Red Lesion Detection Using Dynamic Shape Features for Diabetic Retinopathy Screening

Simultaneous Diagnosis of Severity and Features of Diabetic Retinopathy in Fundus Photography Using Deep Learning

Deep learning methods for diabetic retinopathy (DR) diagnosis are usually criticized as being lack of interpretability in the diagnostic result, thus limiting their application in clinic. Simultaneous prediction of DR related features during the DR severity diagnosis is able to resolve this issue by providing supporting evidence (i.e. DR related features) for the diagnostic result (i.e. DR severity). In this study, we propose a hierarchical multi-task deep learning framework for simultaneous diagnosis of DR severity and DR related features in fundus images. A hierarchical structure is introduced to incorporate the casual relationship between DR related features and DR severity levels. In the experiments, the proposed approach was evaluated on two independent testing sets using quadratic weighted Cohen's kappa coefficient, receiver operating characteristic analysis, and precision-recall analysis. A grader study was also conducted to compare the performance of the proposed approach with those of general ophthalmologists with different levels of experience. The results demonstrate that the proposed approach could improve the performance for both DR severity diagnosis and DR related feature detection when comparing with the traditional deep learning-based methods. It achieves performance close to general ophthalmologists with five years of experience when diagnosing DR severity levels, and general ophthalmologists with ten years of experience for referable DR detection.

Automatic Identification of Referral-Warranted Diabetic Retinopathy Using Deep Learning on Mobile Phone Images

Purpose

To evaluate the performance of a deep learning algorithm in the detection of referral-warranted diabetic retinopathy (RDR) on low-resolution fundus images acquired with a smartphone and indirect ophthalmoscope lens adapter.

Methods

An automated deep learning algorithm trained on 92,364 traditional fundus camera images was tested on a dataset of smartphone fundus images from 103 eyes acquired from two previously published studies. Images were extracted from live video screenshots from fundus examinations using a commercially available lens adapter and exported as a screenshot from live video clips filmed at 1080p resolution. Each image was graded twice by a board-certified ophthalmologist and compared to the output of the algorithm, which classified each image as having RDR (moderate nonproliferative DR or worse) or no RDR.

Results

In spite of the presence of multiple artifacts (lens glare, lens particulates/smudging, user hands over the objective lens) and low-resolution images achieved by users of various levels of medical training, the algorithm achieved a 0.89 (95% confidence interval [CI] 0.83-0.95) area under the curve with an 89% sensitivity (95% CI 81%-100%) and 83% specificity (95% CI 77%-89%) for detecting RDR on mobile phone acquired fundus photos.

Conclusions

The fully data-driven artificial intelligence-based grading algorithm herein can be used to screen fundus photos taken from mobile devices and identify with high reliability which cases should be referred to an ophthalmologist for further evaluation and treatment.

Translational Relevance

The implementation of this algorithm on a global basis could drastically reduce the rate of vision loss attributed to 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.

Automatic microaneurysm detection in fundus image based on local cross-section transformation and multi-feature fusion

BACKGROUND AND OBJECTIVE

Retinal microaneurysm (MA) is one of the earliest clinical signs of diabetic retinopathy(DR). Its detection is essential for controlling DR and preventing vision loss. However, the spatial scale of MA is extremely small and the contrast to surrounding background is subtle, which make MA detection challenging. The purpose of this work is to automatically detect MAs from fundus images.

METHODS

Our MA detector involves two stages: MA candidate extraction and classification. In MA candidate extraction stage, local minimum region extraction and block filtering are used to exploit the regions where MA may exist. In this way, most of irrelavent background regions are discarded , which subsequently facilitates the training of MA classifier. In the second stage, multiple features are extracted to train the MA classifier. To distinguish MA from vascular regions, we propose a series of descriptors according to the cross-section profile of MA. Specially, as MAs are small and their contrast to surroundings is subtle, we propose local cross-section transformation (LCT) to amplify the difference between the MA and confusing structures. Finally, an under-sampling boosting-based classifier (RUSBoost) is trained to determine whether the candidate is an MA.

RESULTS

The proposed method is evaluated on three public available databases i.e. e-ophtha-MA, DiaretDB1 and ROC training set. It achieves high sensitivities for low false positive rates on the three databases. Using the FROC metric, the final scores are 0.516, 0.402 and 0.293 respectively, which are comparable to existing state-of-the-art methods.

CONCLUSIONS

The proposed local cross-section transformation enhances the discrimination of descriptors by amplifying difference between MAs and confusing structures, which facilitates the classification and improves the detection performances. With the powerful descriptors, our method achieves state-of-the-art performances on three public datasets consistently.

A robust method for the automatic location of the optic disc and the fovea in fundus images

BACKGROUND AND OBJECTIVE

The location of the optic disc (OD) and the fovea is usually crucial in automatic screening systems for diabetic retinopathy. Previous methods aimed at their location often fail when these structures do not have the standard appearance. The purpose of this work is to propose novel, robust methods for the automatic detection of the OD and the fovea.

