FIGURE 9 - available via license: Creative Commons Attribution 4.0 International
Content may be subject to copyright.
Source publication
Recent advancements in deep learning architectures have extended their application to computer vision tasks, one of which is the segmentation of retinal blood vessels from retinal fundus images. This is a problem that has piqued researchers’ interest in recent times. This paper presents a review of the taxonomy and analysis of enhancement technique...
Context in source publication
Citations
... Retinal vessel segmentation can be used to characterize the morphology of retinal vessels, such as length, width, branches pattern and angle. Current medical research suggests that retinal vasculopathy may precede cardiovascular diseases, such as hypertension, coronary artery disease, and diabetes, and that retinal vessel segmentation can be used as a basis for diagnosing related diseases [1][2][3][4][5]. However, the complex distribution and trend of blood vessels in the retina, the large variation in size and the interference of lesions, as well as the low illumination and imaging resolution of fundus cameras, make it difficult to completely segment retinal vessels [6]. ...
Retinal vessel segmentation is critical for diagnosing related diseases in the medical field. However, the complex structure and variable size and shape of retinal vessels make segmentation challenging. To enhance feature extraction capabilities in existing algorithms, we propose PAM-UNet, a U-shaped network architecture incorporating a novel Plenary Attention Mechanism (PAM). In the BottleNeck stage of the network, PAM identifies key channels and embeds positional information, allowing spatial features within significant channels to receive more focus. We also propose a new regularization method, DropBlock_Diagonal, which discards diagonal regions of the feature map to prevent overfitting and enhance vessel feature learning. Within the decoder stage of the network, features from each stage are merged to enhance the segmentation accuracy of the final vessel. Experimental validation on two retinal image datasets, DRIVE and CHASE_DB1, shows that PAM-UNet achieves 97.15%, 83.16%, 98.45%, 83.15%, 98.66% and 97.64%, 85.82%, 98.46%, 82.56%, 98.95% on Acc, Se, Sp, F1, AUC, respectively, outperforming UNet and most other retinal vessel segmentation algorithms.
... Early diagnosis and regular eye examinations are key steps in the prevention and treatment of these diseases, and the application of retinal vascular segmentation technology is gaining increasing attention in this field, providing physicians with a precise and efficient tool to help detect and intervene earlier in these diseases, thereby protecting the visual health of patients. However, blood vessels are complex and varied globally, thin and fragile locally, and easy to fracture [4]. Therefore, automatic segmentation of blood vessels is a challenging task, especially for the accurate segmentation of thin blood vessels and their marginal parts [5]. ...
The precise segmentation of retinal vasculature is crucial for the early screening of various eye diseases, such as diabetic retinopathy and hypertensive retinopathy. Given the complex and variable overall structure of retinal vessels and their delicate, minute local features, the accurate extraction of fine vessels and edge pixels remains a technical challenge in the current research. To enhance the ability to extract thin vessels, this paper incorporates a pyramid channel attention module into a U-shaped network. This allows for more effective capture of information at different levels and increased attention to vessel-related channels, thereby improving model performance. Simultaneously, to prevent overfitting, this paper optimizes the standard convolutional block in the U-Net with the pre-activated residual discard convolution block, thus improving the model’s generalization ability. The model is evaluated on three benchmark retinal datasets: DRIVE, CHASE_DB1, and STARE. Experimental results demonstrate that, compared to the baseline model, the proposed model achieves improvements in sensitivity (Sen) scores of 7.12%, 9.65%, and 5.36% on these three datasets, respectively, proving its strong ability to extract fine vessels.
... Real-time medical image analysis can help clinicians to improve diagnosis and decisions, such as in blood vessel segmentation, which is used extensively in retinal images Sule (2022) and coronary artery imaging Carballal et al (2018). Machine learning (ML) models Liskowski and Krawiec (2016) (2015), encoder-decoder architectures, residual skip connections He et al (2016), and attention mechanisms Bahdanau et al (2014). ...
