Recent trends and advances in fundus image analysis: A review

Retinal fundus image super-resolution based on generative adversarial network guided with vascular structure prior

Many ophthalmic and systemic diseases can be screened by analyzing retinal fundus images. The clarity and resolution of retinal fundus images directly determine the effectiveness of clinical diagnosis. Deep learning methods based on generative adversarial networks are used in various research fields due to their powerful generative capabilities, especially image super-resolution. Although Real-ESRGAN is a recently proposed method that excels in processing real-world degraded images, it suffers from structural distortions when super-resolving retinal fundus images are rich in structural information. To address this shortcoming, we first process the input image using a pre-trained U-Net model to obtain a structural segmentation map of the retinal vessels and use the segmentation map as the structural prior. The spatial feature transform layer is then used to better integrate the structural prior into the generation process of the generator. In addition, we introduce channel and spatial attention modules into the skip connections of the discriminator to emphasize meaningful features and accordingly enhance the discriminative power of the discriminator. Based on the original loss functions, we introduce the L1 loss function to measure the pixel-level differences between the segmentation maps of retinal vascular structures in the high-resolution images and the super-resolution images to further constrain the super-resolution images. Simulation results on retinal image datasets show that our improved algorithm results have a better visual performance by suppressing structural distortions in the super-resolution images.

Determinants of Human Asymmetry: Does Asymmetrical Retinal Vasculature Predict Asymmetry Elsewhere in the Body?

The aim of this study was to explore retinal vasculature asymmetry (ReVA) patterns in subjects from the islands of Vis and Korcula and the city of Split, Croatia. Asymmetry estimates were based on topographic image analysis of non-mydriatic retinal fundus photographs and compared with nine ophthalmic measurements, three Doppler-based pressure indices and eight frequencies of audiometry. ReVA was also correlated to the genomic runs of homozygosity (ROHs) and used in a Cox regression survival model, where we adjusted for the effects of sex, age and comorbidity. In 1873 subjects, ReVA estimates were significantly correlated with most ophthalmic asymmetry measures, less strongly with the ankle-brachial pressure index and only modestly with higher-amplitude audiometry asymmetries (lowest p = 0.020). ReVA was significantly correlated with the number of ROHs (r = 0.229, p < 0.001) but less strongly with the ROH length (r = 0.101, p < 0.001). The overlap of asymmetries was low, with only 107 subjects (5.7% of the total sample) who had two or more instances in which they were among the top 10%. Multiple asymmetries did not affect survival (HR = 0.74, 95% confidence intervals 0.45-1.22). Retinal vasculature asymmetry is a poor predictor of asymmetry elsewhere in the body. Despite its existence and apparent association with comorbidities, the observed extent of retinal vasculature asymmetry did not affect the lifespan in this population.

LMBiS-Net: A lightweight bidirectional skip connection based multipath CNN for retinal blood vessel segmentation

Blinding eye diseases are often related to changes in retinal structure, which can be detected by analysing retinal blood vessels in fundus images. However, existing techniques struggle to accurately segment these delicate vessels. Although deep learning has shown promise in medical image segmentation, its reliance on specific operations can limit its ability to capture crucial details such as the edges of the vessel. This paper introduces LMBiS-Net, a lightweight convolutional neural network designed for the segmentation of retinal vessels. LMBiS-Net achieves exceptional performance with a remarkably low number of learnable parameters (only 0.172 million). The network used multipath feature extraction blocks and incorporates bidirectional skip connections for the information flow between the encoder and decoder. In addition, we have optimised the efficiency of the model by carefully selecting the number of filters to avoid filter overlap. This optimisation significantly reduces training time and improves computational efficiency. To assess LMBiS-Net's robustness and ability to generalise to unseen data, we conducted comprehensive evaluations on four publicly available datasets: DRIVE, STARE, CHASE_DB1, and HRF The proposed LMBiS-Net achieves significant performance metrics in various datasets. It obtains sensitivity values of 83.60%, 84.37%, 86.05%, and 83.48%, specificity values of 98.83%, 98.77%, 98.96%, and 98.77%, accuracy (acc) scores of 97.08%, 97.69%, 97.75%, and 96.90%, and AUC values of 98.80%, 98.82%, 98.71%, and 88.77% on the DRIVE, STARE, CHEASE_DB, and HRF datasets, respectively. In addition, it records F1 scores of 83.43%, 84.44%, 83.54%, and 78.73% on the same datasets. Our evaluations demonstrate that LMBiS-Net achieves high segmentation accuracy (acc) while exhibiting both robustness and generalisability across various retinal image datasets. This combination of qualities makes LMBiS-Net a promising tool for various clinical applications.

