A lightweight multi-deep learning framework for accurate diabetic retinopathy detection and multi-level severity identification

Accurate and timely detection of diabetic retinopathy (DR) is crucial for managing its progression and improving patient outcomes. However, developing algorithms to analyze complex fundus images continues to be a major challenge. This work presents a lightweight deep-learning network developed for DR detection. The proposed framework consists of two stages. In the first step, the developed model is used to assess the presence of DR [i.e., healthy (no DR) or diseased (DR)]. The next step involves the use of transfer learning for further subclassification of DR severity (i.e., mild, moderate, severe DR, and proliferative DR). The designed model is reused for transfer learning, as correlated images facilitate further classification of DR severity. The online dataset is used to validate the proposed framework, and results show that the proposed model is lightweight and has comparatively low learnable parameters compared to others. The proposed two-stage framework enhances the classification performance, achieving a 99.06% classification rate for DR detection and an accuracy of 90.75% for DR severity identification for APTOS 2019 dataset.

SwAV-driven diagnostics: new perspectives on grading diabetic retinopathy from retinal photography

Diabetic Retinopathy (DR) is a serious eye condition that occurs due to high blood sugar levels in patients with Diabetes Mellitus. If left untreated, DR can potentially result in blindness. Using automated neural network-based methods to grade DR shows potential for early detection. However, the uneven and non-quadrilateral forms of DR lesions provide difficulties for traditional Convolutional Neural Network (CNN)-based architectures. To address this challenge and explore a novel algorithm architecture, this work delves into the usage of contrasting cluster assignments in retinal fundus images with the Swapping Assignments between multiple Views (SwAV) algorithm for DR grading. An ablation study was made where SwAV outperformed other CNN and Transformer-based models, independently and in ensemble configurations with an accuracy of 87.00% despite having fewer parameters and layers. The proposed approach outperforms existing state-of-the-art models regarding classification metrics, complexity, and prediction time. The findings offer great potential for medical practitioners, allowing for more accurate diagnosis of DR and earlier treatments to avoid visual loss.

Spatial attention U-Net model with Harris hawks optimization for retinal blood vessel and optic disc segmentation in fundus images

BACKGROUND

The state of the human eye's blood vessels is a crucial aspect in the diagnosis of ophthalmological illnesses. For many computer-aided diagnostic systems, precise retinal vessel segmentation is an essential job. However, it remains a difficult task due to the intricate vascular system of the eye. Although many different vascular segmentation techniques have already been presented, additional study is still required to address the problem of inadequate segmentation of thin and tiny vessels.

METHODS

In this work, we introduce the Spatial Attention U-Net (SAU-Net) model with harris hawks' optimization (HHO), a lightweight network that can be applied as a data augmentation technique to improve the efficiency of the existing annotated samples without the need of thousands of training instances for Retinal Blood Vessel and Optic Disc Segmentation. The SAU-Net-HHO implementation uses a spatially inferred attention map multiplied by the input feature map for adaptive feature enhancement. U-Net convolutional blocks have been replaced with structured dropout blocks in the proposed network to prevent overfitting. Data from both vascular extraction (DRIVE) and structured analysis of the retina (STARE) are used to evaluate SAU-Net-HHO performance.

RESULTS

The results show that the proposed SAU-Net-HHO performs well on both datasets. Analysing the obtained results, an average of 98.5% accuracy and Specificity 96.7% was achieved for DRIVE dataset and 97.8% accuracy and specificity 94.5% for STARE dataset. The proposed method yields numerical results with average values that are on par with those of state-of-the-art methods.

CONCLUSION

Visual inspection has revealed that the suggested method can segment thin and tiny vessels with greater accuracy than previous methods. It also demonstrates its potential for real-life clinical application.

A graph convolutional network with dynamic weight fusion of multi-scale local features for diabetic retinopathy grading

Diabetic retinopathy (DR) is a serious ocular complication that can pose a serious risk to a patient's vision and overall health. Currently, the automatic grading of DR is mainly using deep learning techniques. However, the lesion information in DR images is complex, variable in shape and size, and randomly distributed in the images, which leads to some shortcomings of the current research methods, i.e., it is difficult to effectively extract the information of these various features, and it is difficult to establish the connection between the lesion information in different regions. To address these shortcomings, we design a multi-scale dynamic fusion (MSDF) module and combine it with graph convolution operations to propose a multi-scale dynamic graph convolutional network (MDGNet) in this paper. MDGNet firstly uses convolution kernels with different sizes to extract features with different shapes and sizes in the lesion regions, and then automatically learns the corresponding weights for feature fusion according to the contribution of different features to model grading. Finally, the graph convolution operation is used to link the lesion features in different regions. As a result, our proposed method can effectively combine local and global features, which is beneficial for the correct DR grading. We evaluate the effectiveness of method on two publicly available datasets, namely APTOS and DDR. Extensive experiments demonstrate that our proposed MDGNet achieves the best grading results on APTOS and DDR, and is more accurate and diverse for the extraction of lesion information.