... It can assist in the extraction of significant information regarding the body organ's condition. For this reason, image processing algorithms and ML methods for blood vessel segmentation has been extensively researched Fraz et al (2012); Moccia et al (2018);Sule (2022). ...
Machine learning offers the potential to enhance real-time image analysis in surgical operations. This paper presents results from the implementation of machine learning algorithms targeted for an intelligent image processing system comprising a custom CMOS image sensor and field programmable gate array (FPGA). A novel method is presented for efficient image segmentation and minimises energy usage and requires low memory resources, which makes it suitable for implementation. Using two eigenvalues of the enhanced Hessian image, simplified traditional machine learning and deep learning methods are employed to learn the prediction of blood vessels. Quantitative comparisons are provided between different machine learning models based on accuracy, resource utilisation, throughput, and power usage. It is shown how a gradient boosting decision tree with 1000 times fewer parameters can achieve comparable state-of-the-art performance whilst only using a much smaller proportion of the resources and producing a 200 MHz design that operates at 1,779 frames per second at 3.85 W, making it highly suitable for the proposed system. A methodology for implementing the AI algorithms onto FPGA is presented and then used to provide additional results by extending the original work to a 512 × 512 image size along with more detailed analysis.
... Benefiting from the influence of data-driven approaches and innovations in computing devices, deep learning methods have made significant progress in retinal vessel segmentation [9,10]. By leveraging the outstanding automatic feature learning and end-to-end learning capabilities of deep neural networks (DNNs), the accuracy of retinal vessel segmentation has been significantly improved [11][12][13]. Especially, after the introduction of the landmark U-Net architecture [14], various outstanding variants for vessel segmentation have emerged [15][16][17]. Despite achieving good segmentation results based on evaluation metrics, these approaches still face challenges in accurately segmenting fine vessels within complex backgrounds. ...
Accurate and automated retinal vessel segmentation is essential for performing diagnosis and surgical planning of retinal diseases. However, conventional U-shaped networks often suffer from segmentation errors when dealing with fine and low-contrast blood vessels due to the loss of continuous resolution in the encoding stage and the inability to recover the lost information in the decoding stage. To address this issue, this paper introduces an effective full-resolution retinal vessel segmentation network, namely FRD-Net, which consists of two core components: the backbone network and the multi-scale feature fusion module (MFFM). The backbone network achieves horizontal and vertical expansion through the interaction mechanism of multi-resolution dilated convolutions while preserving the complete image resolution. In the backbone network, the effective application of dilated convolutions with varying dilation rates, coupled with the utilization of dilated residual modules for integrating multi-scale feature maps from adjacent stages, facilitates continuous learning of multi-scale features to enhance high-level contextual information. Moreover, MFFM further enhances segmentation by fusing deeper multi-scale features with the original image, facilitating edge detail recovery for accurate vessel segmentation. In tests on multiple classical datasets,compared to state-of-the-art segmentation algorithms, FRD-Net achieves superior performance and generalization with fewer model parameters.
... Addressing these challenges requires the development of robust segmentation algorithms that can handle variations in vessel appearance, structure, and imaging conditions. Thresholding [3,4], edgebased techniques [5,6], mathematical morphology [7,8], graph-based techniques [9], machine learning [10], and deep learning [11] are a few methods used to accurately segment blood vessels. Machine learning techniques such as SVM [12], Random Forest [13], and CNN [14] have shown promising results in segmentation. ...
Delineation of retinal vessels in fundus images is essential for detecting a range of eye disorders. An automated technique for vessel segmentation can assist clinicians and enhance the efficiency of the diagnostic process. Traditional methods fail to extract multiscale information, discard unnecessary information, and delineate thin vessels. In this paper, a novel residual U-Net architecture that incorporates multi-scale feature learning and effective attention is proposed to delineate the retinal vessels precisely. Since drop block regularization performs better than drop out in preventing overfitting, drop block was used in this study. A multi-scale feature learning module was added instead of a skip connection to learn multi-scale features. A novel effective attention block was proposed and integrated with the decoder block to obtain precise spatial and channel information. Experimental findings indicated that the proposed model exhibited outstanding performance in retinal vessel delineation. The sensitivities achieved for DRIVE, STARE, and CHASE_DB datasets were 0.8293, 0.8151 and 0.8084, respectively.