METHODS

The proposed method comprises a preprocessing stage, a method for retinal background extraction, a vasculature segmentation phase and the computation of various novel saliency maps. The main novelty of this work is the combination of the proposed saliency maps, which represent the spatial relationships between some structures of the retina and the visual appearance of the OD and fovea. Another contribution is the method to extract the retinal background, based on region-growing.

RESULTS

The proposed methods were evaluated over a proprietary database and three public databases: DRIVE, DiaretDB1 and Messidor. For the OD, we achieved 100% accuracy for all databases except Messidor (99.50%). As for the fovea location, we also reached 100% accuracy for all databases except Messidor (99.67%).

CONCLUSIONS

Our results suggest that the proposed methods are robust and effective to automatically detect the OD and the fovea. This way, they can be useful in automatic screening systems for diabetic retinopathy as well as other retinal diseases.

Microaneurysm detection in color eye fundus images for diabetic retinopathy screening

Diabetic retinopathy (DR) is a diabetes complication, which in extreme situations may lead to blindness. Since the first stages are often asymptomatic, regular eye examinations are required for an early diagnosis. As microaneurysms (MAs) are one of the first signs of DR, several automated methods have been proposed for their detection in order to reduce the ophthalmologists' workload. Although local convergence filters (LCFs) have already been applied for feature extraction, their potential as MA enhancement operators was not explored yet. In this work, we propose a sliding band filter for MA enhancement aiming at obtaining a set of initial MA candidates. Then, a combination of the filter responses with color, contrast and shape information is used by an ensemble of classifiers for final candidate classification. Finally, for each eye fundus image, a score is computed from the confidence values assigned to the MAs detected in the image. The performance of the proposed methodology was evaluated in four datasets. At the lesion level, sensitivities of 64% and 81% were achieved for an average of 8 false positives per image (FPIs) in e-ophtha MA and SCREEN-DR, respectively. In the last dataset, an AUC of 0.83 was also obtained for DR detection.

Automated detection of diabetic retinopathy in fundus images using fused features

Diabetic retinopathy (DR) is one of the severe eye conditions due to diabetes complication which can lead to vision loss if left untreated. In this paper, a computationally simple, yet very effective, DR detection method is proposed. First, a segmentation independent two-stage preprocessing based technique is proposed which can effectively extract DR pathognomonic signs; both bright and red lesions, and blood vessels from the eye fundus image. Then, the performance of Local Binary Patterns (LBP), Local Ternary Patterns (LTP), Dense Scale-Invariant Feature Transform (DSIFT) and Histogram of Oriented Gradients (HOG) as a feature descriptor for fundus images, is thoroughly analyzed. SVM kernel-based classifiers are trained and tested, using a 5-fold cross-validation scheme, on both newly acquired fundus image database from the local hospital and combined database created from the open-sourced available databases. The classification accuracy of 96.6% with 0.964 sensitivity and 0.969 specificity is achieved using a Cubic SVM classifier with LBP and LTP fused features for the local database. More importantly, in out-of-sample testing on the combined database, the model gives an accuracy of 95.21% with a sensitivity of 0.970 and specificity of 0.932. This indicates the proposed model is very well-fitted and generalized which is further corroborated by the presented train-test curves.

Automatic Diabetic Retinopathy Grading via Self-Knowledge Distillation

Diabetic retinopathy (DR) is a common fundus disease that leads to irreversible blindness, which plagues the working-age population. Automatic medical imaging diagnosis provides a non-invasive method to assist ophthalmologists in timely screening of suspected DR cases, which prevents its further deterioration. However, the state-of-the-art deep-learning-based methods generally have a large amount of model parameters, which makes large-scale clinical deployment a time-consuming task. Moreover, the severity of DR is associated with lesions, and it is difficult for the model to focus on these regions. In this paper, we propose a novel deep-learning technique for grading DR with only image-level supervision. Specifically, we first customize the model with the help of self-knowledge distillation to achieve a trade-off between model performance and time complexity. Secondly, CAM-Attention is used to allow the network to focus on discriminative zone, e.g., microaneurysms, soft/hard exudates, etc.. Considering that directly attaching a classifier after the Side branch will disrupt the hierarchical nature of convolutional neural networks, a Mimicking Module is employed that allows the Side branch to actively mimic the main branch structure. Extensive experiments are conducted on two benchmark datasets, with an AUC of 0.965 and an accuracy of 92.9% for the Messidor dataset and 67.96% accuracy achieved for the challenging IDRID dataset, which demonstrates the superior performance of our proposed method.