Micro-segmentation of retinal image lesions in diabetic retinopathy using energy-based fuzzy C-Means clustering (EFM-FCM)

Diabetic retinopathy (DR) is a prevalent cause of global visual impairment, contributing to approximately 4.8% of blindness cases worldwide as reported by the World Health Organization (WHO). The condition is characterized by pathological abnormalities in the retinal layer, including microaneurysms, vitreous hemorrhages, and exudates. Microscopic analysis of retinal images is crucial in diagnosing and treating DR. This article proposes a novel method for early DR screening using segmentation and unsupervised learning techniques. The approach integrates a neural network energy-based model into the Fuzzy C-Means (FCM) algorithm to enhance convergence criteria, aiming to improve the accuracy and efficiency of automated DR screening tools. The evaluation of results includes the primary dataset from the Shiva Netralaya Centre, IDRiD, and DIARETDB1. The performance of the proposed method is compared against FCM, EFCM, FLICM, and M-FLICM techniques, utilizing metrics such as accuracy in noiseless and noisy conditions and average execution time. The results showcase auspicious performance on both primary and secondary datasets, achieving accuracy rates of 99.03% in noiseless conditions and 93.13% in noisy images, with an average execution time of 16.1 s. The proposed method holds significant potential in medical image analysis and could pave the way for future advancements in automated DR diagnosis and management. RESEARCH HIGHLIGHTS: A novel approach is proposed in the article, integrating a neural network energy-based model into the FCM algorithm to enhance the convergence criteria and the accuracy of automated DR screening tools. By leveraging the microscopic characteristics of retinal images, the proposed method significantly improves the accuracy of lesion segmentation, facilitating early detection and monitoring of DR. The evaluation of the method's performance includes primary datasets from reputable sources such as the Shiva Netralaya Centre, IDRiD, and DIARETDB1, demonstrating its effectiveness in comparison to other techniques (FCM, EFCM, FLICM, and M-FLICM) in terms of accuracy in both noiseless and noisy conditions. It achieves impressive accuracy rates of 99.03% in noiseless conditions and 93.13% in noisy images, with an average execution time of 16.1 s.

Exhaled breath signal analysis for diabetes detection: an optimized deep learning approach

In this study, a flexible deep learning system for breath analysis is created using an optimal hybrid deep learning model. To improve the quality of the gathered breath signals, the raw data are first pre-processed. Then, the most relevant features like Improved IMFCC, BFCC (bark frequency), DWT, peak detection, QT intervals, and PR intervals are extracted. Then, using these features the hybrid classifiers built into the diabetic's detection phase is trained. The diabetic detection phase is modeled with an optimized DBN and BI-GRU model. To enhance the detection accuracy of the proposed model, the weight function of DBN is fine-tuned with the newly projected Sine Customized by Marine Predators (SCMP) model that is modeled by conceptually blending the standard MPA and SCA models, respectively. The final outcome from optimized DBN and Bi-GRU is combined to acquire the ultimate detected outcome. Further, to validate the efficiency of the projected model, a comparative evaluation has been undergone. Accordingly, the accuracy of the proposed model is above 98%. The accuracy of the proposed model is 54.6%, 56.9%, 56.95, 44.55, 57%, 56.95, 18.2%, and 56.9% improved over the traditional models like CNN + LSTM, CNN + LSTM, CNN, LSTM, RNN, SVM, RF, and DBN, at 60th learning percentage.

Recent Advances and Perspectives in Relation to the Metabolomics-Based Study of Diabetic Retinopathy

Diabetic retinopathy (DR), a prevalent microvascular complication of diabetes, is a major cause of acquired blindness in adults. Currently, a clinical diagnosis of DR primarily relies on fundus fluorescein angiography, with a limited availability of effective biomarkers. Metabolomics, a discipline dedicated to scrutinizing the response of various metabolites within living organisms, has shown noteworthy advancements in uncovering metabolic disorders and identifying key metabolites associated with DR in recent years. Consequently, this review aims to present the latest advancements in metabolomics techniques and comprehensively discuss the principal metabolic outcomes derived from analyzing blood, vitreous humor, aqueous humor, urine, and fecal samples.

