Search

Abstract Early detection and correct identification of the optic disc (OD) on scanned retinal images are significant for diagnosing and treating several ophthalmic conditions, including glaucoma and diabetic retinopathy. Conventional methods for detecting the OD often struggle with processing retinal images due to noise, changes in illumination, and complex overlapping images. This study presents the development of effective and accurate fixation of the optic disc using the Bitterling Fish Optimization (BFO) algorithm, which enhances the processes of OD imaging in speed and precision. The proposed method begins with image enhancement and noise suppression for preprocessing, followed by applying the BFO algorithm to locate and delineate the OD region. The performance evaluation of the algorithm was conducted within several public domain retinal images, including DRIVE, STARE, ORIGA, DRISHTI-GS, DiaRetDB0, and DiaRetDB1 datasets about some internal metrics: sensitivity (SE), specificity (SP), accuracy (ACC), DICE overlap coefficient, overlap and time of processing respectively. The technique based on BFO provided better results, with 99.33%, 99.94%, and 98.22% accuracy achieved for OD in DRIVE, DRISHTI-GS, and DiaRetDB 1, respectively. The approach also demonstrated high overlaps and good DICE results, with a DICE coefficient of 0.9501 for the DRISHTI-GS database. On average, the processing time per image was less than 2.5 s, proving the approach’s efficiency in computations. The BFO approach has demonstrated its effectiveness and scalability in detecting optic discs in retinal images in an automated manner. It showed impressive performance levels in terms of computation time and accuracy and was variation resistant irrespective of the quality of the image and the pathology present on it. This method holds significant potential for clinical use, providing a meaningful way of diagnosing and managing ocular disease at an early stage.

One of the common eye conditions affecting patients with diabetes is diabetic retinopathy (DR). It is characterised by the progressive impairment to the blood vessels with the increase of glucose level in the blood. The grading efficiency still finds challenging because of the existence of intra-class variations and imbalanced data distributions on the retinal images. Traditional machine learning techniques utilise hand-engineered features for classification of the affected retinal images. As convolutional neural network produces better image classification accuracy in many medical images, this work utilises the CNN-based feature extraction method. This feature has been used to build Gaussian mixture model (GMM) for each class that maps the CNN features to log-likelihood dimensional vector spaces. Since the Gaussian mixture model can be realised as a mixture of both parametric and nonparametric density models and has their flexibility in capturing different data distributions, probabilistic outputs, interpretability, efficient parameter estimation, and robustness to outliers, the proposed model aimed to obtain and provide a smooth approximation of the underlying distribution of features for training the model. Then these vector spaces are trained by the SVM classifier. Experimental results illustrate the efficacy of the proposed model with accuracy 86.3% and 89.1%, respectively. [ABSTRACT FROM AUTHOR]

Background: Uncorrected refractive error is a major cause of vision impairment worldwide and its increasing prevalent necessitates effective screening and management strategies. Meanwhile, deep learning, a subset of Artificial Intelligence, has significantly advanced ophthalmological diagnostics by automating tasks that required extensive clinical expertise. Although recent studies have investigated the use of deep learning models for refractive power detection through various imaging techniques, a comprehensive systematic review on this topic is has yet be done. This review aims to summarise and evaluate the performance of ocular image-based deep learning models in predicting refractive errors. Main text: We search on three databases (PubMed, Scopus, Web of Science) up till June 2023, focusing on deep learning applications in detecting refractive error from ocular images. We included studies that had reported refractive error outcomes, regardless of publication years. We systematically extracted and evaluated the continuous outcomes (sphere, SE, cylinder) and categorical outcomes (myopia), ground truth measurements, ocular imaging modalities, deep learning models, and performance metrics, adhering to PRISMA guidelines. Nine studies were identified and categorised into three groups: retinal photo-based (n ​= ​5), OCT-based (n ​= ​1), and external ocular photo-based (n ​= ​3).For high myopia prediction, retinal photo-based models achieved AUC between 0.91 and 0.98, sensitivity levels between 85.10% and 97.80%, and specificity levels between 76.40% and 94.50%. For continuous prediction, retinal photo-based models reported MAE ranging from 0.31D to 2.19D, and R2 between 0.05 and 0.96. The OCT-based model achieved an AUC of 0.79–0.81, sensitivity of 82.30% and 87.20% and specificity of 61.70%–68.90%. For external ocular photo-based models, the AUC ranged from 0.91 to 0.99, sensitivity of 81.13%–84.00% and specificity of 74.00%–86.42%, MAE ranges from 0.07D to 0.18D and accuracy ranges from 81.60% to 96.70%. The reported papers collectively showed promising performances, in particular the retinal photo-based and external eye photo -based DL models. Conclusions: The integration of deep learning model and ocular imaging for refractive error detection appear promising. However, their real-world clinical utility in current screening workflow have yet been evaluated and would require thoughtful consideration in design and implementation.

The evaluation of Generative Adversarial Networks in the medical domain has shown significant potential for various applications, including adversarial machine learning on medical imaging. This study specifically focuses on assessing the resilience of Convolutional Neural Networks in differentiating between real and Generative Adversarial Network-generated retinal images. The main contributions of this research include the training and testing of Convolutional Neural Networks to evaluate their ability to distinguish real images from synthetic ones. By identifying networks with optimal performances, the study ensures the development of better models for diagnostic classification, enhancing generalization and resilience to adversarial images. Overall, the aim of the study is to demonstrate that the application of Generative Adversarial Networks can improve the resilience of the tested networks, resulting in better classifiers for retinal images. In particular, a network developed by authors, i.e., Standard_CNN, reports the best performance with accuracy equal to 1. [ABSTRACT FROM AUTHOR]

Retinal vessel segmentation plays a vital role in the clinical diagnosis of ophthalmic diseases. Despite convolutional neural networks (CNNs) excelling in this task, challenges persist, such as restricted receptive fields and information loss from downsampling. To address these issues, we propose a new multi-fusion network with grouped attention (MAG-Net). First, we introduce a hybrid convolutional fusion module instead of the original encoding block to learn more feature information by expanding the receptive field. Additionally, the grouped attention enhancement module uses high-level features to guide low-level features and facilitates detailed information transmission through skip connections. Finally, the multi-scale feature fusion module aggregates features at different scales, effectively reducing information loss during decoder upsampling. To evaluate the performance of the MAG-Net, we conducted experiments on three widely used retinal datasets: DRIVE, CHASE and STARE. The results demonstrate remarkable segmentation accuracy, specificity and Dice coefficients. Specifically, the MAG-Net achieved segmentation accuracy values of 0.9708, 0.9773 and 0.9743, specificity values of 0.9836, 0.9875 and 0.9906 and Dice coefficients of 0.8576, 0.8069 and 0.8228, respectively. The experimental results demonstrate that our method outperforms existing segmentation methods exhibiting superior performance and segmentation outcomes.