CANet: Cross-Disease Attention Network for Joint Diabetic Retinopathy and Diabetic Macular Edema Grading

Diabetic retinopathy (DR) and diabetic macular edema (DME) are the leading causes of permanent blindness in the working-age population. Automatic grading of DR and DME helps ophthalmologists design tailored treatments to patients, thus is of vital importance in the clinical practice. However, prior works either grade DR or DME, and ignore the correlation between DR and its complication, i.e., DME. Moreover, the location information, e.g., macula and soft hard exhaust annotations, are widely used as a prior for grading. Such annotations are costly to obtain, hence it is desirable to develop automatic grading methods with only image-level supervision. In this article, we present a novel cross-disease attention network (CANet) to jointly grade DR and DME by exploring the internal relationship between the diseases with only image-level supervision. Our key contributions include the disease-specific attention module to selectively learn useful features for individual diseases, and the disease-dependent attention module to further capture the internal relationship between the two diseases. We integrate these two attention modules in a deep network to produce disease-specific and disease-dependent features, and to maximize the overall performance jointly for grading DR and DME. We evaluate our network on two public benchmark datasets, i.e., ISBI 2018 IDRiD challenge dataset and Messidor dataset. Our method achieves the best result on the ISBI 2018 IDRiD challenge dataset and outperforms other methods on the Messidor dataset. Our code is publicly available at https://github.com/xmengli999/CANet.

Microaneurysms detection in color fundus images using machine learning based on directional local contrast

Background

As one of the major complications of diabetes, diabetic retinopathy (DR) is a leading cause of visual impairment and blindness due to delayed diagnosis and intervention. Microaneurysms appear as the earliest symptom of DR. Accurate and reliable detection of microaneurysms in color fundus images has great importance for DR screening.

Methods

A microaneurysms' detection method using machine learning based on directional local contrast (DLC) is proposed for the early diagnosis of DR. First, blood vessels were enhanced and segmented using improved enhancement function based on analyzing eigenvalues of Hessian matrix. Next, with blood vessels excluded, microaneurysm candidate regions were obtained using shape characteristics and connected components analysis. After image segmented to patches, the features of each microaneurysm candidate patch were extracted, and each candidate patch was classified into microaneurysm or non-microaneurysm. The main contributions of our study are (1) making use of directional local contrast in microaneurysms' detection for the first time, which does make sense for better microaneurysms' classification. (2) Applying three different machine learning techniques for classification and comparing their performance for microaneurysms' detection. The proposed algorithm was trained and tested on e-ophtha MA database, and further tested on another independent DIARETDB1 database. Results of microaneurysms' detection on the two databases were evaluated on lesion level and compared with existing algorithms.

Results

The proposed method has achieved better performance compared with existing algorithms on accuracy and computation time. On e-ophtha MA and DIARETDB1 databases, the area under curve (AUC) of receiver operating characteristic (ROC) curve was 0.87 and 0.86, respectively. The free-response ROC (FROC) score on the two databases was 0.374 and 0.210, respectively. The computation time per image with resolution of 2544×1969, 1400×960 and 1500×1152 is 29 s, 3 s and 2.6 s, respectively.

Conclusions

The proposed method using machine learning based on directional local contrast of image patches can effectively detect microaneurysms in color fundus images and provide an effective scientific basis for early clinical DR diagnosis.

Diabetic retinopathy detection using red lesion localization and convolutional neural networks

Detecting the early signs of diabetic retinopathy (DR) is essential, as timely treatment might reduce or even prevent vision loss. Moreover, automatically localizing the regions of the retinal image that might contain lesions can favorably assist specialists in the task of detection. In this study, we designed a lesion localization model using a deep network patch-based approach. Our goal was to reduce the complexity of the model while improving its performance. For this purpose, we designed an efficient procedure (including two convolutional neural network models) for selecting the training patches, such that the challenging examples would be given special attention during the training process. Using the labeling of the region, a DR decision can be given to the initial image, without the need for special training. The model is trained on the Standard Diabetic Retinopathy Database, Calibration Level 1 (DIARETDB1) database and is tested on several databases (including Messidor) without any further adaptation. It reaches an area under the receiver operating characteristic curve of 0.912-95%CI(0.897-0.928) for DR screening, and a sensitivity of 0.940-95%CI(0.921-0.959). These values are competitive with other state-of-the-art approaches.

IDRiD: Diabetic Retinopathy - Segmentation and Grading Challenge

Diabetic Retinopathy (DR) is the most common cause of avoidable vision loss, predominantly affecting the working-age population across the globe. Screening for DR, coupled with timely consultation and treatment, is a globally trusted policy to avoid vision loss. However, implementation of DR screening programs is challenging due to the scarcity of medical professionals able to screen a growing global diabetic population at risk for DR. Computer-aided disease diagnosis in retinal image analysis could provide a sustainable approach for such large-scale screening effort. The recent scientific advances in computing capacity and machine learning approaches provide an avenue for biomedical scientists to reach this goal. Aiming to advance the state-of-the-art in automatic DR diagnosis, a grand challenge on "Diabetic Retinopathy - Segmentation and Grading" was organized in conjunction with the IEEE International Symposium on Biomedical Imaging (ISBI - 2018). In this paper, we report the set-up and results of this challenge that is primarily based on Indian Diabetic Retinopathy Image Dataset (IDRiD). There were three principal sub-challenges: lesion segmentation, disease severity grading, and localization of retinal landmarks and segmentation. These multiple tasks in this challenge allow to test the generalizability of algorithms, and this is what makes it different from existing ones. It received a positive response from the scientific community with 148 submissions from 495 registrations effectively entered in this challenge. This paper outlines the challenge, its organization, the dataset used, evaluation methods and results of top-performing participating solutions. The top-performing approaches utilized a blend of clinical information, data augmentation, and an ensemble of models. These findings have the potential to enable new developments in retinal image analysis and image-based DR screening in particular.