Hybrid adaptive deep learning classifier for early detection of diabetic retinopathy using optimal feature extraction and classification

Objectives

Diabetic retinopathy (DR) is one of the leading causes of blindness. It is important to use a comprehensive learning method to identify the DR. However, comprehensive learning methods often rely heavily on encrypted data, which can be costly and time consuming. Also, the DR function is not displayed and is scattered in the high-definition image below.

Methods

Therefore, learning how to distribute such DR functions is a big challenge. In this work, we proposed a hybrid adaptive deep learning classifier for early detection of diabetic retinopathy (HADL-DR). First, we provide an improved multichannel-based generative adversarial network (MGAN) with semi-maintenance to detect blood vessels segmentation.

Results

By reducing the reliance on the encoded data, the following high-resolution images can be used to detect the indivisible features of some semi-observed MGAN references. Scale invariant feature transform (SIFT) function is then extracted and the best function is selected using the improved sequential approximation optimization (SAO) algorithm. After that, a hybrid recurrent neural network with long short-term memory (RNN-LSTM) is utilized for DR classification. The proposed RNN-LSTM classifier evaluated through standard benchmark Kaggle and Messidor datasets.

Conclusion

Finally, the simulation results are compared with the existing state-of-art classifiers in terms of accuracy, precision, recall, f-measure and area under cover (AUC), it is seen that more successful results are obtained.

Detecting red-lesions from retinal fundus images using unique morphological features

One of the most important retinal diseases is Diabetic Retinopathy (DR) which can lead to serious damage to vision if remains untreated. Red-lesions are from important demonstrations of DR helping its identification in early stages. The detection and verification of them is helpful in the evaluation of disease severity and progression. In this paper, a novel image processing method is proposed for extracting red-lesions from fundus images. The method works based on finding and extracting the unique morphological features of red-lesions. After quality improvement of images, a pixel-based verification is performed in the proposed method to find the ones which provide a significant intensity change in a curve-like neighborhood. In order to do so, a curve is considered around each pixel and the intensity changes around the curve boundary are considered. The pixels for which it is possible to find such curves in at least two directions are considered as parts of red-lesions. The simplicity of computations, the high accuracy of results, and no need to post-processing operations are the important characteristics of the proposed method endorsing its good performance.

Exudate identification in retinal fundus images using precise textural verifications

One of the most salient diseases of retina is Diabetic Retinopathy (DR) which may lead to irreparable damages to eye vision in the advanced phases. A large number of the people infected with diabetes experience DR. The early identification of DR signs facilitates the treatment process and prevents from blindness. Hard Exudates (HE) are bright lesions appeared in retinal fundus images of DR patients. Thus, the detection of HEs is an important task preventing the progress of DR. However, the detection of HEs is a challenging process due to their different appearance features. In this paper, an automatic method for the identification of HEs with various sizes and shapes is proposed. The method works based on a pixel-wise approach. It considers several semi-circular regions around each pixel. For each semi-circular region, the intensity changes around several directions and non-necessarily equal radiuses are computed. All pixels for which several semi-circular regions include considerable intensity changes are considered as the pixels located in HEs. In order to reduce false positives, an optic disc localization method is proposed in the post-processing phase. The performance of the proposed method has been evaluated on DIARETDB0 and DIARETDB1 datasets. The experimental results confirm the improved performance of the suggested method in term of accuracy.

Automatic Multilabel Classification of Multiple Fundus Diseases Based on Convolutional Neural Network With Squeeze-and-Excitation Attention

Purpose

Automatic multilabel classification of multiple fundus diseases is of importance for ophthalmologists. This study aims to design an effective multilabel classification model that can automatically classify multiple fundus diseases based on color fundus images.

Methods

We proposed a multilabel fundus disease classification model based on a convolutional neural network to classify normal and seven categories of common fundus diseases. Specifically, an attention mechanism was introduced into the network to further extract information features from color fundus images. The fundus images with eight categories of labels were applied to train, validate, and test our model. We employed the validation accuracy, area under the receiver operating characteristic curve (AUC), and F1-score as performance metrics to evaluate our model.

Results

Our proposed model achieved better performance with a validation accuracy of 94.27%, an AUC of 85.80%, and an F1-score of 86.08%, compared to two state-of-the-art models. Most important, the number of training parameters has dramatically dropped by three and eight times compared to the two state-of-the-art models.