Multi-modal retinal image registration plays an important role in the ophthalmological diagnosis process. The conventional methods lack robustness in aligning multi-modal images of various imaging qualities. Deep-learning methods have not been widely developed for this task, especially for the coarse-to-fine registration pipeline. To handle this task, we propose a two-step method based on deep convolutional networks, including a coarse alignment step and a fine alignment step. In the coarse alignment step, a global registration matrix is estimated by three sequentially connected networks for vessel segmentation, feature detection and description, and outlier rejection, respectively. In the fine alignment step, a deformable registration network is set up to find pixel-wise correspondence between a target image and a coarsely aligned image from the previous step to further improve the alignment accuracy. Particularly, an unsupervised learning framework is proposed to handle the difficulties of inconsistent modalities and lack of labeled training data for the fine alignment step. The proposed framework first changes multi-modal images into a same modality through modality transformers, and then adopts photometric consistency loss and smoothness loss to train the deformable registration network. The experimental results show that the proposed method achieves state-of-the-art results in Dice metrics and is more robust in challenging cases.

Early detection of diabetic retinopathy (DR) is critical in preventing vision loss. However, building accurate Artificial intelligence (AI) models for multiple classes, including early-stage (Class-1) detection, is challenging due to limited and imbalanced medical datasets. The availability of such datasets is restricted due to ethical and privacy concerns. Traditional ensemble models also struggle with raw medical images, further complicating the issue as they require structured data. This study presents a novel deep learning-based ensemble model (EM) designed for multiple and specifically for precise early stage (Class 1) DR classification. The EM uses eight diverse Convolutional Neural Networks (CNNs) with carefully crafted strategies to enhance diversity. Data augmentation and generation techniques address imbalanced data through data diversity, while parameter and architectural diver-sity within CNNs-based EM maximize predictive performance. Evaluation on the publicly available Kaggle APTOS DR dataset demonstrates significant improvement over individual models and existing approaches. The proposed EM achieves multi-class accuracy (93.00 %), precision (93.00 %), sensitivity (98.00 %), and specificity (99.00 %). This research highlights the effectiveness of diversified CNNs ensembles in overcoming challenges posed by imbalanced and scarce data for multiple-class DR classification. This approach paves the way for developing robust and accurate AI-powered diagnostic tools for improved diabetic retinopathy screening.

The tortuosity of retinal blood vessels is an important phenomenon, and it can act as a biomarker in the diagnosis of several eye diseases. The study of abnormalities in the tortuosity of retinal arteries and veins provides ophthalmologists with important information for disease diagnosis. Our study aims to compare the tortuosity relation between retinal arteries and veins by quantifying the vessels' tortuosity in the retina using 14 tortuosity measures applied to the AV-classification retinal dataset. Two feature sets are created, one for arteries and the other for veins. The comparison between the tortuosity of arteries and veins is based on a two-sample T-test statistical method, a regression analysis between the quantified tortuosity features, principal component analysis at the dataset level, and the introduction of the arteriovenous length ratios concept to compare the variations in these new ratios to see the tortuosity behavior in each image. The methods' results have shown that the tortuosity of retinal arteries and veins is similar. The result of the two-sample T-test supports the research hypothesis, as the P-value obtained was greater than 0.05. Furthermore, the regression analysis between arteries and veins features showed a high correlation ( r 2 = 89.39% and 89.11%) for arteries and veins, respectively. The study concludes that the retinal vessel type has no statistical significance in the tortuosity calculation results. [ABSTRACT FROM AUTHOR]

Glaucoma stands out as a prevalent ocular ailment in the elderly population, causing substantial harm to the optic nerves and eventual vision impairment. Fundus photography plays a pivotal role in the clinical assessment of glaucoma, facilitating the exploration of associated morphological alterations. Computational algorithms, capable of processing fundus images, have emerged as indispensable tools in this diagnostic domain. Hence, the imperative development of an automated diagnostic system leveraging image processing techniques is underscored. In this study, a novel approach to the segmentation and classification of retinal optic nerve head images is introduced. This method concurrently executes both tasks through a deep learning framework, thereby enhancing the learning speed within the network. The proposed network encompasses approximately 29 million parameters and demonstrates an efficiency of 2.5 seconds for segmenting and classifying retinal images. Central to this strategy is a multi-task deep learning network, harmonizing segmentation and classification processes, and leveraging information from both tasks to optimize learning efficacy. Validation of the proposed method is conducted using the publicly available ORIGA dataset. The attained performance metrics for accuracy, sensitivity, specificity, and F1-score are 99.461, 93.46, 100, and 98.7006, respectively. These results collectively affirm the substantial advancement achieved by the proposed method in comparison to existing methodologies. [ABSTRACT FROM AUTHOR]

Experts require large high-resolution retinal images to detect tiny abnormalities, such as microaneurysms or issues of vascular branches. However, these images often suffer from low quality (e.g., resolution) due to poor imaging device configuration and misoperations. Many works utilized Convolutional Neural Network-based (CNN) methods for image super-resolution. The authors focused on making these models more complex by adding layers and various blocks. It leads to additional computational expenses and obstructs the application in real-life scenarios. Thus, this paper proposes a novel, lightweight, deep-learning super-resolution method for retinal images. It comprises a Vision Transformer (ViT) encoder and a convolutional neural network decoder. To our best knowledge, this is the first attempt to use a transformer-based network to solve the issue of accurate retinal image super-resolution. A progressively growing super-resolution training technique is applied to increase the resolution of images by factors of 2, 4, and 8. The prominent architecture remains constant thanks to the adaptive patch embedding layer, which does not lead to additional computational expense due to increased up-scaling factors. This patch embedding layer includes 2-dimensional convolution with specific values of kernel size and strides that depend on the input shape. This strategy has removed the need to append additional super-resolution blocks to the model. The proposed method has been evaluated through quantitative and qualitative measures. The qualitative analysis also includes vessel segmentation of super-resolved and ground truth images. Experimental results indicate that the proposed method outperforms the current state-of-the-art methods.

Background and purpose: As one common feature of cerebral small vascular disease (cSVD), white matter lesions (WMLs) could lead to reduction in brain function. Using a convenient, cheap, and non-intrusive method to detect WMLs could substantially benefit to patient management in the community screening, especially in the settings of availability or contraindication of magnetic resonance imaging (MRI). Therefore, this study aimed to develop a useful model to incorporate clinical laboratory data and retinal images using deep learning models to predict the severity of WMLs. Methods: Two hundred fifty-nine patients with any kind of neurological diseases were enrolled in our study. Demographic data, retinal images, MRI, and laboratory data were collected for the patients. The patients were assigned to the absent/mild and moderate-severe WMLs groups according to Fazekas scoring system. Retinal images were acquired by fundus photography. A ResNet deep learning framework was used to analyze the retinal images. A clinical-laboratory signature was generated from laboratory data. Two prediction models, a combined model including demographic data, the clinical-laboratory signature, and the retinal images and a clinical model including only demographic data and the clinicallaboratory signature, were developed to predict the severity of WMLs. Results: Approximately one-quarter of the patients (25.6%) had moderate-severe WMLs. The left and right retinal images predicted moderate-severe WMLs with area under the curves (AUCs) of 0.73 and 0.94. The clinical-laboratory signature predicted moderate-severe WMLs with an AUC of 0.73. The combined model showed good performance in predicting moderate-severe WMLs with an AUC of 0.95, while the clinical model predicted moderate-severe WMLs with an AUC of 0.78. Conclusion: Combined with retinal images from conventional fundus photography and clinical laboratory data are reliable and convenient approach to predict the severity of WMLs and are helpful for the management and follow-up of WMLs patients. [ABSTRACT FROM AUTHOR]