Automated retinal lesion detection via image saliency analysis

BACKGROUND AND OBJECTIVE

The detection of abnormalities such as lesions or leakage from retinal images is an important health informatics task for automated early diagnosis of diabetic and malarial retinopathy or other eye diseases, in order to prevent blindness and common systematic conditions. In this work, we propose a novel retinal lesion detection method by adapting the concepts of saliency.

METHODS

Retinal images are first segmented as superpixels, two new saliency feature representations: uniqueness and compactness, are then derived to represent the superpixels. The pixel level saliency is then estimated from these superpixel saliency values via a bilateral filter. These extracted saliency features form a matrix for low-rank analysis to achieve saliency detection. The precise contour of a lesion is finally extracted from the generated saliency map after removing confounding structures such as blood vessels, the optic disk, and the fovea. The main novelty of this method is that it is an effective tool for detecting different abnormalities at the pixel level from different modalities of retinal images, without the need to tune parameters.

RESULTS

To evaluate its effectiveness, we have applied our method to seven public datasets of diabetic and malarial retinopathy with four different types of lesions: exudate, hemorrhage, microaneurysms, and leakage. The evaluation was undertaken at the pixel level, lesion level, or image level according to ground truth availability in these datasets.

CONCLUSIONS

The experimental results show that the proposed method outperforms existing state-of-the-art ones in applicability, effectiveness, and accuracy.

A Novel Weakly Supervised Multitask Architecture for Retinal Lesions Segmentation on Fundus Images

Obtaining the complete segmentation map of retinal lesions is the first step toward an automated diagnosis tool for retinopathy that is interpretable in its decision-making. However, the limited availability of ground truth lesion detection maps at a pixel level restricts the ability of deep segmentation neural networks to generalize over large databases. In this paper, we propose a novel approach for training a convolutional multi-task architecture with supervised learning and reinforcing it with weakly supervised learning. The architecture is simultaneously trained for three tasks: segmentation of red lesions and of bright lesions, those two tasks done concurrently with lesion detection. In addition, we propose and discuss the advantages of a new preprocessing method that guarantees the color consistency between the raw image and its enhanced version. Our complete system produces segmentations of both red and bright lesions. The method is validated at the pixel level and per-image using four databases and a cross-validation strategy. When evaluated on the task of screening for the presence or absence of lesions on the Messidor image set, the proposed method achieves an area under the ROC curve of 0.839, comparable with the state-of-the-art.

An Intelligent Segmentation and Diagnosis Method for Diabetic Retinopathy Based on Improved U-NET Network

Due to insufficient samples, the generalization performance of deep network is insufficient. In order to solve this problem, an improved U-net based image automatic segmentation and diagnosis algorithm was proposed, in which the max-pooling operation in original U-net model was replaced by the convolution operation to keep more feature information. Firstly, the regions of 128×128 were extracted from all slices of the patients as data samples. Secondly, the patient samples were divided into training sample set and testing sample set, and data augmentation was performed on the training samples. Finally, all the training samples were adopted to train the model. Compared with Fully Convolutional Network (FCN) model and max-pooling based U-net model, DSC and CR coefficients of the proposed method achieve the best results, while PM coefficient is 2.55 percentage lower than the maximum value in the two comparison models, and Average Symmetric Surface Distance is slightly higher than the minimum value of the two comparison models by 0.004. The experimental results show that the proposed model can achieve good segmentation and diagnosis results.

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.

A review on computer-aided recent developments for automatic detection of diabetic retinopathy

Diabetic retinopathy is a serious microvascular disorder that might result in loss of vision and blindness. It seriously damages the retinal blood vessels and reduces the light-sensitive inner layer of the eye. Due to the manual inspection of retinal fundus images on diabetic retinopathy to detect the morphological abnormalities in Microaneurysms (MAs), Exudates (EXs), Haemorrhages (HMs), and Inter retinal microvascular abnormalities (IRMA) is very difficult and time consuming process. In order to avoid this, the regular follow-up screening process, and early automatic Diabetic Retinopathy detection are necessary. This paper discusses various methods of analysing automatic retinopathy detection and classification of different grading based on the severity levels. In addition, retinal blood vessel detection techniques are also discussed for the ultimate detection and diagnostic procedure of proliferative diabetic retinopathy. Furthermore, the paper elaborately discussed the systematic review accessed by authors on various publicly available databases collected from different medical sources. In the survey, meta-analysis of several methods for diabetic feature extraction, segmentation and various types of classifiers have been used to evaluate the system performance metrics for the diagnosis of DR. This survey will be helpful for the technical persons and researchers who want to focus on enhancing the diagnosis of a system that would be more powerful in real life.

