screening.

Study of Foveal Avascular Zone Growth in Individuals With Mild Diabetic Retinopathy by Optical Coherence Tomography

Purpose

The purpose of this study was to investigate the association between foveal vessels and retinal thickness in individuals with diabetic retinopathy (DR) and control subjects, and to reveal foveal avascular zone (FAZ) growth in early individuals with DR.

Methods

The regions with a thickness less than 60 µm were marked from the intima thickness maps and named FAZThic. The avascular zones extracted from the deep vascular plexus were designated as FAZAngi. The boundary of the two FAZ forms a ring region, which we called FAZRing. The FAZ growth rate was defined as the ratio of the FAZRing area to the FAZThic area. Thirty healthy controls and 30 individuals with mild nonproliferative DR were recruited for this study.

Results

The FAZThic area in individuals with mild DR and control subjects showed similar distribution. The FAZAngi area in individuals with mild DR are higher than that in control subjects on the whole, but there was no significant difference (P > 0.05). The FAZRing area in individuals with mild DR was significantly higher than that in control subjects (P < 0.001). However, there is still a small amount of overlap data between the two groups. For the FAZ growth rate, the individuals with mild DR were also significantly larger than the control subjects (P < 0.001). But there were no overlapping data between the two groups.

Conclusions

The growth of FAZ in individuals with mild DR can be inferred by comparing FAZAngi with FAZThic. This method minimizes the impact of individual variations and helps researchers to understand the progression mechanism of DR more deeply.

Hybrid Methods for Fundus Image Analysis for Diagnosis of Diabetic Retinopathy Development Stages Based on Fusion Features

Diabetic retinopathy (DR) is a complication of diabetes that damages the delicate blood vessels of the retina and leads to blindness. Ophthalmologists rely on diagnosing the retina by imaging the fundus. The process takes a long time and needs skilled doctors to diagnose and determine the stage of DR. Therefore, automatic techniques using artificial intelligence play an important role in analyzing fundus images for the detection of the stages of DR development. However, diagnosis using artificial intelligence techniques is a difficult task and passes through many stages, and the extraction of representative features is important in reaching satisfactory results. Convolutional Neural Network (CNN) models play an important and distinct role in extracting features with high accuracy. In this study, fundus images were used for the detection of the developmental stages of DR by two proposed methods, each with two systems. The first proposed method uses GoogLeNet with SVM and ResNet-18 with SVM. The second method uses Feed-Forward Neural Networks (FFNN) based on the hybrid features extracted by first using GoogLeNet, Fuzzy color histogram (FCH), Gray Level Co-occurrence Matrix (GLCM), and Local Binary Pattern (LBP); followed by ResNet-18, FCH, GLCM and LBP. All the proposed methods obtained superior results. The FFNN network with hybrid features of ResNet-18, FCH, GLCM, and LBP obtained 99.7% accuracy, 99.6% precision, 99.6% sensitivity, 100% specificity, and 99.86% AUC.

Fine-grained attention & knowledge-based collaborative network for diabetic retinopathy grading

Accurate diabetic retinopathy (DR) grading is crucial for making the proper treatment plan to reduce the damage caused by vision loss. This task is challenging due to the fact that the DR related lesions are often small and subtle in visual differences and intra-class variations. Moreover, relationships between the lesions and the DR levels are complicated. Although many deep learning (DL) DR grading systems have been developed with some success, there are still rooms for grading accuracy improvement. A common issue is that not much medical knowledge was used in these DL DR grading systems. As a result, the grading results are not properly interpreted by ophthalmologists, thus hinder the potential for practical applications. This paper proposes a novel fine-grained attention & knowledge-based collaborative network (FA+KC-Net) to address this concern. The fine-grained attention network dynamically divides the extracted feature maps into smaller patches and effectively captures small image features that are meaningful in the sense of its training from large amount of retinopathy fundus images. The knowledge-based collaborative network extracts a-priori medical knowledge features, i.e., lesions such as the microaneurysms (MAs), soft exudates (SEs), hard exudates (EXs), and hemorrhages (HEs). Finally, decision rules are developed to fuse the DR grading results from the fine-grained network and the knowledge-based collaborative network to make the final grading. Extensive experiments are carried out on four widely-used datasets, the DDR, Messidor, APTOS, and EyePACS to evaluate the efficacy of our method and compare with other state-of-the-art (SOTA) DL models. Simulation results show that proposed FA+KC-Net is accurate and stable, achieves the best performances on the DDR, Messidor, and APTOS datasets.