Retinal vessel segmentation, skeletonization, and the generation of vessel segments are considered significant steps in any automated system for measuring the vessel biomarkers of several disease diagnoses. Most of the current tortuosity quantification methods rely on precise vascular segmentation and skeletonization of the retinal vessels. Additionally, the existence of a reference dataset for accurate vessel segment images is an essential need for implementing deep learning solutions and an automated system for measuring the vessel biomarkers of several disease diagnoses, especially for optimized quantification of vessel tortuosity or accurate measurement of AV-nicking. This study aimed to present an improved method for skeletonizing and extracting the retinal vessel segments from the 504 images in the AV classification dataset. The study utilized the Six Sigma process capability index, sigma level, and yield to measure the vessels' tortuosity calculation improvement before and after optimizing the extracted vessels. As a result, the study showed that the sigma level for the vessel segment optimization improved from 2.7 to 4.39, the confirming yield improved from 88 percent to 99.77 percent, and the optimized vessel segments of the AV classification dataset retinal images are available in monochrome and colored formats. [ABSTRACT FROM AUTHOR]

The study aimed to apply to Machine Learning (ML) researchers working in image processing and biomedical analysis who play an extensive role in comprehending and performing on complex medical data, eventually improving patient care. Developing a novel ML algorithm specific to Diabetic Retinopathy (DR) is a challenge and need of the hour. Biomedical images include several challenges, including relevant feature selection, class variations, and robust classification. Although the current research in DR has yielded favourable results, several research issues need to be explored. There is a requirement to look at novel pre-processing methods to discard irrelevant features, balance the obtained relevant features, and obtain a robust classification. This is performed using the Steerable Kernalized Partial Derivative and Platt Scale Classifier (SKPD-PSC) method. The novelty of this method relies on the appropriate non-linear classification of exclusive image processing models in harmony with the Platt Scale Classifier (PSC) to improve the accuracy of DR detection. First, a Steerable Filter Kernel Pre-processing (SFKP) model is applied to the Retinal Images (RI) to remove irrelevant and redundant features and extract more meaningful pathological features through Directional Derivatives of Gaussians (DDG). Next, the Partial Derivative Image Localization (PDIL) model is applied to the extracted features to localize candidate features and suppress the background noise. Finally, a Platt Scale Classifier (PSC) is applied to the localized features for robust classification. For the experiments, we used the publicly available DR detection database provided by Standard Diabetic Retinopathy (SDR), called DIARETDB0. A database of 130 image samples has been collected to train and test the ML-based classifiers. Experimental results show that the proposed method that combines the image processing and ML models can attain good detection performance with a high DR detection accuracy rate with minimum time and complexity compared to the state-of-the-art methods. The accuracy and speed of DR detection for numerous types of images will be tested through experimental evaluation. Compared to state-of-the-art methods, the method increases DR detection accuracy by 24% and DR detection time by 37. [ABSTRACT FROM AUTHOR]

Glaucoma is a serious threat and it causes blindness and it ranks third in India. Early identification of glaucoma sickness prevents eye disorders from worsening. Due to the need for early illness detection tools to aid in screening and management, retinal image analysis has attracted keen interest. This article presents an automated glaucoma detection system, which is based on machine learning. The retinal images are denoised and contrast enhanced, followed by which the Optic Disc and Cup are extracted. The Complete Local Binary Pattern (CLBP) and contourlet features are extracted to train the Extreme Learning Machine (ELM) classifier. The ELM differentiates between the glaucomatous and non-glaucomatous images. The experimental findings are evaluated with the existing methods, and it is found that the proposed work is superior in terms of standard performance measures. [ABSTRACT FROM AUTHOR]

The tortuosity of retinal blood vessels is an important phenomenon, and it can act as a biomarker in the diagnosis of several eye diseases. The study of abnormalities in the tortuosity of retinal arteries and veins provides ophthalmologists with important information for disease diagnosis. Our study aims to compare the tortuosity relation between retinal arteries and veins by quantifying the vessels’ tortuosity in the retina using 14 tortuosity measures applied to the AV-classification retinal dataset. Two feature sets are created, one for arteries and the other for veins. The comparison between the tortuosity of arteries and veins is based on a two-sample T-test statistical method, a regression analysis between the quantified tortuosity features, principal component analysis at the dataset level, and the introduction of the arteriovenous length ratios concept to compare the variations in these new ratios to see the tortuosity behavior in each image. The methods’ results have shown that the tortuosity of retinal arteries and veins is similar. The result of the two-sample T-test supports the research hypothesis, as the P-value obtained was greater than 0.05. Furthermore, the regression analysis between arteries and veins features showed a high correlation (r2 = 89.39% and 89.11%) for arteries and veins, respectively. The study concludes that the retinal vessel type has no statistical significance in the tortuosity calculation results.

Background: The aim of this study was to assess the performance of regional graders and artificial intelligence algorithms across retinal cameras with different specifications in classifying an image as gradable and ungradable. Methods: Study subjects were included from a community-based nationwide diabetic retinopathy screening program in Thailand. Various non-mydriatic fundus cameras were used for image acquisition, including Kowa Nonmyd, Kowa Nonmyd α-DⅢ, Kowa Nonmyd 7, Kowa Nonmyd WX, Kowa VX 10 α, Kowa VX 20 and Nidek AFC 210. All retinal photographs were graded by deep learning algorithms and human graders and compared with a standard reference. Results: Images were divided into two categories as gradable and ungradable images. Four thousand eight hundred fifty-two participants with 19,408 fundus images were included, of which 15,351 (79.09%) were gradable images and the remaining 4057 (20.90%) were ungradable images. Conclusions: The deep learning (DL) algorithm demonstrated better sensitivity, specificity and kappa than the human graders for all eight types of non-mydriatic fundus cameras. The deep learning system showed, more consistent diagnostic performance than the human graders across images of varying quality and camera types. [ABSTRACT FROM AUTHOR]

In medical world, Glaucoma is a vision threatening retinal disease. This leads to the research scope of detecting glaucoma at early stages for better treatments. Manual approach for detection by ophthalmologists is tiresome and time-consuming, hence an image processing approach of determining the ratio of optic cup with respect to disc (CDR) is focused. This research work proposes a neutrosophic approach for segmentation by transforming the input retinal images to neutrosophic domain. In this neutrosophic approach, the intensity values are represented as truth, indeterminacy and falsity membership. Next, an intensification operation on the resultant images, followed by score function is done to result in a comprehensive outcome. Finally, the clustering technique IFCM is used for segmentation of the optic cup boundary and the optic disc. Experimental result analysis shows that the effectiveness of the proposed methodology is demonstrated since it provides unbiased results of average accuracy of 92.38% on DRISHTI-GS dataset and 91.67% on RIM-ONE dataset. [ABSTRACT FROM AUTHOR]