Weakly Supervised Lesion Detection From Fundus Images

Early diagnosis and continuous monitoring of patients suffering from eye diseases have been major concerns in the computer-aided detection techniques. Detecting one or several specific types of retinal lesions has made a significant breakthrough in computer-aided screen in the past few decades. However, due to the variety of retinal lesions and complex normal anatomical structures, automatic detection of lesions with unknown and diverse types from a retina remains a challenging task. In this paper, a weakly supervised method, requiring only a series of normal and abnormal retinal images without need to specifically annotate their locations and types, is proposed for this task. Specifically, a fundus image is understood as a superposition of background, blood vessels, and background noise (lesions included for abnormal images). Background is formulated as a low-rank structure after a series of simple preprocessing steps, including spatial alignment, color normalization, and blood vessels removal. Background noise is regarded as stochastic variable and modeled through Gaussian for normal images and mixture of Gaussian for abnormal images, respectively. The proposed method encodes both the background knowledge of fundus images and the background noise into one unique model, and corporately optimizes the model using normal and abnormal images, which fully depict the low-rank subspace of the background and distinguish the lesions from the background noise in abnormal fundus images. Experimental results demonstrate that the proposed method is of fine arts accuracy and outperforms the previous related methods.

Secondary Observer System for Detection of Microaneurysms in Fundus Images Using Texture Descriptors

The increase of diabetic retinopathy patients and diabetic mellitus worldwide yields lot of challenges to ophthalmologists in the screening of diabetic retinopathy. Different signs of diabetic retinopathy were identified in retinal images taken through fundus photography. Among these stages, the early stage of diabetic retinopathy termed as microaneurysms plays a vital role in diabetic retinopathy patients. To assist the ophthalmologists, and to avoid vision loss among diabetic retinopathy patients, a computer-aided diagnosis is essential that can be used as a second opinion while screening diabetic retinopathy. On this vision, a new methodology is proposed to detect the microaneurysms and non-microaneurysms through the stages of image pre-processing, candidate extraction, feature extraction, and classification. The feature extractor, generalized rotational invariant local binary pattern, contributes in extracting the texture-based features of microaneurysms. As a result, our proposed system achieved a free-response receiver operating characteristic score of 0.421 with Retinopathy Online Challenge database.

Entropy Rate Superpixel Classification for Automatic Red Lesion Detection in Fundus Images

Diabetic retinopathy (DR) is the main cause of blindness in the working-age population in developed countries. Digital color fundus images can be analyzed to detect lesions for large-scale screening. Thereby, automated systems can be helpful in the diagnosis of this disease. The aim of this study was to develop a method to automatically detect red lesions (RLs) in retinal images, including hemorrhages and microaneurysms. These signs are the earliest indicators of DR. Firstly, we performed a novel preprocessing stage to normalize the inter-image and intra-image appearance and enhance the retinal structures. Secondly, the Entropy Rate Superpixel method was used to segment the potential RL candidates. Then, we reduced superpixel candidates by combining inaccurately fragmented regions within structures. Finally, we classified the superpixels using a multilayer perceptron neural network. The used database contained 564 fundus images. The DB was randomly divided into a training set and a test set. Results on the test set were measured using two different criteria. With a pixel-based criterion, we obtained a sensitivity of 81.43% and a positive predictive value of 86.59%. Using an image-based criterion, we reached 84.04% sensitivity, 85.00% specificity and 84.45% accuracy. The algorithm was also evaluated on the DiaretDB1 database. The proposed method could help specialists in the detection of RLs in diabetic patients.

Validation of Multicolor Imaging of Diabetic Retinopathy Lesions Vis a Vis Conventional Color Fundus Photographs

BACKGROUND AND OBJECTIVE

To analyze the visibility of various diabetic retinopathy lesions in multicolor imaging (MCI) and compare them to corresponding color fundus photography (CFP).

PATIENTS AND METHODS

Retrospective review of 130 eyes of 65 consecutive patients with diabetic retinopathy who underwent multicolor confocal scanning laser ophthalmoscopy and CFP.

RESULTS

Hard exudates (Hex) were seen in 74 eyes (71.2%). In all 74 eyes, Hex were visible on both CFP and MCI. Among other color channels, Hex were picked up most in green reflectance (GR) images in 73 eyes (70.2%). Cotton-wool spots (CWS) were picked up in 29 eyes (27.9%) on MCI and in 27 eyes (26%) on CFP. In both GR and blue reflectance (BR) imaging, they were equally picked up in 29 eyes (27.9%). Retinal hemorrhages were picked up in 83 eyes (79.8%) on MCI and in 82 eyes (72.8%) on CFP. Among other channels, they were picked up most in GR images in 81 (77.9%) eyes. Hex, CWS, and hemorrhages were seen better on MCI and in GR images as compared to CFP, BR, and infrared imaging, respectively. With CFP as the comparator, the sensitivity and specificity of MCI to detect of these lesions were more than 90%.