Conclusions

This model can automatically classify multiple fundus diseases with not only excellent accuracy, AUC, and F1-score but also significantly fewer training parameters and lower computational cost, providing a reliable assistant in clinical screening.

Translational Relevance

The proposed model can be widely applied in large-scale multiple fundus disease screening, helping to create more efficient diagnostics in primary care settings.

Recent trends and advances in fundus image analysis: A review

Automated retinal image analysis holds prime significance in the accurate diagnosis of various critical eye diseases that include diabetic retinopathy (DR), age-related macular degeneration (AMD), atherosclerosis, and glaucoma. Manual diagnosis of retinal diseases by ophthalmologists takes time, effort, and financial resources, and is prone to error, in comparison to computer-aided diagnosis systems. In this context, robust classification and segmentation of retinal images are primary operations that aid clinicians in the early screening of patients to ensure the prevention and/or treatment of these diseases. This paper conducts an extensive review of the state-of-the-art methods for the detection and segmentation of retinal image features. Existing notable techniques for the detection of retinal features are categorized into essential groups and compared in depth. Additionally, a summary of quantifiable performance measures for various important stages of retinal image analysis, such as image acquisition and preprocessing, is provided. Finally, the widely used in the literature datasets for analyzing retinal images are described and their significance is emphasized.

Nested U-Net for Segmentation of Red Lesions in Retinal Fundus Images and Sub-image Classification for Removal of False Positives

Diabetic retinopathy is a pathological change of the retina that occurs for long-term diabetes. The patients become symptomatic in advanced stages of diabetic retinopathy resulting in severe non-proliferative diabetic retinopathy or proliferative diabetic retinopathy stages. There is a need of an automated screening tool for the early detection and treatment of patients with diabetic retinopathy. This paper focuses on the segmentation of red lesions using nested U-Net Zhou et al. (Deep Learning in Medical Image Analysis and Multimodal Learning for Clinical Decision Support, Springer, 2018) followed by removal of false positives based on the sub-image classification method. Different sizes of sub-images were studied for the reduction in false positives in the sub-image classification method. The network could capture semantic features and fine details due to dense convolutional blocks connected via skip connections in between down sampling and up sampling paths. False-negative candidates were very few and the sub-image classification network effectively reduced the falsely detected candidates. The proposed framework achieves a sensitivity of [Formula: see text], precision of [Formula: see text], and F1-Score of [Formula: see text] for the DIARETDB1 data set Kalviainen and Uusutalo (Medical Image Understanding and Analysis, Citeseer, 2007). It outperforms the state-of-the-art networks such as U-Net Ronneberger et al. (International Conference on Medical Image Computing and Computer-Assisted Intervention, Springer, 2015) and attention U-Net Oktay et al. (Attention u-net: Learning where to look for the pancreas, 2018).

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.

Optimal Feature Selection for Diagnosing Diabetic Retinopathy Using FireFly Migration Operator-Based Monarch Butterfly Optimization

In recent years, diabetic retinopathy (DR) needs to be focused with the intention of developing accurate and effective approaches by accomplishing the existing challenges in the traditional models. With this objective, this paper aims to introduce an effective diagnosis system by utilizing retinal fundus images. The implementation of this diagnosis model incorporates 4 stages like (i) preprocessing, (ii) blood vessel segmentation, (iii) feature extraction, as well as (iv) classification. Originally, the median filter as well as contrast limited adaptive histogram equalization (CLAHE) help to preprocess the image. Moreover, the Fuzzy C Mean (FCM) thresholding is applied for blood vessel segmentation, which generates stochastic clustering of pixels to obtain enhanced threshold values. Further, feature extraction is accomplished by utilizing gray-level run-length matrix (GLRM), local, and morphological transformation-based features. Furthermore, a deep learning (DL) model known as convolutional neural network (CNN) is employed for the diagnosis or classification purpose. As a main novelty, this paper introduces an optimal feature selection as well as classification model. Further, the feature selection is done optimally by FireFly Migration Operator-based Monarch Butterfly Optimization (FM-MBO) which hybridized of the monarch butterfly optimization (MBO) and fire fly (FF) algorithms as the entire adopted extracted features attain higher feature length. Moreover, the proposed FM-MBO algorithm helps for optimizing the count of CNN's convolutional neurons to further improve the performance accuracy. At the end, the enhanced outcomes of the adopted diagnostic scheme are validated via a valuable comparative examination in terms of significant performance measures.