Hypertensive retinopathy severity classification is proportionally related to tortuosity severity grading. No tortuosity severity scale enables a computer-aided system to classify the tortuosity severity of a retinal image. This work aimed to introduce a machine learning model that can identify the severity of a retinal image automatically and hence contribute to developing a hypertensive retinopathy or diabetic retinopathy automated grading system. First, the tortuosity is quantified using fourteen tortuosity measurement formulas for the retinal images of the AV-Classification dataset to create the tortuosity feature set. Secondly, a manual labeling is performed and reviewed by two ophthalmologists to construct a tortuosity severity ground truth grading for each image in the AV classification dataset. Finally, the feature set is used to train and validate the machine learning models (J48 decision tree, ensemble rotation forest, and distributed random forest). The best performance learned model is used as the tortuosity severity classifier to identify the tortuosity severity (normal, mild, moderate, and severe) for any given retinal image. The distributed random forest model has reported the highest accuracy (99.4%) compared to the J48 Decision tree model and the rotation forest model with minimal least root mean square error (0.0000192) and the least mean average error (0.0000182). The proposed tortuosity severity grading matched the ophthalmologist's judgment. Moreover, detecting the tortuosity severity of the retinal vessels', optimizing vessel segmentation, the vessel segment extraction, and the created feature set have increased the accuracy of the automatic tortuosity severity detection model. [ABSTRACT FROM AUTHOR]

Background: Labeling color fundus photos (CFP) is an important step in the development of artificial intelligence screening algorithms for the detection of diabetic retinopathy (DR). Most studies use the International Classification of Diabetic Retinopathy (ICDR) to assign labels to CFP, plus the presence or absence of macular edema (ME). Images can be grouped as referrable or nonreferrable according to these classifications. There is little guidance in the literature about how to collect and use metadata as a part of the CFP labeling process., Objective: This study aimed to improve the quality of the Multimodal Database of Retinal Images in Africa (MoDRIA) by determining whether the availability of metadata during the image labeling process influences the accuracy, sensitivity, and specificity of image labels. MoDRIA was developed as one of the inaugural research projects of the Mbarara University Data Science Research Hub, part of the Data Science for Health Discovery and Innovation in Africa (DS-I Africa) initiative., Methods: This is a crossover assessment with 2 groups and 2 phases. Each group had 10 randomly assigned labelers who provided an ICDR score and the presence or absence of ME for each of the 50 CFP in a test image with and without metadata including blood pressure, visual acuity, glucose, and medical history. Specificity and sensitivity of referable retinopathy were based on ICDR scores, and ME was calculated using a 2-sided t test. Comparison of sensitivity and specificity for ICDR scores and ME with and without metadata for each participant was calculated using the Wilcoxon signed rank test. Statistical significance was set at P<.05., Results: The sensitivity for identifying referrable DR with metadata was 92.8% (95% CI 87.6-98.0) compared with 93.3% (95% CI 87.6-98.9) without metadata, and the specificity was 84.9% (95% CI 75.1-94.6) with metadata compared with 88.2% (95% CI 79.5-96.8) without metadata. The sensitivity for identifying the presence of ME was 64.3% (95% CI 57.6-71.0) with metadata, compared with 63.1% (95% CI 53.4-73.0) without metadata, and the specificity was 86.5% (95% CI 81.4-91.5) with metadata compared with 87.7% (95% CI 83.9-91.5) without metadata. The sensitivity and specificity of the ICDR score and the presence or absence of ME were calculated for each labeler with and without metadata. No findings were statistically significant., Conclusions: The sensitivity and specificity scores for the detection of referrable DR were slightly better without metadata, but the difference was not statistically significant. We cannot make definitive conclusions about the impact of metadata on the sensitivity and specificity of image labels in our study. Given the importance of metadata in clinical situations, we believe that metadata may benefit labeling quality. A more rigorous study to determine the sensitivity and specificity of CFP labels with and without metadata is recommended., (©Simon Arunga, Katharine Elise Morley, Teddy Kwaga, Michael Gerard Morley, Luis Filipe Nakayama, Rogers Mwavu, Fred Kaggwa, Julius Ssempiira, Leo Anthony Celi, Jessica E Haberer, Celestino Obua. Originally published in JMIR Formative Research (https://formative.jmir.org), 18.09.2024.)

Retinal vessel segmentation, skeletonization, and the generation of vessel segments are considered significant steps in any automated system for measuring the vessel biomarkers of several disease diagnoses. Most of the current tortuosity quantification methods rely on precise vascular segmentation and skeletonization of the retinal vessels. Additionally, the existence of a reference dataset for accurate vessel segment images is an essential need for implementing deep learning solutions and an automated system for measuring the vessel biomarkers of several disease diagnoses, especially for optimized quantification of vessel tortuosity or accurate measurement of AV-nicking. This study aimed to present an improved method for skeletonizing and extracting the retinal vessel segments from the 504 images in the AV classification dataset. The study utilized the Six Sigma process capability index, sigma level, and yield to measure the vessels’ tortuosity calculation improvement before and after optimizing the extracted vessels. As a result, the study showed that the sigma level for the vessel segment optimization improved from 2.7 to 4.39, the confirming yield improved from 88 percent to 99.77 percent, and the optimized vessel segments of the AV classification dataset retinal images are available in monochrome and colored formats.

Analyzing medical images has always been a challenging task because these images are used to observe complex internal structures of the human body. This research work is based on the study of the retinal fundus and magnetic resonance images (MRI) for the analysis of ocular and cerebral abnormalities. Typically, clinical quality images of the eyes and brain have low-varying contrast, making it challenge to diagnose a specific disease. These issues can be overcome, and preprocessing or an image enhancement technique is required to properly enhance images to facilitate postprocessing. In this paper, we propose an iterative algorithm based on the McCann Retinex algorithm for retinal and brain MRI. The foveal avascular zone (FAZ) region of retinal images and the coronal, axial, and sagittal brain images are enhanced during the preprocessing step. The High-Resolution Fundus (HRF) and MR brain Oasis images databases are used, and image contrast and peak signal-to-noise ratio (PSNR) are used to assess the enhancement step parameters. The average PSNR enhancement on images from the Oasis brain MRI database was about 3 dB with an average contrast of 57.4. The average PSNR enhancement of the HRF database images was approximately 2.5 dB with a contrast average of 40 over the database. The proposed method was also validated in the postprocessing steps to observe its impact. A well-segmented image was obtained with an accuracy of 0.953 and 0.0949 on the DRIVE and STARE databases. Brain tumors were detected from the Oasis brain MRI database with an accuracy of 0.97. This method can play an important role in helping medical experts diagnose eye diseases and brain tumors from retinal images and Oasis brain images. [ABSTRACT FROM AUTHOR]