CONCLUSIONS

The authors' pilot study validates the efficacy of MCI in picking up lesions of DR vis a vis CFP. MCI has potential to replace CFP in clinical and DR screening setting. [Ophthalmic Surg Lasers Imaging Retina. 2019;50:8-15.].

Fundus Image Classification Using VGG-19 Architecture with PCA and SVD

Automated medical image analysis is an emerging field of research that identifies the disease with the help of imaging technology. Diabetic retinopathy (DR) is a retinal disease that is diagnosed in diabetic patients. Deep neural network (DNN) is widely used to classify diabetic retinopathy from fundus images collected from suspected persons. The proposed DR classification system achieves a symmetrically optimized solution through the combination of a Gaussian mixture model (GMM), visual geometry group network (VGGNet), singular value decomposition (SVD) and principle component analysis (PCA), and softmax, for region segmentation, high dimensional feature extraction, feature selection and fundus image classification, respectively. The experiments were performed using a standard KAGGLE dataset containing 35,126 images. The proposed VGG-19 DNN based DR model outperformed the AlexNet and spatial invariant feature transform (SIFT) in terms of classification accuracy and computational time. Utilization of PCA and SVD feature selection with fully connected (FC) layers demonstrated the classification accuracies of 92.21%, 98.34%, 97.96%, and 98.13% for FC7-PCA, FC7-SVD, FC8-PCA, and FC8-SVD, respectively.

Transforming Retinal Photographs to Entropy Images in Deep Learning to Improve Automated Detection for Diabetic Retinopathy

Entropy images, representing the complexity of original fundus photographs, may strengthen the contrast between diabetic retinopathy (DR) lesions and unaffected areas. The aim of this study is to compare the detection performance for severe DR between original fundus photographs and entropy images by deep learning. A sample of 21,123 interpretable fundus photographs obtained from a publicly available data set was expanded to 33,000 images by rotating and flipping. All photographs were transformed into entropy images using block size 9 and downsized to a standard resolution of 100 × 100 pixels. The stages of DR are classified into 5 grades based on the International Clinical Diabetic Retinopathy Disease Severity Scale: Grade 0 (no DR), Grade 1 (mild nonproliferative DR), Grade 2 (moderate nonproliferative DR), Grade 3 (severe nonproliferative DR), and Grade 4 (proliferative DR). Of these 33,000 photographs, 30,000 images were randomly selected as the training set, and the remaining 3,000 images were used as the testing set. Both the original fundus photographs and the entropy images were used as the inputs of convolutional neural network (CNN), and the results of detecting referable DR (Grades 2-4) as the outputs from the two data sets were compared. The detection accuracy, sensitivity, and specificity of using the original fundus photographs data set were 81.80%, 68.36%, 89.87%, respectively, for the entropy images data set, and the figures significantly increased to 86.10%, 73.24%, and 93.81%, respectively (all p values <0.001). The entropy image quantifies the amount of information in the fundus photograph and efficiently accelerates the generating of feature maps in the CNN. The research results draw the conclusion that transformed entropy imaging of fundus photographs can increase the machinery detection accuracy, sensitivity, and specificity of referable DR for the deep learning-based system.

Retinal Microaneurysms Detection Using Local Convergence Index Features

Retinal microaneurysms (MAs) are the earliest clinical sign of diabetic retinopathy disease. Detection of MAs is crucial for the early diagnosis of diabetic retinopathy and prevention of blindness. In this paper, a novel and reliable method for automatic detection of MAs in retinal images is proposed. In the first stage of the proposed method, several preliminary microaneurysm candidates are extracted using a gradient weighting technique and an iterative thresholding approach. In the next stage, in addition to intensity and shape descriptors, a new set of features based on local convergence index filters is extracted for each candidate. Finally, the collective set of features is fed to a hybrid sampling/boosting classifier to discriminate the MAs from non-MAs candidates. The method is evaluated on images with different resolutions and modalities (color and scanning laser ophthalmoscope) using six publicly available data sets including the retinopathy online challenges (ROC) data set. The proposed method achieves an average sensitivity score of 0.471 on the ROC data set outperforming state-of-the-art approaches in an extensive comparison. The experimental results on the other five data sets demonstrate the effectiveness and robustness of the proposed MAs detection method regardless of different image resolutions and modalities.