A Computer-Aided Diagnostic System to Identify Diabetic Retinopathy, Utilizing a Modified Compact Convolutional Transformer and Low-Resolution Images to Reduce Computation Time

Diabetic retinopathy (DR) is the foremost cause of blindness in people with diabetes worldwide, and early diagnosis is essential for effective treatment. Unfortunately, the present DR screening method requires the skill of ophthalmologists and is time-consuming. In this study, we present an automated system for DR severity classification employing the fine-tuned Compact Convolutional Transformer (CCT) model to overcome these issues. We assembled five datasets to generate a more extensive dataset containing 53,185 raw images. Various image pre-processing techniques and 12 types of augmentation procedures were applied to improve image quality and create a massive dataset. A new DR-CCTNet model is proposed. It is a modification of the original CCT model to address training time concerns and work with a large amount of data. Our proposed model delivers excellent accuracy even with low-pixel images and still has strong performance with fewer images, indicating that the model is robust. We compare our model's performance with transfer learning models such as VGG19, VGG16, MobileNetV2, and ResNet50. The test accuracy of the VGG19, ResNet50, VGG16, and MobileNetV2 were, respectively, 72.88%, 76.67%, 73.22%, and 71.98%. Our proposed DR-CCTNet model to classify DR outperformed all of these with a 90.17% test accuracy. This approach provides a novel and efficient method for the detection of DR, which may lower the burden on ophthalmologists and expedite treatment for patients.

A convolutional attention mapping deep neural network for classification and localization of cardiomegaly on chest X-rays

Building a reliable and precise model for disease classification and identifying abnormal sites can provide physicians assistance in their decision-making process. Deep learning based image analysis is a promising technique for enriching the decision making process, and accordingly strengthening patient care. This work presents a convolutional attention mapping deep learning model, Cardio-XAttentionNet, to classify and localize cardiomegaly effectively. We revisit the global average pooling (GAP) system and add a weighting term to develop a light and effective Attention Mapping Mechanism (AMM). The model enables the classification of cardiomegaly from chest X-rays through image-level classification and pixel-level localization only from image-level labels. We leverage some of the advanced ConvNet architectures as a backbone-model of the proposed attention mapping network to build Cardio-XAttentionNet. The proposed model is trained on ChestX-Ray14, which is a publicly accessible chest X-ray dataset. The best single model achieves an overall precision, recall, F-1 measure and area under curve (AUC) scores of 0.87, 0.85, 0.86 and 0.89, respectively, for the classification of the cardiomegaly. The results also demonstrate that the Cardio-XAttentionNet model well captures the cardiomegaly class information at image-level as well as localization at pixel-level on chest x-rays. A comparative analysis between the proposed AMM and existing GAP based models shows that the proposed model achieves a state-of-the-art performance on this dataset for cardiomegaly detection using a single model.

Computational Intelligence-Based Disease Severity Identification: A Review of Multidisciplinary Domains

Disease severity identification using computational intelligence-based approaches is gaining popularity nowadays. Artificial intelligence and deep-learning-assisted approaches are proving to be significant in the rapid and accurate diagnosis of several diseases. In addition to disease identification, these approaches have the potential to identify the severity of a disease. The problem of disease severity identification can be considered multi-class classification, where the class labels are the severity levels of the disease. Plenty of computational intelligence-based solutions have been presented by researchers for severity identification. This paper presents a comprehensive review of recent approaches for identifying disease severity levels using computational intelligence-based approaches. We followed the PRISMA guidelines and compiled several works related to the severity identification of multidisciplinary diseases of the last decade from well-known publishers, such as MDPI, Springer, IEEE, Elsevier, etc. This article is devoted toward the severity identification of two main diseases, viz. Parkinson's Disease and Diabetic Retinopathy. However, severity identification of a few other diseases, such as COVID-19, autonomic nervous system dysfunction, tuberculosis, sepsis, sleep apnea, psychosis, traumatic brain injury, breast cancer, knee osteoarthritis, and Alzheimer's disease, was also briefly covered. Each work has been carefully examined against its methodology, dataset used, and the type of disease on several performance metrics, accuracy, specificity, etc. In addition to this, we also presented a few public repositories that can be utilized to conduct research on disease severity identification. We hope that this review not only acts as a compendium but also provides insights to the researchers working on disease severity identification using computational intelligence-based approaches.