Computational single fundus image restoration techniques: a review

Fundus cameras are widely used by ophthalmologists for monitoring and diagnosing retinal pathologies. Unfortunately, no optical system is perfect, and the visibility of retinal images can be greatly degraded due to the presence of problematic illumination, intraocular scattering, or blurriness caused by sudden movements. To improve image quality, different retinal image restoration/enhancement techniques have been developed, which play an important role in improving the performance of various clinical and computer-assisted applications. This paper gives a comprehensive review of these restoration/enhancement techniques, discusses their underlying mathematical models, and shows how they may be effectively applied in real-life practice to increase the visual quality of retinal images for potential clinical applications including diagnosis and retinal structure recognition. All three main topics of retinal image restoration/enhancement techniques, i.e., illumination correction, dehazing, and deblurring, are addressed. Finally, some considerations about challenges and the future scope of retinal image restoration/enhancement techniques will be discussed.

Automatic artery/vein classification methods for retinal blood vessel: A review

Automatic retinal arteriovenous classification can assist ophthalmologists in disease early diagnosis. Deep learning-based methods and topological graph-based methods have become the main solutions for retinal arteriovenous classification in recent years. This paper reviews the automatic retinal arteriovenous classification methods from 2003 to 2022. Firstly, we compare different methods and provide comparison tables of the summary results. Secondly, we complete the classification of the public arteriovenous classification datasets and provide the annotation development tables of different datasets. Finally, we sort out the challenges of evaluation methods and provide a comprehensive evaluation system. Quantitative and qualitative analysis shows the changes in research hotspots over time, Quantitative and qualitative analyses reveal the evolution of research hotspots over time, highlighting the significance of exploring the integration of deep learning with topological information in future research.

CRA-Net: Transformer guided category-relation attention network for diabetic retinopathy grading

Automated grading of diabetic retinopathy (DR) is an important means for assisting clinical diagnosis and preventing further retinal damage. However, imbalances and similarities between categories in the DR dataset make it highly challenging to accurately grade the severity of the condition. Furthermore, DR images encompass various lesions, and the pathological relationship information among these lesions can be easily overlooked. For instance, under different severity levels, the varying contributions of different lesions to accurate model grading differ significantly. To address the aforementioned issues, we design a transformer guided category-relation attention network (CRA-Net). Specifically, we propose a novel category attention block that enhances feature information within the class from the perspective of DR image categories, thereby alleviating class imbalance problems. Additionally, we design a lesion relation attention block that captures relationships between lesions by incorporating attention mechanisms in two primary aspects: capsule attention models the relative importance of different lesions, allowing the model to focus on more "informative" ones. Spatial attention captures the global position relationship between lesion features under transformer guidance, facilitating more accurate localization of lesions. Experimental and ablation studies on two datasets DDR and APTOS 2019 demonstrate the effectiveness of CRA-Net and obtain competitive performance.

High-precision retinal blood vessel segmentation based on a multi-stage and dual-channel deep learning network

Objective.The high-precision segmentation of retinal vessels in fundus images is important for the early diagnosis of ophthalmic diseases. However, the extraction for microvessels is challenging due to their characteristics of low contrast and high structural complexity. Although some works have been developed to improve the segmentation ability in thin vessels, they have only been successful in recognizing small vessels with relatively high contrast.Approach.Therefore, we develop a deep learning (DL) framework with a multi-stage and dual-channel network model (MSDC_NET) to further improve the thin-vessel segmentation with low contrast. Specifically, an adaptive image enhancement strategy combining multiple preprocessing and the DL method is firstly proposed to elevate the contrast of thin vessels; then, a two-channel model with multi-scale perception is developed to implement whole- and thin-vessel segmentation; and finally, a series of post-processing operations are designed to extract more small vessels in the predicted maps from thin-vessel channels.Main results.Experiments on DRIVE, STARE and CHASE_DB1 demonstrate the superiorities of the proposed MSDC_NET in extracting more thin vessels in fundus images, and quantitative evaluations on several parameters based on the advanced ground truth further verify the advantages of our proposed DL model. Compared with the previous multi-branch method, the specificity and F1score are improved by about 2.18%, 0.68%, 1.73% and 2.91%, 0.24%, 8.38% on the three datasets, respectively.Significance.This work may provide richer information to ophthalmologists for the diagnosis and treatment of vascular-related ophthalmic diseases.