Purpose: To assess the value of automatic disc-fovea angle (DFA) measurement using the DeepLabv3+ segmentation model. Methods: A total of 682 normal fundus image datasets were collected from the Eye Hospital of Nanjing Medical University. The following parts of the images were labeled and subsequently reviewed by ophthalmologists: optic disc center, macular center, optic disc area, and virtual macular area. A total of 477 normal fundus images were used to train DeepLabv3+, U-Net, and PSPNet model, which were used to obtain the optic disc area and virtual macular area. Then, the coordinates of the optic disc center and macular center were obstained by using the minimum outer circle technique. Finally the DFA was calculated. Results: In this study, 205 normal fundus images were used to test the model. The experimental results showed that the errors in automatic DFA measurement using DeepLabv3+, U-Net, and PSPNet segmentation models were 0.76°, 1.4°, and 2.12°, respectively. The mean intersection over union (MIoU), mean pixel accuracy (MPA), average error in the center of the optic disc, and average error in the center of the virtual macula obstained by using DeepLabv3+ model was 94.77%, 97.32%, 10.94 pixels, and 13.44 pixels, respectively. The automatic DFA measurement using DeepLabv3+ got the less error than the errors that using the other segmentation models. Therefore, the DeepLabv3+ segmentation model was finally chosen to measure DFA automatically. Conclusions: The DeepLabv3+ segmentation model -based automatic segmentation techniques can produce accurate and rapid DFA measurements. [ABSTRACT FROM AUTHOR]

Public databases for glaucoma studies contain color images of the retina, emphasizing the optic papilla. These databases are intended for research and standardized automated methodologies such as those using deep learning techniques. These techniques are used to solve complex problems in medical imaging, particularly in the automated screening of glaucomatous disease. The development of deep learning techniques has demonstrated potential for implementing protocols for large-scale glaucoma screening in the population, eliminating possible diagnostic doubts among specialists, and benefiting early treatment to delay the onset of blindness. However, the images are obtained by different cameras, in distinct locations, and from various population groups and are centered on multiple parts of the retina. We can also cite the small number of data, the lack of segmentation of the optic papillae, and the excavation. This work is intended to offer contributions to the structure and presentation of public databases used in the automated screening of glaucomatous papillae, adding relevant information from a medical point of view. The gold standard public databases present images with segmentations of the disc and cupping made by experts and division between training and test groups, serving as a reference for use in deep learning architectures. However, the data offered are not interchangeable. The quality and presentation of images are heterogeneous. Moreover, the databases use different criteria for binary classification with and without glaucoma, do not offer simultaneous pictures of the two eyes, and do not contain elements for early diagnosis. [ABSTRACT FROM AUTHOR]

Glaucoma is a group of eye conditions that damage the optic nerve, the health of which is vital for good eyesight. This damage is often caused by higher-than-normal pressure in the eye. In the past few years, the applications of artificial intelligence and data science have increased rapidly in medicine especially in imaging applications. In particular, deep learning tools have been successfully applied obtaining, in some cases, results superior to those obtained by humans. In this article, we present a soft novel ensemble model based on the K-NN algorithm, that combines the probability of class membership obtained by several deep learning models. In this research, three models of different nature (CNN, CapsNets and Convolutional Autoencoders) have been selected searching for diversity. The latent space of these models are combined using the local information provided by the true sample labels and the K-NN algorithm is applied to determine the final decision. The results obtained on two different datasets of retinal images show that the proposed ensemble model improves the diagnosis capabilities for both the individual models and the state-of-the-art results. [ABSTRACT FROM AUTHOR]

• Exudates are the abnormal pattern lesions in Diabetic Retinopathy (DR) images, which is the primary cause of DR in diabetic patients. • Therefore, its detection process is essential for further severity estimation of DR images. • Automated detection systems' robustness can be hampered by training datasets that are not representative. • In this paper, the DR image is detected and classified using the proposed Dual Functional Convolutional Neural Networks (DFCNN). • This proposed system consists of a noise detection and removal subblock, enhancement subblock, Gabor transform subblock, Feature computation subblock, and the proposed CNN classification architecture subblock. • This proposed methodology is divided into two modules: a training module and a testing module. • In the training module, the proposed DFCNN classification architecture is used to train both the abnormal case (DR case) and the healthy case (HCA) retinal images. • In the testing module, the test source retinal image is classified as either a beneficial or DR case retinal image. • From the classified DR case retinal image, the exudates are identified through the segmentation process in this research work. • This developed DR and exudates detection system stated in this paper are evaluated on DRIVE, and DIARETDB1 retinal images and the experimental results are conducted with respect to various performance metrics in this paper. • Once the suggested methodology was compared to other classification approaches, the proposed method's accuracy was found to be greater (99.4 %). Exudates are the abnormal pattern lesions in Diabetic Retinopathy (DR) images, which is the primary cause of DR in diabetic patients. Therefore, its detection process is essential for further severity estimation of DR images. Automated detection systems' robustness can be hampered by training datasets that are not representative. In this paper, the DR image is detected and classified using the proposed Dual Functional Convolutional Neural Networks (DFCNN). This proposed system consists of a noise detection and removal subblock, enhancement subblock, Gabor transform subblock, Feature computation subblock, and the proposed CNN classification architecture subblock. This proposed methodology is divided into two modules: a training module and a testing module. In the training module, the proposed DFCNN classification architecture is used to train both the abnormal case (DR case) and the healthy case (HCA) retinal images. In the testing module, the test source retinal image is classified as either a beneficial or DR case retinal image. From the classified DR case retinal image, the exudates are identified through the segmentation process in this research work. This developed DR and exudates detection system stated in this paper are evaluated on DRIVE, and DIARETDB1 retinal images and the experimental results are conducted with respect to various performance metrics in this paper. Once the suggested methodology was compared to other classification approaches, the proposed method's accuracy was found to be greater (99.4 %). [ABSTRACT FROM AUTHOR]

Introduction: Glaucoma is the most common cause of blindness in some countries. In the meantime, the field of retinal image processing has been proposed in order to provide automatic systems for disease diagnosis. Among the methods of medical image processing, image segmentation is a process of identification and change in the display of an image. The objective of this study was to use the segmentation method and compare it with previous algorithms so as to be able to diagnose retinal optic disc more accurately. Method: In the present analytical study, using the image segmentation method, each pixel was assigned a label in such a way that pixels with the same label had similar characteristics. The optic disc segmentation was performed. Using MATLAB software, retinal images of patients with glaucoma were entered into the program and an ideal output was obtained. Results: The quantitative analysis of the obtained results showed a high accuracy (85%) for the proposed method for the segmentation of the retinal optic disc; thus, the results can be used to efficiently diagnose a person with glaucoma. Conclusion: The purpose of segmenting an image is to make raw data more usable for subsequent statistical processing. It is expected that in the future, feature extraction be more accurate, and more details be available to machine vision systems to identify objects in the images.