Red-lesion extraction in retinal fundus images by directional intensity changes' analysis

Diabetic retinopathy (DR) is an important retinal disease threatening people with the long diabetic history. Blood leakage in retina leads to the formation of red lesions in retina the analysis of which is helpful in the determination of severity of disease. In this paper, a novel red-lesion extraction method is proposed. The new method firstly determines the boundary pixels of blood vessel and red lesions. Then, it determines the distinguishing features of boundary pixels of red-lesions to discriminate them from other boundary pixels. The main point utilized here is that a red lesion can be observed as significant intensity changes in almost all directions in the fundus image. This can be feasible through considering special neighborhood windows around the extracted boundary pixels. The performance of the proposed method has been evaluated for three different datasets including Diaretdb0, Diaretdb1 and Kaggle datasets. It is shown that the method is capable of providing the values of 0.87 and 0.88 for sensitivity and specificity of Diaretdb1, 0.89 and 0.9 for sensitivity and specificity of Diaretdb0, 0.82 and 0.9 for sensitivity and specificity of Kaggle. Also, the proposed method has a time-efficient performance in the red-lesion extraction process.

Region of interest-based predictive algorithm for subretinal hemorrhage detection using faster R-CNN

Macular edema (ME) is an essential sort of macular issue caused due to the storing of fluid underneath the macula. Age-related Macular Degeneration (AMD) and diabetic macular edema (DME) are the two customary visual contaminations that can lead to fragmentary or complete vision loss. This paper proposes a deep learning-based predictive algorithm that can be used to detect the presence of a Subretinal hemorrhage. Region Convolutional Neural Network (R-CNN) and faster R-CNN are used to develop the predictive algorithm that can improve the classification accuracy. This method initially detects the presence of Subretinal hemorrhage, and it then segments the Region of Interest (ROI) by a semantic segmentation process. The segmented ROI is applied to a predictive algorithm which is derived from the Fast Region Convolutional Neural Network algorithm, that can categorize the Subretinal hemorrhage as responsive or non-responsive. The dataset, provided by a medical institution, comprised of optical coherence tomography (OCT) images of both pre- and post-treatment images, was used for training the proposed Faster Region Convolutional Neural Network (Faster R-CNN). We also used the Kaggle dataset for performance comparison with the traditional methods that are derived from the convolutional neural network (CNN) algorithm. The evaluation results using the Kaggle dataset and the hospital images provide an average sensitivity, selectivity, and accuracy of 85.3%, 89.64%, and 93.48% respectively. Further, the proposed method provides a time complexity in testing as 2.64s, which is less than the traditional schemes like CNN, R-CNN, and Fast R-CNN.

Review of Various Tasks Performed in the Preprocessing Phase of a Diabetic Retinopathy Diagnosis System

Diabetic Retinopathy (DR) is a major cause of blindness in diabetic patients. The increasing population of diabetic patients and difficulty to diagnose it at an early stage are limiting the screening capabilities of manual diagnosis by ophthalmologists. Color fundus images are widely used to detect DR lesions due to their comfortable, cost-effective and non-invasive acquisition procedure. Computer Aided Diagnosis (CAD) of DR based on these images can assist ophthalmologists and help in saving many sight years of diabetic patients. In a CAD system, preprocessing is a crucial phase, which significantly affects its performance. Commonly used preprocessing operations are the enhancement of poor contrast, balancing the illumination imbalance due to the spherical shape of a retina, noise reduction, image resizing to support multi-resolution, color normalization, extraction of a field of view (FOV), etc. Also, the presence of blood vessels and optic discs makes the lesion detection more challenging because these two artifacts exhibit specific attributes, which are similar to those of DR lesions. Preprocessing operations can be broadly divided into three categories: 1) fixing the native defects, 2) segmentation of blood vessels, and 3) localization and segmentation of optic discs. This paper presents a review of the state-of-the-art preprocessing techniques related to three categories of operations, highlighting their significant aspects and limitations. The survey is concluded with the most effective preprocessing methods, which have been shown to improve the accuracy and efficiency of the CAD systems.

Kim P, Kim J. Retinal Healthcare Diagnosis Approaches with Deep Learning Techniques

The retina is an important organ of the human body, with a crucial function in the vision mechanism. A minor disturbance in the retina can cause various abnormalities in the eye, as well as complex retinal diseases such as diabetic retinopathy. To diagnose such diseases in early stages, many researchers are incorporating machine learning (ML) technique. The combination of medical science with ML improves the healthcare diagnosis systems of hospitals, clinics, and other providers. Recently, AI-based healthcare diagnosis systems assist clinicians in handling more patients in less time and improves diagnosis accuracy. In this paper, we review cutting-edge AI-based retinal diagnosis technologies. This article also briefly describes the potential of the latest densely connected convolutional networks (DenseNets) to improve the performance of diagnosis systems. Moreover, this paper focuses on state-of-the-art results from comprehensive investigations in retinal diagnosis and the development of AI-based retinal healthcare diagnosis approaches with deep-learning models.