Developments in the detection of diabetic retinopathy: a state-of-the-art review of computer-aided diagnosis and machine learning methods

The exponential increase in the number of diabetics around the world has led to an equally large increase in the number of diabetic retinopathy (DR) cases which is one of the major complications caused by diabetes. Left unattended, DR worsens the vision and would lead to partial or complete blindness. As the number of diabetics continue to increase exponentially in the coming years, the number of qualified ophthalmologists need to increase in tandem in order to meet the demand for screening of the growing number of diabetic patients. This makes it pertinent to develop ways to automate the detection process of DR. A computer aided diagnosis system has the potential to significantly reduce the burden currently placed on the ophthalmologists. Hence, this review paper is presented with the aim of summarizing, classifying, and analyzing all the recent development on automated DR detection using fundus images from 2015 up to this date. Such work offers an unprecedentedly thorough review of all the recent works on DR, which will potentially increase the understanding of all the recent studies on automated DR detection, particularly on those that deploys machine learning algorithms. Firstly, in this paper, a comprehensive state-of-the-art review of the methods that have been introduced in the detection of DR is presented, with a focus on machine learning models such as convolutional neural networks (CNN) and artificial neural networks (ANN) and various hybrid models. Each AI will then be classified according to its type (e.g. CNN, ANN, SVM), its specific task(s) in performing DR detection. In particular, the models that deploy CNN will be further analyzed and classified according to some important properties of the respective CNN architectures of each model. A total of 150 research articles related to the aforementioned areas that were published in the recent 5 years have been utilized in this review to provide a comprehensive overview of the latest developments in the detection of DR.

Supplementary Information

The online version contains supplementary material available at 10.1007/s10462-022-10185-6.

Deep attentive convolutional neural network for automatic grading of imbalanced diabetic retinopathy in retinal fundus images

Automated fine-grained diabetic retinopathy (DR) grading was of great significance for assisting ophthalmologists in monitoring DR and designing tailored treatments for patients. Nevertheless, it is a challenging task as a result of high intra-class variations, high inter-class similarities, small lesions, and imbalanced data distributions. The pivotal factor for the success in fine-grained DR grading is to discern more subtle associated lesion features, such as microaneurysms (MA), Hemorrhages (HM), soft exudates (SE), and hard exudates (HE). In this paper, we constructed a simple yet effective deep attentive convolutional neural network (DACNN) for DR grading and lesion discovery with only image-wise supervision. Designed as a top-down architecture, our model incorporated stochastic atrous spatial pyramid pooling (sASPP), global attention mechanism (GAM), category attention mechanism (CAM), and learnable connected module (LCM) to better extract lesion-related features and maximize the DR grading performance. To be concrete, we devised sASPP combining randomness with atrous spatial pyramid pooling (ASPP) to accommodate the various scales of the lesions and struggle against the co-adaptation of multiple atrous convolutions. Then, GAM was introduced to extract class-agnostic global attention feature details, whilst CAM was explored for seeking class-specific distinctive region-level lesion feature information and regarding each DR severity grade in an equal way, which tackled the problem of imbalance DR data distributions. Further, the LCM was designed to automatically and adaptively search the optimal connections among layers for better extracting detailed small lesion feature representations. The proposed approach obtained high accuracy of 88.0% and kappa score of 88.6% for multi-class DR grading task on the EyePACS dataset, respectively, while 98.5% AUC, 93.8% accuracy, 87.9% kappa, 90.7% recall, 94.6% precision, and 92.6% F1-score for referral and non-referral classification on the Messidor dataset. Extensive experimental results on three challenging benchmarks demonstrated that the proposed approach achieved competitive performance in DR grading and lesion discovery using retinal fundus images compared with existing cutting-edge methods, and had good generalization capacity for unseen DR datasets. These promising results highlighted its potential as an efficient and reliable tool to assist ophthalmologists in large-scale DR screening.