Background: Coronary heart disease (CHD) is the leading cause of death worldwide, constituting a growing health and social burden. People with cardiometabolic disorders are more likely to develop CHD. Retinal image analysis is a novel and noninvasive method to assess microvascular function. We aim to investigate whether retinal images can be used for CHD risk estimation for people with cardiometabolic disorders. Methods: We have conducted a case–control study at Shenzhen Traditional Chinese Medicine Hospital, where 188 CHD patients and 128 controls with cardiometabolic disorders were recruited. Retinal images were captured within two weeks of admission. The retinal characteristics were estimated by the automatic retinal imaging analysis (ARIA) algorithm. Risk estimation models were established for CHD patients using machine learning approaches. We divided CHD patients into a diabetes group and a non-diabetes group for sensitivity analysis. A ten-fold cross-validation method was used to validate the results. Results: The sensitivity and specificity were 81.3% and 88.3%, respectively, with an accuracy of 85.4% for CHD risk estimation. The risk estimation model for CHD with diabetes performed better than the model for CHD without diabetes. Conclusions: The ARIA algorithm can be used as a risk assessment tool for CHD for people with cardiometabolic disorders. [ABSTRACT FROM AUTHOR]

The manual segmentation of the blood vessels in retinal images has numerous limitations. It is very time consuming and prone to human error, particularly with a very twisted structure of the blood vessel and a vast number of retinal images that needs to be analysed. Therefore, an automatic algorithm for segmenting and extracting useful clinical features from the retinal blood vessels is critical to help ophthalmologists and eye specialists to diagnose different retinal diseases and to assess early treatment. An accurate, rapid, and fully automatic blood vessel segmentation and clinical features measurement algorithm for retinal fundus images is proposed to improve the diagnosis precision and decrease the workload of the ophthalmologists. The main pipeline of the proposed algorithm is composed of two essential stages: image segmentation and clinical features extraction stage. Several comprehensive experiments were carried out to assess the performance of the developed fully automated segmentation algorithm in detecting the retinal blood vessels using two extremely challenging fundus images datasets, named the DRIVE and HRF. Initially, the accuracy of the proposed algorithm was evaluated in terms of adequately detecting the retinal blood vessels. In these experiments, five quantitative performances were measured and calculated to validate the efficiency of the proposed algorithm, which consist of the Acc., Sen., Spe., PPV, and NPV measures compared with current state-of-the-art vessel segmentation approaches on the DRIVE dataset. The results obtained showed a significantly improvement by achieving an Acc., Sen., Spe., PPV, and NPV of 99.55%, 99.93%, 99.09%, 93.45%, and 98.89, respectively. [ABSTRACT FROM AUTHOR]

Eye fundus images are used in clinical diagnosis for the detection and assessment of retinal disorders. When retinal images are degraded by scattering due to opacities of the eye tissues, the precise detection of abnormalities is complicated depending on the grading of the opacity. This paper presents a concept proof study on the use of the contrast limited adaptive histogram equalization (CLAHE) technique for better visualization of eye fundus images for different levels of blurring due to different stages of cataracts. Processing is performed in three different color spaces: RGB, CIELAB and HSV, with the aim of finding which one better enhances the missed diagnostic features due to blur. The experimental results show that some fundus features not observable by naked eye can be detected in some of the space color processed with the proposed method. In this work, we also develop and provide an online image process, which allows clinicians to tune the default parameters of the algorithm for a better visualization of the characteristics of fundus images. It also allows the choice of a region of interest (ROI) within the images that provide better visualization of some features than those enhanced by the processing of the full picture. [ABSTRACT FROM AUTHOR]

Hypertensive retinopathy (HR) refers to changes in the morphological diameter of the retinal vessels due to persistent high blood pressure. Early detection of such changes helps in preventing blindness or even death due to stroke. These changes can be quantified by computing the arteriovenous ratio and the tortuosity severity in the retinal vasculature. This paper presents a decision support system for detecting and grading HR using morphometric analysis of retinal vasculature, particularly measuring the arteriovenous ratio (AVR) and retinal vessel tortuosity. In the first step, the retinal blood vessels are segmented and classified as arteries and veins. Then, the width of arteries and veins is measured within the region of interest around the optic disk. Next, a new iterative method is proposed to compute the AVR from the caliber measurements of arteries and veins using Parr–Hubbard and Knudtson methods. Moreover, the retinal vessel tortuosity severity index is computed for each image using 14 tortuosity severity metrics. In the end, a hybrid decision support system is proposed for the detection and grading of HR using AVR and tortuosity severity index. Furthermore, we present a new publicly available retinal vessel morphometry (RVM) dataset to evaluate the proposed methodology. The RVM dataset contains 504 retinal images with pixel-level annotations for vessel segmentation, artery/vein classification, and optic disk localization. The image-level labels for vessel tortuosity index and HR grade are also available. The proposed methods of iterative AVR measurement, tortuosity index, and HR grading are evaluated using the new RVM dataset. The results indicate that the proposed method gives superior performance than existing methods. The presented methodology is a novel advancement in automated detection and grading of HR, which can potentially be used as a clinical decision support system. [ABSTRACT FROM AUTHOR]

Limited labelled data is a challenge in the field of medical imaging and the need for a large number of them is paramount for the training of machine learning algorithms, as well as measuring the performance of image processing algorithms. The purpose of this study is to construct synthetic and labelled optical coherence tomography (OCT) data to solve the problems of having access to accurately labelled data and evaluating the processing algorithms. In this study, a modified active shape model is used which considers the anatomical features of available images such as the number and thickness of the layers as well as their associated brightness, the location of retinal blood vessels and shadow information with respect to speckle noise. The algorithm is also able to provide different data sets with the varying noise level. The validity of the proposed method for the synthesis of retinal images is measured by two methods (qualitative assessment and quantitative analysis).

The number of patient suffering from complex congenital heart diseases (CHDs) increases gradually each year. The perioperative parameters assessment of complex CHDs patients is critical in choosing a suitable surgery method, but there is still a lack of an accurate and interpretable approach to preoperatively assess surgical risks and prognosis. The vascular patterns in retinal images of patients with complex CHDs reflect the severity of heart disease, so retinal images are used to predict the risk of perioperative parameters of heart disease. Perioperative parameters classification from retinal images is challenging due to the limited available retinal image data in patients with CHDs and the interference caused by retinal images with poor quality. In this work, a method called deep learning based perioperative parameter classifier is proposed to classify perioperative parameter risk from retinal images of patients with complex CHDs. To evaluate its effectiveness, our method is verified with 6 perioperative parameters, respectively. Experimental results show that the proposed method is superior to several popular classification networks in this task. Saliency maps are also provided to enhance the interpretability in our model and may be of great use for future medical researches. [ABSTRACT FROM AUTHOR]

This study presents an automated registration method based on optical flow for an adaptive optics scanning laser ophthalmoscope. The method was designed to align and average images to obtain a higher signal-to-noise ratio image. A correlation based optical flow image registration method, which has large registration degrees of freedom, is adopted as a local registration method. By comparing the images before and after image registration, we show the effectiveness of our method. Furthermore, the advantage of our method, which is the containment of large registration degrees of freedom, is confirmed.

Geometrical analysis of cone photoreceptor cells is important not only for ophthalmic diagnosis, but also for research on eye diseases. In this study, an automated cone photoreceptor cell segmentation and identification method based on morphological processing and watershed algorithm is presented for adaptive optics scanning laser ophthalmoscope images. Our method includes steps for image denoising, rough segmentation, fine segmentation, small region removal, and identification. The effectiveness of the proposed method was confirmed by comparing its results with those obtained manually yielding precision, recall, and F1-score values of 93.6%, 98.0% and 95.8%, respectively. The performance of our method is further verified by processing images with different cone photoreceptor cell densities from healthy retina and an image from an eye with diabetic retinopathy. The experimental results show that our algorithm achieved high accuracy in cone photoreceptor cell segmentation and identification in healthy retinas as well as in retina with diabetic retinopathy.