Perception-oriented generative adversarial network for retinal fundus image super-resolution

Retinal fundus imaging is a crucial diagnostic tool in ophthalmology, enabling the early detection and monitoring of various ocular diseases. However, capturing high-resolution fundus images often presents challenges due to factors such as defocusing and diffraction in the digital imaging process, limited shutter speed, sensor unit density, and random noise in the image sensor or during image transmission. Super-resolution techniques offer a promising solution to overcome these limitations and enhance the visual details in retinal fundus images. Since the retina has rich texture details, the super-resolution images often introduce artifacts into texture details and lose some fine retinal vessel structures. To improve the perceptual quality of the retinal fundus image, a generative adversarial network that consists of a generator and a discriminator is proposed. The proposed generator mainly comprises 23 multi-scale feature extraction blocks, an image segmentation network, and 23 residual-in-residual dense blocks. These components are employed to extract features at different scales, acquire the retinal vessel grayscale image, and extract retinal vascular features, respectively. The generator has two branches that are mainly responsible for extracting global features and vascular features, respectively. The extracted features from the two branches are fused to better restore the super-resolution image. The proposed generator can restore more details and more accurate fine vessel structures in retinal images. The improved discriminator is proposed by introducing our designed attention modules to help the generator yield clearer super-resolution images. Additionally, an artifact loss function is also introduced to enhance the generative adversarial network, enabling more accurate measurement of the disparity between the high-resolution image and the restored image. Experimental results show that the generated images obtained by our proposed method have a better perceptual quality than the state-of-the-art image super-resolution methods.

Semantic segmentation of retinal exudates using a residual encoder-decoder architecture in diabetic retinopathy

Exudates are a common sign of diabetic retinopathy, which is a disease that affects the blood vessels in the retina. Early detection of exudates is critical to avoiding vision problems through continuous screening and treatment. In traditional clinical practice, the involved lesions are manually detected using photographs of the fundus. However, this task is cumbersome and time-consuming and requires intense effort due to the small size of the lesion and the low contrast of the images. Thus, computer-assisted diagnosis of retinal disease based on the detection of red lesions has been actively explored recently. In this paper, we present a comparison of deep convolutional neural network (CNN) architectures and propose a residual CNN with residual skip connections to reduce the parameter for the semantic segmentation of exudates in retinal images. A suitable image augmentation technique is used to improve the performance of network architecture. The proposed network can robustly segment exudates with high accuracy, which makes it suitable for diabetic retinopathy screening. A comparative performance analysis of three benchmark databases: E-ophtha, DIARETDB1, and Hamilton Ophthalmology Institute's Macular Edema, is presented. The proposed method achieves a precision of 0.95, 0.92, 0.97, accuracy of 0.98, 0.98, 0.98, sensitivity of 0.97, 0.95, 0.95, specificity of 0.99, 0.99, 0.99, and area under the curve of 0.97, 0.94, and 0.96, respectively. RESEARCH HIGHLIGHTS: The research focuses on the detection and segmentation of exudates in diabetic retinopathy, a disease affecting the retina. Early detection of exudates is important to avoid vision problems and requires continuous screening and treatment. Currently, manual detection is time-consuming and requires intense effort. The authors compare qualitative results of the state-of-the-art convolutional neural network (CNN) architectures and propose a computer-assisted diagnosis approach based on deep learning, using a residual CNN with residual skip connections to reduce parameters. The proposed method is evaluated on three benchmark databases and demonstrates high accuracy and suitability for diabetic retinopathy screening.

Hybrid morphological-convolutional neural networks for computer-aided diagnosis

Training deep Convolutional Neural Networks (CNNs) presents challenges in terms of memory requirements and computational resources, often resulting in issues such as model overfitting and lack of generalization. These challenges can only be mitigated by using an excessive number of training images. However, medical image datasets commonly suffer from data scarcity due to the complexities involved in their acquisition, preparation, and curation. To address this issue, we propose a compact and hybrid machine learning architecture based on the Morphological and Convolutional Neural Network (MCNN), followed by a Random Forest classifier. Unlike deep CNN architectures, the MCNN was specifically designed to achieve effective performance with medical image datasets limited to a few hundred samples. It incorporates various morphological operations into a single layer and uses independent neural networks to extract information from each signal channel. The final classification is obtained by utilizing a Random Forest classifier on the outputs of the last neural network layer. We compare the classification performance of our proposed method with three popular deep CNN architectures (ResNet-18, ShuffleNet-V2, and MobileNet-V2) using two training approaches: full training and transfer learning. The evaluation was conducted on two distinct medical image datasets: the ISIC dataset for melanoma classification and the ORIGA dataset for glaucoma classification. Results demonstrate that the MCNN method exhibits reliable performance in melanoma classification, achieving an AUC of 0.94 (95% CI: 0.91 to 0.97), outperforming the popular CNN architectures. For the glaucoma dataset, the MCNN achieved an AUC of 0.65 (95% CI: 0.53 to 0.74), which was similar to the performance of the popular CNN architectures. This study contributes to the understanding of mathematical morphology in shallow neural networks for medical image classification and highlights the potential of hybrid architectures in effectively learning from medical image datasets that are limited by a small number of case samples.