Gray wolf optimization-extreme learning machine approach for diabetic retinopathy detection

Many works have employed Machine Learning (ML) techniques in the detection of Diabetic Retinopathy (DR), a disease that affects the human eye. However, the accuracy of most DR detection methods still need improvement. Gray Wolf Optimization-Extreme Learning Machine (GWO-ELM) is one of the most popular ML algorithms, and can be considered as an accurate algorithm in the process of classification, but has not been used in solving DR detection. Therefore, this work aims to apply the GWO-ELM classifier and employ one of the most popular features extractions, Histogram of Oriented Gradients-Principal Component Analysis (HOG-PCA), to increase the accuracy of DR detection system. Although the HOG-PCA has been tested in many image processing domains including medical domains, it has not yet been tested in DR. The GWO-ELM can prevent overfitting, solve multi and binary classifications problems, and it performs like a kernel-based Support Vector Machine with a Neural Network structure, whilst the HOG-PCA has the ability to extract the most relevant features with low dimensionality. Therefore, the combination of the GWO-ELM classifier and HOG-PCA features might produce an effective technique for DR classification and features extraction. The proposed GWO-ELM is evaluated based on two different datasets, namely APTOS-2019 and Indian Diabetic Retinopathy Image Dataset (IDRiD), in both binary and multi-class classification. The experiment results have shown an excellent performance of the proposed GWO-ELM model where it achieved an accuracy of 96.21% for multi-class and 99.47% for binary using APTOS-2019 dataset as well as 96.15% for multi-class and 99.04% for binary using IDRiD dataset. This demonstrates that the combination of the GWO-ELM and HOG-PCA is an effective classifier for detecting DR and might be applicable in solving other image data types.

Diabetic Retinopathy Detection from Fundus Images of the Eye Using Hybrid Deep Learning Features

Diabetic Retinopathy (DR) is a medical condition present in patients suffering from long-term diabetes. If a diagnosis is not carried out at an early stage, it can lead to vision impairment. High blood sugar in diabetic patients is the main source of DR. This affects the blood vessels within the retina. Manual detection of DR is a difficult task since it can affect the retina, causing structural changes such as Microaneurysms (MAs), Exudates (EXs), Hemorrhages (HMs), and extra blood vessel growth. In this work, a hybrid technique for the detection and classification of Diabetic Retinopathy in fundus images of the eye is proposed. Transfer learning (TL) is used on pre-trained Convolutional Neural Network (CNN) models to extract features that are combined to generate a hybrid feature vector. This feature vector is passed on to various classifiers for binary and multiclass classification of fundus images. System performance is measured using various metrics and results are compared with recent approaches for DR detection. The proposed method provides significant performance improvement in DR detection for fundus images. For binary classification, the proposed modified method achieved the highest accuracy of 97.8% and 89.29% for multiclass classification.

Multimodal image encoding pre-training for diabetic retinopathy grading

Diabetic retinopathy is an increasingly prevalent eye disorder that can lead to severe vision impairment. The severity grading of the disease using retinal images is key to provide an adequate treatment. However, in order to learn the diverse patterns and complex relations that are required for the grading, deep neural networks require very large annotated datasets that are not always available. This has been typically addressed by reusing networks that were pre-trained for natural image classification, hence relying on additional annotated data from a different domain. In contrast, we propose a novel pre-training approach that takes advantage of unlabeled multimodal visual data commonly available in ophthalmology. The use of multimodal visual data for pre-training purposes has been previously explored by training a network in the prediction of one image modality from another. However, that approach does not ensure a broad understanding of the retinal images, given that the network may exclusively focus on the similarities between modalities while ignoring the differences. Thus, we propose a novel self-supervised pre-training that explicitly teaches the networks to learn the common characteristics between modalities as well as the characteristics that are exclusive to the input modality. This provides a complete comprehension of the input domain and facilitates the training of downstream tasks that require a broad understanding of the retinal images, such as the grading of diabetic retinopathy. To validate and analyze the proposed approach, we performed an exhaustive experimentation on different public datasets. The transfer learning performance for the grading of diabetic retinopathy is evaluated under different settings while also comparing against previous state-of-the-art pre-training approaches. Additionally, a comparison against relevant state-of-the-art works for the detection and grading of diabetic retinopathy is also provided. The results show a satisfactory performance of the proposed approach, which outperforms previous pre-training alternatives in the grading of diabetic retinopathy.