Automated diagnosis of diabetic retinopathy enabled by optimized thresholding-based blood vessel segmentation and hybrid classifier

Objectives

The focus of this paper is to introduce an automated early Diabetic Retinopathy (DR) detection scheme from colour fundus images through enhanced segmentation and classification strategies by analyzing blood vessels.

Methods

The occurrence of DR is increasing from the past years, impacting the eyes due to a sudden rise in the glucose level of blood. All over the world, half of the people who are under age 70 are severely suffered from diabetes. The patients who are affected by DR will lose their vision during the absence of early recognition of DR and appropriate treatment. To decrease the growth and occurrence of loss of vision, the early detection and timely treatment of DR are desirable. At present, deep learning models have presented better performance using retinal images for DR detection. In this work, the input retinal fundus images are initially subjected to pre-processing that undergoes contrast enhancement by Contrast Limited Adaptive Histogram Equalization (CLAHE) and average filtering. Further, the optimized binary thresholding-based segmentation is done for blood vessel segmentation. For the segmented image, Tri-level Discrete Level Decomposition (Tri-DWT) is performed to decompose it. In the feature extraction phase, Local Binary Pattern (LBP), and Gray-Level Co-occurrence Matrices (GLCMs) are extracted. Next, the classification of images is done through the combination of two algorithms, one is Neural Network (NN), and the other Convolutional Neural Network (CNN). The extracted features are subjected to NN, and the tri-DWT-based segmented image is subjected to CNN. Both the segmentation and classification phases are enhanced by the improved meta-heuristic algorithm called Fitness Rate-based Crow Search Algorithm (FR-CSA), in which few parameters are optimized for attaining maximum detection accuracy.

Results

The proposed DR detection model was implemented in MATLAB 2018a, and the analysis was done using three datasets, HRF, Messidor, and DIARETDB.

Conclusions

The developed FR-CSA algorithm has the best detection accuracy in diagnosing DR.

Effective Fundus Image Decomposition for the Detection of Red Lesions and Hard Exudates to Aid in the Diagnosis of Diabetic Retinopathy

Diabetic retinopathy (DR) is characterized by the presence of red lesions (RLs), such as microaneurysms and hemorrhages, and bright lesions, such as exudates (EXs). Early DR diagnosis is paramount to prevent serious sight damage. Computer-assisted diagnostic systems are based on the detection of those lesions through the analysis of fundus images. In this paper, a novel method is proposed for the automatic detection of RLs and EXs. As the main contribution, the fundus image was decomposed into various layers, including the lesion candidates, the reflective features of the retina, and the choroidal vasculature visible in tigroid retinas. We used a proprietary database containing 564 images, randomly divided into a training set and a test set, and the public database DiaretDB1 to verify the robustness of the algorithm. Lesion detection results were computed per pixel and per image. Using the proprietary database, 88.34% per-image accuracy (ACCi), 91.07% per-pixel positive predictive value (PPVp), and 85.25% per-pixel sensitivity (SEp) were reached for the detection of RLs. Using the public database, 90.16% ACCi, 96.26% PPV_p, and 84.79% SEp were obtained. As for the detection of EXs, 95.41% ACCi, 96.01% PPV_p, and 89.42% SE_p were reached with the proprietary database. Using the public database, 91.80% ACCi, 98.59% PPVp, and 91.65% SEp were obtained. The proposed method could be useful to aid in the diagnosis of DR, reducing the workload of specialists and improving the attention to diabetic patients.

A Multi-Label Deep Learning Model with Interpretable Grad-CAM for Diabetic Retinopathy Classification

The characteristics of diabetic retinopathy (DR) fundus images generally consist of multiple types of lesions which provided strong evidence for the ophthalmologists to make diagnosis. It is particularly significant to figure out an efficient method to not only accurately classify DR fundus images but also recognize all kinds of lesions on them. In this paper, a deep learning-based multi-label classification model with Gradient-weighted Class Activation Mapping (Grad-CAM) was proposed, which can both make DR classification and automatically locate the regions of different lesions. To reducing laborious annotation work and improve the efficiency of labeling, this paper innovatively considered different types of lesions as different labels for a fundus image so that this paper changed the task of lesion detection into that of image classification. A total of five labels were pre-defined and 3228 fundus images were collected for developing our model. The architecture of deep learning model was designed by ourselves based on ResNet. Through experiments on the test images, this method acquired a sensitive of 93.9% and a specificity of 94.4% on DR classification. Moreover, the corresponding regions of lesions were reasonably outlined on the DR fundus images.