Retinal hemorrhage detection by rule-based and machine learning approach

Robust detection of hemorrhages (HMs) in color fundus image is important in an automatic diabetic retinopathy grading system. Detection of the hemorrhages that are close to or connected with retinal blood vessels was found to be challenge. However, most methods didn't put research on it, even some of them mentioned this issue. In this paper, we proposed a novel hemorrhage detection method based on rule-based and machine learning methods. We focused on the improvement of detection of the hemorrhages that are close to or connected with retinal blood vessels, besides detecting the independent hemorrhage regions. A preliminary test for detecting HM presence was conducted on the images from two databases. We achieved sensitivity and specificity of 93.3% and 88% as well as 91.9% and 85.6% on the two datasets.

Particle swarm optimization method for small retinal vessels detection on multiresolution fundus images

Retinal vessel segmentation plays an important role in the diagnosis of eye diseases and is considered as one of the most challenging tasks in computer-aided diagnosis (CAD) systems. The main goal of this study was to propose a method for blood-vessel segmentation that could deal with the problem of detecting vessels of varying diameters in high- and low-resolution fundus images. We proposed to use the particle swarm optimization (PSO) algorithm to improve the multiscale line detection (MSLD) method. The PSO algorithm was applied to find the best arrangement of scales in the MSLD method and to handle the problem of multiscale response recombination. The performance of the proposed method was evaluated on two low-resolution (DRIVE and STARE) and one high-resolution fundus (HRF) image datasets. The data include healthy (H) and diabetic retinopathy (DR) cases. The proposed approach improved the sensitivity rate against the MSLD by 4.7% for the DRIVE dataset and by 1.8% for the STARE dataset. For the high-resolution dataset, the proposed approach achieved 87.09% sensitivity rate, whereas the MSLD method achieves 82.58% sensitivity rate at the same specificity level. When only the smallest vessels were considered, the proposed approach improved the sensitivity rate by 11.02% and by 4.42% for the healthy and the diabetic cases, respectively. Integrating the proposed method in a comprehensive CAD system for DR screening would allow the reduction of false positives due to missed small vessels, misclassified as red lesions.

Microaneurysm detection using fully convolutional neural networks

BACKROUND AND OBJECTIVES

Diabetic retinopathy is a microvascular complication of diabetes that can lead to sight loss if treated not early enough. Microaneurysms are the earliest clinical signs of diabetic retinopathy. This paper presents an automatic method for detecting microaneurysms in fundus photographies.

METHODS

A novel patch-based fully convolutional neural network with batch normalization layers and Dice loss function is proposed. Compared to other methods that require up to five processing stages, it requires only three. Furthermore, to the best of the authors' knowledge, this is the first paper that shows how to successfully transfer knowledge between datasets in the microaneurysm detection domain.

RESULTS

The proposed method was evaluated using three publicly available and widely used datasets: E-Ophtha, DIARETDB1, and ROC. It achieved better results than state-of-the-art methods using the FROC metric. The proposed algorithm accomplished highest sensitivities for low false positive rates, which is particularly important for screening purposes.

CONCLUSIONS

Performance, simplicity, and robustness of the proposed method demonstrates its suitability for diabetic retinopathy screening applications.

Clinical Report Guided Retinal Microaneurysm Detection With Multi-Sieving Deep Learning

Timely detection and treatment of microaneurysms is a critical step to prevent the development of vision-threatening eye diseases such as diabetic retinopathy. However, detecting microaneurysms in fundus images is a highly challenging task due to the low image contrast, misleading cues of other red lesions, and the large variation of imaging conditions. Existing methods tend to fail in face of the large intra-class variation and small inter-class variations for microaneurysm detection in fundus images. Recently, hybrid text/image mining computer-aided diagnosis systems have emerged to offer a promise of bridging the semantic gap between images and diagnostic information. In this paper, we focus on developing an interleaved deep mining technique to cope intelligently with the unbalanced microaneurysm detection problem. Specifically, we present a clinical report guided multi-sieving convolutional neural network, which leverages a small amount of supervised information in clinical reports to identify the potential microaneurysm regions via the image-to-text mapping in the feature space. These potential microaneurysm regions are then interleaved with fundus image information for multi-sieving deep mining in a highly unbalanced classification problem. Critically, the clinical reports are employed to bridge the semantic gap between low-level image features and high-level diagnostic information. We build an efficient microaneurysm detection framework based on the hybrid text/image interleaving and validate its performance on challenging clinical data sets acquired from diabetic retinopathy patients. Extensive evaluations are carried out in terms of fundus detection and classification. Experimental results show that our framework achieves 99.7% precision and 87.8% recall, comparing favorably with the state-of-the-art algorithms. Integration of expert domain knowledge and image information demonstrates the feasibility of reducing the difficulty of training classifiers under extremely unbalanced data distributions.