Lesion-attention pyramid network for diabetic retinopathy grading

As one of the most common diabetic complications, diabetic retinopathy (DR) can cause retinal damage, vision loss and even blindness. Automated DR grading technology has important clinical significance, which can help ophthalmologists achieve rapid and early diagnosis. With the popularity of deep learning, DR grading based on the convolutional neural networks (CNNs) has become the mainstream method. Unfortunately, although the CNN-based method can achieve satisfactory diagnostic accuracy, it lacks significant clinical information. In this paper, a lesion-attention pyramid network (LAPN) is presented. The pyramid network integrates the subnetworks with different resolutions to get multi-scale features. In order to take the lesion regions in the high-resolution image as the diagnostic evidence, the low-resolution network calculates the lesion activation map (using the weakly-supervised localization method) and guides the high-resolution network to concentrate on the lesion regions. Furthermore, a lesion attention module (LAM) is designed to capture the complementary relationship between the high-resolution features and the low-resolution features, and to fuse the lesion activation map. Experiment results show that the proposed scheme outperforms other existing approaches, and the proposed method can provide lesion activation map with lesion consistency as an additional evidence for clinical diagnosis.

Optimized hybrid machine learning approach for smartphone based diabetic retinopathy detection

Diabetic Retinopathy (DR) is defined as the Diabetes Mellitus difficulty that harms the blood vessels in the retina. It is also known as a silent disease and cause mild vision issues or no symptoms. In order to enhance the chances of effective treatment, yearly eye tests are vital for premature discovery. Hence, it uses fundus cameras for capturing retinal images, but due to its size and cost, it is a troublesome for extensive screening. Therefore, the smartphones are utilized for scheming low-power, small-sized, and reasonable retinal imaging schemes to activate automated DR detection and DR screening. In this article, the new DIY (do it yourself) smartphone enabled camera is used for smartphone based DR detection. Initially, the preprocessing like green channel transformation and CLAHE (Contrast Limited Adaptive Histogram Equalization) are performed. Further, the segmentation process starts with optic disc segmentation by WT (watershed transform) and abnormality segmentation (Exudates, microaneurysms, haemorrhages, and IRMA) by Triplet half band filter bank (THFB). Then the different features are extracted by Haralick and ADTCWT (Anisotropic Dual Tree Complex Wavelet Transform) methods. Using life choice-based optimizer (LCBO) algorithm, the optimal features are chosen from the mined features. Then the selected features are applied to the optimized hybrid ML (machine learning) classifier with the combination of NN and DCNN (Deep Convolutional Neural Network) in which the SSD (Social Ski-Driver) is utilized for the best weight values of hybrid classifier to categorize the severity level as mild DR, severe DR, normal, moderate DR, and Proliferative DR. The proposed work is simulated in python environment and to test the efficiency of the proposed scheme the datasets like APTOS-2019-Blindness-Detection, and EyePacs are used. The model has been evaluated using different performance metrics. The simulation results verified that the suggested scheme is provides well accuracy for each dataset than other current approaches.

Review on diabetic retinopathy with deep learning methods

Purpose: The purpose of our review paper is to examine many existing works of literature presenting the different methods utilized for diabetic retinopathy (DR) recognition employing deep learning (DL) and machine learning (ML) techniques, and also to address the difficulties faced in various datasets used by DR. Approach: DR is a progressive illness and may become a reason for vision loss. Early identification of DR lesions is, therefore, helpful and prevents damage to the retina. However, it is a complex job in view of the fact that it is symptomless earlier, and also ophthalmologists have been needed in traditional approaches. Recently, automated identification of DR-based studies has been stated based on image processing, ML, and DL. We analyze the recent literature and provide a comparative study that also includes the limitations of the literature and future work directions. Results: A relative analysis among the databases used, performance metrics employed, and ML and DL techniques adopted recently in DR detection based on various DR features is presented. Conclusion: Our review paper discusses the methods employed in DR detection along with the technical and clinical challenges that are encountered, which is missing in existing reviews, as well as future scopes to assist researchers in the field of retinal imaging.

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.

Diabetic retinopathy detection through convolutional neural networks with synaptic metaplasticity

BACKGROUND AND OBJECTIVES

Diabetic retinopathy is a type of diabetes that causes vascular changes that can lead to blindness. The ravages of this disease cannot be reversed, so early detection is essential. This work presents an automated method for early detection of this disease using fundus colored images.

METHODS

A bio-inspired approach is proposed on synaptic metaplasticity in convolutional neural networks. This biological phenomenon is known to directly interfere in both learning and memory by reinforcing less common occurrences during the learning process. Synaptic metaplasticity has been included in the backpropagation stage of a convolution operation for every convolutional layer.