From diagnosing cardiovascular diseases to analyzing the progression of diabetic retinopathy, accurate retinal artery/vein (A/V) classification is critical. Promising approaches for A/V classification, ranging from conventional graph based methods to recent convolutional neural network (CNN) based models, have been known. However, the inability of traditional graph based methods to utilize deep hierarchical features extracted by CNNs and the limitations of current CNN based methods to incorporate vessel topology information hinder their effectiveness. In this paper, we propose a new CNN based framework, VTG-Net (vessel topology graph network), for retinal A/V classification by incorporating vessel topology information. VTG-Net exploits retinal vessel topology along with CNN features to improve A/V classification accuracy. Specifically, we transform vessel features extracted by CNN in the image domain into a graph representation preserving the vessel topology. Then by exploiting a graph convolutional network (GCN), we enable our model to learn both CNN features and vessel topological features simultaneously. The final predication is attained by fusing the CNN and GCN outputs. Using a publicly available AV-DRIVE dataset and an in-house dataset, we verify the high performance of our VTG-Net for retinal A/V classification over state-of-the-art methods (with ~2% improvement in accuracy on the AV-DRIVE dataset).

Background: The aim of this study was to assess the performance of regional graders and artificial intelligence algorithms across retinal cameras with different specifications in classifying an image as gradable and ungradable. Methods: Study subjects were included from a community-based nationwide diabetic retinopathy screening program in Thailand. Various non-mydriatic fundus cameras were used for image acquisition, including Kowa Nonmyd, Kowa Nonmyd α-DⅢ, Kowa Nonmyd 7, Kowa Nonmyd WX, Kowa VX 10 α, Kowa VX 20 and Nidek AFC 210. All retinal photographs were graded by deep learning algorithms and human graders and compared with a standard reference. Results: Images were divided into two categories as gradable and ungradable images. Four thousand eight hundred fifty-two participants with 19,408 fundus images were included, of which 15,351 (79.09%) were gradable images and the remaining 4057 (20.90%) were ungradable images. Conclusions: The deep learning (DL) algorithm demonstrated better sensitivity, specificity and kappa than the human graders for all eight types of non-mydriatic fundus cameras. The deep learning system showed, more consistent diagnostic performance than the human graders across images of varying quality and camera types.

Hypertensive retinopathy severity classification is proportionally related to tortuosity severity grading. No tortuosity severity scale enables a computer-aided system to classify the tortuosity severity of a retinal image. This work aimed to introduce a machine learning model that can identify the severity of a retinal image automatically and hence contribute to developing a hypertensive retinopathy or diabetic retinopathy automated grading system. First, the tortuosity is quantified using fourteen tortuosity measurement formulas for the retinal images of the AV-Classification dataset to create the tortuosity feature set. Secondly, a manual labeling is performed and reviewed by two ophthalmologists to construct a tortuosity severity ground truth grading for each image in the AV classification dataset. Finally, the feature set is used to train and validate the machine learning models (J48 decision tree, ensemble rotation forest, and distributed random forest). The best performance learned model is used as the tortuosity severity classifier to identify the tortuosity severity (normal, mild, moderate, and severe) for any given retinal image. The distributed random forest model has reported the highest accuracy (99.4%) compared to the J48 Decision tree model and the rotation forest model with minimal least root mean square error (0.0000192) and the least mean average error (0.0000182). The proposed tortuosity severity grading matched the ophthalmologist’s judgment. Moreover, detecting the tortuosity severity of the retinal vessels’, optimizing vessel segmentation, the vessel segment extraction, and the created feature set have increased the accuracy of the automatic tortuosity severity detection model.

Multimodal retinal imaging plays an important role in ophthalmology. We propose a content-adaptive multimodal retinal image registration method in this paper that focuses on the globally coarse alignment and includes three weakly supervised neural networks for vessel segmentation, feature detection and description, and outlier rejection. We apply the proposed framework to register color fundus images with infrared reflectance and fluorescein angiography images, and compare it with several conventional and deep learning methods. Our proposed framework demonstrates a significant improvement in robustness and accuracy reflected by a higher success rate and Dice coefficient compared with other methods. [ABSTRACT FROM AUTHOR]

This paper aims to propose a robust hybrid probabilistic learning approach that combines appropriately the advantages of both the generative and discriminative models for the challenging problem of diabetic retinopathy classification in retinal images. We build new probabilistic kernels based on information divergences and Fisher score from the mixture of scaled Dirichlet distributions for support vector machines (SVMs). We also investigate the incorporation of a minimum description length criterion into the learning model to deal with the common problems of determining suitable components and also selecting the best model that describes the dataset. The developed hybrid model is introduced in this paper as an effective SVM kernel able to incorporate prior knowledge about the nature of data involved in the problem at hand and, therefore, permits a good data discrimination. Our approach has been shown to be a better alternative to other methods, which is able to describe the intrinsic nature of datasets and to be of a significant value in a variety of applications involving data classification. We demonstrate the flexibility and the merits of the proposed framework for the problem of diabetic retinopathy detection in eye images.

A line-scanning ophthalmoscope (LSO) is a retinal imaging technique that has the characteristics of high imaging resolution, wide field of view, and high imaging speed. However, the high-speed imaging with rather short exposure time inevitably reduces the signal intensity, and many factors, such as speckle noise and intraocular scatter, further degrade the signal-to-noise ratio (SNR) of retinal images. To effectively improve the image quality without increasing the LSO system's complexity, the post-processing method of image super-resolution (SR) is adopted. In this paper, we propose a learning-based multi-frame retinal image SR method that directly learns an end-to-end mapping from low-resolution (LR) image sequences to high-resolution (HR) images. This network was validated on down-sampled and real LSO image sequences. We evaluated the method on a down-sampled dataset with the metrics of peak signal-to-noise ratio (PSNR), structural similarity (SSIM), and perceptual distance. Moreover, the power spectra and full width at half maximum (FWHM) were used as the no-reference image quality assessment (NR-IQA) algorithms to evaluate the reconstruction results of the real LSO image sequences. The experimental results indicate that the proposed method can significantly enhance the SNR of LSO images and efficiently improve the resolution of LSO retinal images, which has great practical significance for clinical diagnosis and analysis.

Analyzing medical images has always been a challenging task because these images are used to observe complex internal structures of the human body. This research work is based on the study of the retinal fundus and magnetic resonance images (MRI) for the analysis of ocular and cerebral abnormalities. Typically, clinical quality images of the eyes and brain have low-varying contrast, making it challenge to diagnose a specific disease. These issues can be overcome, and preprocessing or an image enhancement technique is required to properly enhance images to facilitate postprocessing. In this paper, we propose an iterative algorithm based on the McCann Retinex algorithm for retinal and brain MRI. The foveal avascular zone (FAZ) region of retinal images and the coronal, axial, and sagittal brain images are enhanced during the preprocessing step. The High-Resolution Fundus (HRF) and MR brain Oasis images databases are used, and image contrast and peak signal-to-noise ratio (PSNR) are used to assess the enhancement step parameters. The average PSNR enhancement on images from the Oasis brain MRI database was about 3 dB with an average contrast of 57.4. The average PSNR enhancement of the HRF database images was approximately 2.5 dB with a contrast average of 40 over the database. The proposed method was also validated in the postprocessing steps to observe its impact. A well-segmented image was obtained with an accuracy of 0.953 and 0.0949 on the DRIVE and STARE databases. Brain tumors were detected from the Oasis brain MRI database with an accuracy of 0.97. This method can play an important role in helping medical experts diagnose eye diseases and brain tumors from retinal images and Oasis brain images.