An ensemble deep learning based approach for red lesion detection in fundus images

BACKGROUND AND OBJECTIVES

Diabetic retinopathy (DR) is one of the leading causes of preventable blindness in the world. Its earliest sign are red lesions, a general term that groups both microaneurysms (MAs) and hemorrhages (HEs). In daily clinical practice, these lesions are manually detected by physicians using fundus photographs. However, this task is tedious and time consuming, and requires an intensive effort due to the small size of the lesions and their lack of contrast. Computer-assisted diagnosis of DR based on red lesion detection is being actively explored due to its improvement effects both in clinicians consistency and accuracy. Moreover, it provides comprehensive feedback that is easy to assess by the physicians. Several methods for detecting red lesions have been proposed in the literature, most of them based on characterizing lesion candidates using hand crafted features, and classifying them into true or false positive detections. Deep learning based approaches, by contrast, are scarce in this domain due to the high expense of annotating the lesions manually.

METHODS

In this paper we propose a novel method for red lesion detection based on combining both deep learned and domain knowledge. Features learned by a convolutional neural network (CNN) are augmented by incorporating hand crafted features. Such ensemble vector of descriptors is used afterwards to identify true lesion candidates using a Random Forest classifier.

RESULTS

We empirically observed that combining both sources of information significantly improve results with respect to using each approach separately. Furthermore, our method reported the highest performance on a per-lesion basis on DIARETDB1 and e-ophtha, and for screening and need for referral on MESSIDOR compared to a second human expert.

CONCLUSIONS

Results highlight the fact that integrating manually engineered approaches with deep learned features is relevant to improve results when the networks are trained from lesion-level annotated data. An open source implementation of our system is publicly available at https://github.com/ignaciorlando/red-lesion-detection.

A Machine Learning Ensemble Classifier for Early Prediction of Diabetic Retinopathy

The main complication of diabetes is Diabetic retinopathy (DR), retinal vascular disease and it leads to the blindness. Regular screening for early DR disease detection is considered as an intensive labor and resource oriented task. Therefore, automatic detection of DR diseases is performed only by using the computational technique is the great solution. An automatic method is more reliable to determine the presence of an abnormality in Fundus images (FI) but, the classification process is poorly performed. Recently, few research works have been designed for analyzing texture discrimination capacity in FI to distinguish the healthy images. However, the feature extraction (FE) process was not performed well, due to the high dimensionality. Therefore, to identify retinal features for DR disease diagnosis and early detection using Machine Learning and Ensemble Classification method, called, Machine Learning Bagging Ensemble Classifier (ML-BEC) is designed. The ML-BEC method comprises of two stages. The first stage in ML-BEC method comprises extraction of the candidate objects from Retinal Images (RI). The candidate objects or the features for DR disease diagnosis include blood vessels, optic nerve, neural tissue, neuroretinal rim, optic disc size, thickness and variance. These features are initially extracted by applying Machine Learning technique called, t-distributed Stochastic Neighbor Embedding (t-SNE). Besides, t-SNE generates a probability distribution across high-dimensional images where the images are separated into similar and dissimilar pairs. Then, t-SNE describes a similar probability distribution across the points in the low-dimensional map. This lessens the Kullback-Leibler divergence among two distributions regarding the locations of the points on the map. The second stage comprises of application of ensemble classifiers to the extracted features for providing accurate analysis of digital FI using machine learning. In this stage, an automatic detection of DR screening system using Bagging Ensemble Classifier (BEC) is investigated. With the help of voting the process in ML-BEC, bagging minimizes the error due to variance of the base classifier. With the publicly available retinal image databases, our classifier is trained with 25% of RI. Results show that the ensemble classifier can achieve better classification accuracy (CA) than single classification models. Empirical experiments suggest that the machine learning-based ensemble classifier is efficient for further reducing DR classification time (CT).

Deep-learning-based automatic computer-aided diagnosis system for diabetic retinopathy

The high-pace rise in advanced computing and imaging systems has given rise to a new research dimension called computer-aided diagnosis (CAD) system for various biomedical purposes. CAD-based diabetic retinopathy (DR) can be of paramount significance to enable early disease detection and diagnosis decision. Considering the robustness of deep neural networks (DNNs) to solve highly intricate classification problems, in this paper, AlexNet DNN, which functions on the basis of convolutional neural network (CNN), has been applied to enable an optimal DR CAD solution. The DR model applies a multilevel optimization measure that incorporates pre-processing, adaptive-learning-based Gaussian mixture model (GMM)-based concept region segmentation, connected component-analysis-based region of interest (ROI) localization, AlexNet DNN-based highly dimensional feature extraction, principle component analysis (PCA)- and linear discriminant analysis (LDA)-based feature selection, and support-vector-machine-based classification to ensure optimal five-class DR classification. The simulation results with standard KAGGLE fundus datasets reveal that the proposed AlexNet DNN-based DR exhibits a better performance with LDA feature selection, where it exhibits a DR classification accuracy of 97.93% with FC7 features, whereas with PCA, it shows 95.26% accuracy. Comparative analysis with spatial invariant feature transform (SIFT) technique (accuracy-94.40%) based DR feature extraction also confirms that AlexNet DNN-based DR outperforms SIFT-based DR.