Automatic Grading of Retinal Blood Vessel in Deep Retinal Image Diagnosis

Automatic grading of retinal blood vessels from fundus image can be a useful tool for diagnosis, planning and treatment of eye. Automatic diagnosis of retinal images for early detection of glaucoma, stroke, and blindness is emerging in intelligent health care system. The method primarily depends on various abnormal signs, such as area of hard exudates, area of blood vessels, bifurcation points, texture, and entropies. The development of an automated screening system based on vessel width, tortuosity, and vessel branching are also used for grading. However, the automated method that directly can come to a decision by taking the fundus images got less attention. Detecting eye problems based on the tortuosity of the vessel from fundus images is a complicated task for opthalmologists. So automated grading algorithm using deep learning can be most valuable for grading retinal health. The aim of this work is to develop an automatic computer aided diagnosis system to solve the problem. This work approaches to achieve an automatic grading method that is opted using Convolutional Neural Network (CNN) model. In this work we have studied the state-of-the-art machine learning algorithms and proposed an attention network which can grade retinal images. The proposed method is validated on a public dataset EIARG1, which is only publicly available dataset for such task as per our knowledge.

Classification of advanced and early stages of diabetic retinopathy from non-diabetic subjects by an ordinary least squares modeling method applied to OCTA images

As the prevalence of diabetic retinopathy (DR) continues to rise, there is a need to develop computer-aided screening methods. The current study reports and validates an ordinary least squares (OLS) method to model optical coherence tomography angiography (OCTA) images and derive OLS parameters for classifying proliferative DR (PDR) and no/mild non-proliferative DR (NPDR) from non-diabetic subjects. OLS parameters were correlated with vessel metrics quantified from OCTA images and were used to determine predicted probabilities of PDR, no/mild NPDR, and non-diabetics. The classification rates of PDR and no/mild NPDR from non-diabetic subjects were 94% and 91%, respectively. The method had excellent predictive ability and was validated. With further development, the method may have potential clinical utility and contribute to image-based computer-aided screening and classification of stages of DR and other ocular and systemic diseases.

A survey on medical image analysis in diabetic retinopathy

Diabetic Retinopathy (DR) represents a highly-prevalent complication of diabetes in which individuals suffer from damage to the blood vessels in the retina. The disease manifests itself through lesion presence, starting with microaneurysms, at the nonproliferative stage before being characterized by neovascularization in the proliferative stage. Retinal specialists strive to detect DR early so that the disease can be treated before substantial, irreversible vision loss occurs. The level of DR severity indicates the extent of treatment necessary - vision loss may be preventable by effective diabetes management in mild (early) stages, rather than subjecting the patient to invasive laser surgery. Using artificial intelligence (AI), highly accurate and efficient systems can be developed to help assist medical professionals in screening and diagnosing DR earlier and without the full resources that are available in specialty clinics. In particular, deep learning facilitates diagnosis earlier and with higher sensitivity and specificity. Such systems make decisions based on minimally handcrafted features and pave the way for personalized therapies. Thus, this survey provides a comprehensive description of the current technology used in each step of DR diagnosis. First, it begins with an introduction to the disease and the current technologies and resources available in this space. It proceeds to discuss the frameworks that different teams have used to detect and classify DR. Ultimately, we conclude that deep learning systems offer revolutionary potential to DR identification and prevention of vision loss.

Deep and Densely Connected Networks for Classification of Diabetic Retinopathy

Diabetes has recently emerged as a worldwide problem, and diabetic retinopathy is an abnormal state associated with the human retina. Due to the increase in daily screen-related activities of modern human beings, diabetic retinopathy is more prevalent among adults, leading to minor and major blindness. Doctors and clinicians are unable to perform early diagnoses due to the large number of patients. To solve this problem, this study introduces a classification model for retinal images that distinguishes between the various stages of diabetic retinopathy. This work involves deploying deep and densely connected networks for retinal image analysis with training from scratch. Dense connections between the convolutional layers of the network are an essential factor to enhance accuracy owing to the deeper supervision between layers. Another factor is the growth rate that further assists our model in learning more sophisticated feature maps regarding retinal images from every stage of the network. We compute the area under the curve, sensitivity, and specificity, particularly for messidor-2 and EyePACS. Compared to existing approaches, our method achieved better results, with an approximate rise rate of 0.01, 0.03, and 0.01, respectively. Therefore, computer-aided programs can help in diagnostic centers as automated detection systems.