Glaucoma is a group of eye conditions that damage the optic nerve, the health of which is vital for good eyesight. This damage is often caused by higher-than-normal pressure in the eye. In the past few years, the applications of artificial intelligence and data science have increased rapidly in medicine especially in imaging applications. In particular, deep learning tools have been successfully applied obtaining, in some cases, results superior to those obtained by humans. In this article, we present a soft novel ensemble model based on the K-NN algorithm, that combines the probability of class membership obtained by several deep learning models. In this research, three models of different nature (CNN, CapsNets and Convolutional Autoencoders) have been selected searching for diversity. The latent space of these models are combined using the local information provided by the true sample labels and the K-NN algorithm is applied to determine the final decision. The results obtained on two different datasets of retinal images show that the proposed ensemble model improves the diagnosis capabilities for both the individual models and the state-of-the-art results.

Diabetes, also known as Diabetes Mellitus is a disease that happens to a person when one's blood glucose or blood sugar is extremely high. Insulin is a hormone secreted by the organ pancreas and helps to convert the blood glucose into useful energy for the body. In some cases, the body doesn't produce enough, or any amount of insulin or doesn't use the produced insulin properly. Hence the Glucose remains in the blood and doesn't reach the body cells. Thus, having a lot of glucose in your blood can causes health problems, which is what exactly happens in Diabetes. Longterm complications of Diabetes develop gradually. Having Diabetes for a long time along with uncontrolled blood sugar levels can cause dangerous complications. In the due course, diabetes complications may be disabling or even life- threatening. Making things even worse, there is no cure for this disease yet! Even though there's no cure for diabetes, it can be treated and controlled, and some people may go into a state of remission. But the very first step towards controlling and minimizing the ill effects of Diabetes is -- the early detection of the disease! Thus, we need comfortable, reliable, and quick methods of detection. Hence, we are proposing an efficient, reliable, comfortable, and time-saving Diabetes detection system for Diabetes detection using diabetic Retinopathy and Implementation of Convolutional Neural Networks (CNN). The level of Diabetic retinopathy present will also give a direct indication about the level of Diabetes. The implementation of this method of Diabetes detection will increase accuracy, efficiency, and ease of Diabetes detection, and further the prognosis and treatment. Also, it will prove to be a better alternative to conventional testing for the disease. [ABSTRACT FROM AUTHOR]

Retinal blood vessels analysis is of interest for medical screening, especially in the diagnosis of diabetic retinopathy. In this paper, we propose a new method for the segmentation of blood vessels in retinal photographs. This method is based on classical edge detection filters and artificial neural networks. Firstly, edge detection filters are applied to extract the features vector. The resulting features are used to train an artificial neural network in order to recognize each pixel as belonging to blood vessels or not. The obtained algorithm is evaluated with the publicly available DRIVE, CHASE and STARE datasets, containing retinal images frequently used for this goal. The performance of the proposed system is calculated in terms of detection accuracy, sensitivity, specificity, and the area under the ROC curve. Our model is compared to other vessel segmentation models with encouraging results obtained. The proposed algorithm is a suitable tool for automated retinal image analysis.

Eye fundus images are used in clinical diagnosis for the detection and assessment of retinal disorders. When retinal images are degraded by scattering due to opacities of the eye tissues, the precise detection of abnormalities is complicated depending on the grading of the opacity. This paper presents a concept proof study on the use of the contrast limited adaptive histogram equalization (CLAHE) technique for better visualization of eye fundus images for different levels of blurring due to different stages of cataracts. Processing is performed in three different color spaces: RGB, CIELAB and HSV, with the aim of finding which one better enhances the missed diagnostic features due to blur. The experimental results show that some fundus features not observable by naked eye can be detected in some of the space color processed with the proposed method. In this work, we also develop and provide an online image process, which allows clinicians to tune the default parameters of the algorithm for a better visualization of the characteristics of fundus images. It also allows the choice of a region of interest (ROI) within the images that provide better visualization of some features than those enhanced by the processing of the full picture.

Limited labelled data is a challenge in the field of medical imaging and the need for a large number of them is paramount for the training of machine learning algorithms, as well as measuring the performance of image processing algorithms. The purpose of this study is to construct synthetic and labelled optical coherence tomography (OCT) data to solve the problems of having access to accurately labelled data and evaluating the processing algorithms. In this study, a modified active shape model is used which considers the anatomical features of available images such as the number and thickness of the layers as well as their associated brightness, the location of retinal blood vessels and shadow information with respect to speckle noise. The algorithm is also able to provide different data sets with the varying noise level. The validity of the proposed method for the synthesis of retinal images is measured by two methods (qualitative assessment and quantitative analysis). [ABSTRACT FROM AUTHOR]

Glaucoma is a silent disease that leads to vision loss or irreversible blindness. Current deep learning methods can help glaucoma screening by extending it to larger populations using retinal images. Low-cost lenses attached to mobile devices can increase the frequency of screening and alert patients earlier for a more thorough evaluation. This work explored and compared the performance of classification and segmentation methods for glaucoma screening with retinal images acquired by both retinography and mobile devices. The goal was to verify the results of these methods and see if similar results could be achieved using images captured by mobile devices. The used classification methods were the Xception, ResNet152 V2 and the Inception ResNet V2 models. The models’ activation maps were produced and analysed to support glaucoma classifier predictions. In clinical practice, glaucoma assessment is commonly based on the cup-to-disc ratio (CDR) criterion, a frequent indicator used by specialists. For this reason, additionally, the U-Net architecture was used with the Inception ResNet V2 and Inception V3 models as the backbone to segment and estimate CDR. For both tasks, the performance of the models reached close to that of state-of-the-art methods, and the classification method applied to a low-quality private dataset illustrates the advantage of using cheaper lenses.

This paper presents a supervised feature learning method to learn discriminative and compact descriptors for drusen segmentation from retinal images. This method combines generalized low rank approximation of matrices with supervised manifold regularization to learn new features from image patches sampled from retinal images. The learned features are closely related to drusen and potentially free from information that is redundant in distinguishing drusen from background. The learned feature representations are then vectorized and used to train a support vector machine (SVM) classifier. Finally, the obtained SVM classifier is employed to classify the pixels in the test images as drusen or non-drusen. The performance of the proposed method is validated on the STARE and DRIVE databases, where it achieves an average sensitivity/specificity/accuracy of 90.03%/97.06%/96.92% and of 87.41%/94.93%/94.81%, respectively. We also experimentally compare the proposed method with the several representative state-of-the-art drusen segmentation techniques and find that it generates superior accuracy.