C2FTFNet: Coarse-to-fine transformer network for joint optic disc and cup segmentation

Glaucoma is a leading cause of worldwide blindness and visual impairment, making early screening and diagnosis is crucial to prevent vision loss. Cup-to-Disk Ratio (CDR) evaluation serves as a widely applied approach for effective glaucoma screening. At present, deep learning methods have exhibited outstanding performance in optic disk (OD) and optic cup (OC) segmentation and maturely deployed in CAD system. However, owning to the complexity of clinical data, these techniques could be constrained. Therefore, an original Coarse-to-Fine Transformer Network (C2FTFNet) is designed to segment OD and OC jointly , which is composed of two stages. In the coarse stage, to eliminate the effects of irrelevant organization on the segmented OC and OD regions, we employ U-Net and Circular Hough Transform (CHT) to segment the Region of Interest (ROI) of OD. Meanwhile, a TransUnet3+ model is designed in the fine segmentation stage to extract the OC and OD regions more accurately from ROI. In this model, to alleviate the limitation of the receptive field caused by traditional convolutional methods, a Transformer module is introduced into the backbone to capture long-distance dependent features for retaining more global information. Then, a Multi-Scale Dense Skip Connection (MSDC) module is proposed to fuse the low-level and high-level features from different layers for reducing the semantic gap among different level features. Comprehensive experiments conducted on DRIONS-DB, Drishti-GS, and REFUGE datasets validate the superior effectiveness of the proposed C2FTFNet compared to existing state-of-the-art approaches.

Retinal vessel segmentation via a Multi-resolution Contextual Network and adversarial learning

Timely and affordable computer-aided diagnosis of retinal diseases is pivotal in precluding blindness. Accurate retinal vessel segmentation plays an important role in disease progression and diagnosis of such vision-threatening diseases. To this end, we propose a Multi-resolution Contextual Network (MRC-Net) that addresses these issues by extracting multi-scale features to learn contextual dependencies between semantically different features and using bi-directional recurrent learning to model former-latter and latter-former dependencies. Another key idea is training in adversarial settings for foreground segmentation improvement through optimization of the region-based scores. This novel strategy boosts the performance of the segmentation network in terms of the Dice score (and correspondingly Jaccard index) while keeping the number of trainable parameters comparatively low. We have evaluated our method on three benchmark datasets, including DRIVE, STARE, and CHASE, demonstrating its superior performance as compared with competitive approaches elsewhere in the literature.

LUVS-Net: A Lightweight U-Net Vessel Segmentor for Retinal Vasculature Detection in Fundus Images

This paper presents LUVS-Net, which is a lightweight convolutional network for retinal vessel segmentation in fundus images that is designed for resource-constrained devices that are typically unable to meet the computational requirements of large neural networks. The computational challenges arise due to low-quality retinal images, wide variance in image acquisition conditions and disparities in intensity. Consequently, the training of existing segmentation methods requires a multitude of trainable parameters for the training of networks, resulting in computational complexity. The proposed Lightweight U-Net for Vessel Segmentation Network (LUVS-Net) can achieve high segmentation performance with only a few trainable parameters. This network uses an encoder–decoder framework in which edge data are transposed from the first layers of the encoder to the last layer of the decoder, massively improving the convergence latency. Additionally, LUVS-Net’s design allows for a dual-stream information flow both inside as well as outside of the encoder–decoder pair. The network width is enhanced using group convolutions, which allow the network to learn a larger number of low- and intermediate-level features. Spatial information loss is minimized using skip connections, and class imbalances are mitigated using dice loss for pixel-wise classification. The performance of the proposed network is evaluated on the publicly available retinal blood vessel datasets DRIVE, CHASE_DB1 and STARE. LUVS-Net proves to be quite competitive, outperforming alternative state-of-the-art segmentation methods and achieving comparable accuracy using trainable parameters that are reduced by two to three orders of magnitude compared with those of comparative state-of-the-art methods.