Referable diabetic retinopathy identification from eye fundus images with weighted path for convolutional neural network

Diabetic retinopathy (DR) is the most common cause of blindness in middle-age subjects and low DR screening rates demonstrates the need for an automated image assessment system, which can benefit from the development of deep learning techniques. Therefore, the effective classification performance is significant in favor of the referable DR identification task. In this paper, we propose a new strategy, which applies multiple weighted paths into convolutional neural network, called the WP-CNN, motivated by the ensemble learning. In WP-CNN, multiple path weight coefficients are optimized by back propagation, and the output features are averaged for redundancy reduction and fast convergence. The experiment results show that with the efficient training convergence rate WP-CNN achieves an accuracy of 94.23% with sensitivity of 90.94%, specificity of 95.74%, an area under the receiver operating curve of 0.9823 and F1-score of 0.9087. By taking full advantage of the multipath mechanism, the proposed WP-CNN is shown to be accurate and effective for referable DR identification compared to the state-of-art algorithms.

Artificial Intelligence for the Detection of Diabetic Retinopathy in Primary Care: Protocol for Algorithm Development

Background

Diabetic retinopathy (DR) is one of the most important causes of blindness worldwide, especially in developed countries. In diabetic patients, periodic examination of the back of the eye using a nonmydriatic camera has been widely demonstrated to be an effective system to control and prevent the onset of DR. Convolutional neural networks have been used to detect DR, achieving very high sensitivities and specificities.

Objective

The objective of this is paper was to develop an artificial intelligence (AI) algorithm for the detection of signs of DR in diabetic patients and to scientifically validate the algorithm to be used as a screening tool in primary care.

Methods

Under this project, 2 studies will be conducted in a concomitant way: (1) Development of an algorithm with AI to detect signs of DR in patients with diabetes and (2) A prospective study comparing the diagnostic capacity of the AI algorithm with respect to the actual system of family physicians evaluating the images. The standard reference to compare with will be a blinded double reading conducted by retina specialists. For the development of the AI algorithm, different iterations and workouts will be performed on the same set of data. Before starting each new workout, the strategy of dividing the set date into 2 groups will be used randomly. A group with 80% of the images will be used during the training (training dataset), and the remaining 20% images will be used to validate the results (validation dataset) of each cycle (epoch). During the prospective study, true-positive, true-negative, false-positive, and false-negative values will be calculated again. From here, we will obtain the resulting confusion matrix and other indicators to measure the performance of the algorithm.

Results

Cession of the images began at the end of 2018. The development of the AI algorithm is calculated to last about 3 to 4 months. Inclusion of patients in the cohort will start in early 2019 and is expected to last 3 to 4 months. Preliminary results are expected to be published by the end of 2019.

Conclusions

The study will allow the development of an algorithm based on AI that can demonstrate an equal or superior performance, and that constitutes a complement or an alternative, to the current screening of DR in diabetic patients.

International Registered Report Identifier (IRRID)

PRR1-10.2196/12539

Development of an artificial intelligence system to classify pathology and clinical features on retinal fundus images

IMPORTANCE

Artificial intelligence (AI) algorithms are under development for use in diabetic retinopathy photo screening pathways. To be clinically acceptable, such systems must also be able to classify other fundus abnormalities and clinical features at the point of care.

BACKGROUND

We aimed to develop an AI system that can detect several fundus pathologies and report relevant clinical features.

DESIGN

Convolutional neural network training with retrospective data set.

PARTICIPANTS

Colour fundus photos were obtained from publicly available fundus image databases.

METHODS

Images were uploaded to a web-based AI platform for training and validation of AI classifiers. Separate classifiers were created for each fundus pathology and clinical feature.

MAIN OUTCOME MEASURES

Accuracy, sensitivity, specificity and area under receiver operating characteristic curve (AUC) for each classifier.

RESULTS

We obtained 4435 images from publicly available fundus image databases. AI classifiers were developed for each disease state above. Although statistical performance was limited by the small sample size, average accuracy was 89%, average sensitivity was 75%, average specificity was 89% and average AUC was 0.58.

CONCLUSION AND RELEVANCE

This study is a proof-of-concept AI system that could be implemented within a diabetic photo-screening pathway. Performance was promising but not yet at the level that would be required for clinical application. We have shown that it is possible for clinicians to develop AI classifiers with no previous programming or AI knowledge, using standard laptop computers.