RESULTS

The proposed method has been evaluated by using a public small diabetic retinopathy dataset from Kaggle with four award-winning convolutional neural network architectures. Results show that convolutional neural network architectures including synaptic metaplasticity improve both learning rate and accuracy. Furthermore, obtained results outperform other methods in current literature, even using smaller datasets for training. Best results have been obtained for the InceptionV3 architecture with synaptic metaplasticity with a 95.56% accuracy, 94.24% F1-score, 98.9% precision and 90% recall, using 3662 images for training.

CONCLUSIONS

Convolutional neural networks with synaptic metaplasticity are suitable for early detection of diabetic retinopathy due to their fast convergence rate, training simplicity and high performance.

Probabilistic domain-knowledge modeling of disorder pathogenesis for dynamics forecasting of acute onset

Disease pathogenesis, a type of domain knowledge about biological mechanisms leading to diseases, has not been adequately encoded in machine-learning-based medical diagnostic models because of the inter-patient variabilities and complex dependencies of the underlying pathogenetic mechanisms. We propose 1) a novel pathogenesis probabilistic graphical model (PPGM) to quantify the dynamics underpinning patient-specific data and pathogenetic domain knowledge, 2) a Bayesian-based inference paradigm to answer the medical queries and forecast acute onsets. The PPGM model consists of two components: a Bayesian network of patient attributes and a temporal model of pathogenetic mechanisms. The model structure was reconstructed from expert knowledge elicitation, and its parameters were estimated using Variational Expectation-Maximization algorithms. We benchmarked our model with two well-established hidden Markov models (HMMs) - Input-output HMM (IO-HMM) and Switching Auto-Regressive HMM (SAR-HMM) - to evaluate the computational costs, forecasting performance, and execution time. Two case studies on Obstructive Sleep Apnea (OSA) and Paroxysmal Atrial Fibrillation (PAF) were used to validate the model. While the performance of the parameter learning step was equivalent to those of IO-HMM and SAR-HMM models, our model forecasting ability was outperforming those two models. The merits of the PPGM model are its representation capability to capture the dynamics of pathogenesis and perform medical inferences and its interpretability for physicians. The model has been used to perform medical queries and forecast the acute onset of OSA and PAF. Additional applications of the model include prognostic healthcare and preventive personalized treatments.

Discriminative Learning Approach Based on Flexible Mixture Model for Medical Data Categorization and Recognition

In this paper, we propose a novel hybrid discriminative learning approach based on shifted-scaled Dirichlet mixture model (SSDMM) and Support Vector Machines (SVMs) to address some challenging problems of medical data categorization and recognition. The main goal is to capture accurately the intrinsic nature of biomedical images by considering the desirable properties of both generative and discriminative models. To achieve this objective, we propose to derive new data-based SVM kernels generated from the developed mixture model SSDMM. The proposed approach includes the following steps: the extraction of robust local descriptors, the learning of the developed mixture model via the expectation-maximization (EM) algorithm, and finally the building of three SVM kernels for data categorization and classification. The potential of the implemented framework is illustrated through two challenging problems that concern the categorization of retinal images into normal or diabetic cases and the recognition of lung diseases in chest X-rays (CXR) images. The obtained results demonstrate the merits of our hybrid approach as compared to other methods.

Detecting Diabetic Retinopathy Using Embedded Computer Vision

Diabetic retinopathy is one of the leading causes of vision loss in the United States and other countries around the world. People who have diabetic retinopathy may not have symptoms until the condition becomes severe, which may eventually lead to vision loss. Thus, the medically underserved populations are at an increased risk of diabetic retinopathy-related blindness. In this paper, we present development efforts on an embedded vision algorithm that can classify healthy versus diabetic retinopathic images. Convolution neural network and a k-fold cross-validation process were used. We used 88,000 labeled high-resolution retina images obtained from the publicly available Kaggle/EyePacs database. The trained algorithm was able to detect diabetic retinopathy with up to 76% accuracy. Although the accuracy needs to be further improved, the presented results represent a significant step forward in the direction of detecting diabetic retinopathy using embedded computer vision. This technology has the potential of being able to detect diabetic retinopathy without having to see an eye specialist in remote and medically underserved locations, which can have significant implications in reducing diabetes-related vision losses.