... The presence of microvascular features and the generation of retinal neovascularization significantly affect the diagnosis of Dr Early-stage DR may not cause any symptoms, while late-stage retinal damage is irreversible (Tsiknakis et al 2021). Currently, DR diagnosis relies mainly on manual screening, which is laborious, time-consuming, and subject to interobserver variability (Sule 2022). ...
... Ensemble models have been widely applied due to the development of machine learning and have demonstrated superiority over individual machine learning models in various fields (S K S 2017, Jagan Mohan et al 2021, Kale and Sharma 2023). However, researchers in previous studies directly applied deep learning methods for the classification of retinal images, and ensemble models have not been fully utilized in the field of DR detection (Sule 2022). This study proposes a deep learning system for DR classification to better demonstrate the role of retinal features in retinal lesions and achieve accurate machine learning predictions. ...
Object: The existing diagnostic paradigm for diabetic retinopathy (DR) greatly relies on subjective assessments by medical practitioners utilizing optical imaging, introducing susceptibility to individual interpretation. This work presents a novel system for the early detection and grading of DR, providing an automated alternative to the manual examination. Approach: First, we use advanced image preprocessing techniques, specifically contrast-limited adaptive histogram equalization and Gaussian filtering, with the goal of enhancing image quality and module learning capabilities. Second, a deep learning-based automatic detection system is developed. The system consists of a feature segmentation module, a deep learning feature extraction module, and an ensemble classification module. The feature segmentation module accomplishes vascular segmentation, the deep learning feature extraction module realizes the global feature and local feature extraction of retinopathy images, and the ensemble module performs the diagnosis and classification of DR for the extracted features. Lastly, nine performance evaluation metrics are applied to assess the quality of the model’s performance. Main results: Extensive experiments are conducted on four retinal image databases (APTOS 2019, Messidor, DDR, and EyePACS). The proposed method demonstrates promising performance in the binary and multi-classification tasks for DR, evaluated through nine indicators, including AUC and quadratic weighted Kappa score. The system shows the best performance in the comparison of three segmentation methods, two convolutional neural network architecture models, four Swin Transformer structures, and the latest literature methods. Significance: In contrast to existing methods, our system demonstrates superior performance across multiple indicators, enabling accurate screening of DR and providing valuable support to clinicians in the diagnostic process. Our automated approach minimizes the reliance on subjective assessments, contributing to more consistent and reliable DR evaluations.
... However, in the literature very few evidence is available that explores the impact of image enhancement techniques on performance of the model. Olubunmi Sule [7] has made comprehensive survey of deep learning techniques for the segmentation of retinal fundus images. This article has concluded that the U-Net architecture is most promising architecture. ...
Medical images captured through various imaging modalities are key to the diagnosis and treatment of diseases, and these images serve as a major input to AI driven models but due to the scarcity of medical experts and their quality research time, the quantum of data required for AI models is limited. Moreover, medical image analysis is a laborious and error prone task. Early detection of retinal diseases by means of AI based semantic segmentation model has been boon to the diagnostic system. However, performing semantic segmentation with limited data of retinal fundus image is quite challenging. The present study is primarily focused on investigation of effectiveness of data augmentation with gamma corrected images to alleviate the problem of limited annotated data in deep learning models. The most widely accepted U-Net model in medical domain for image segmentation is trained employing retinal fundus image dataset augmented with gamma corrected images on all image channels and then tested against major publicly available datasets. The proposed method has outperformed other complex contemporary methods in terms of sensitivity and has also shown better generalizability across datasets from different institutions.
... At the initial stage, DR does not show any symptoms or minor vision impairment in the body parts. The symptoms of DR include blurred or color vision impairment and dark strings, which occur in the float of the patient's vision (Sule, 2022;Ullah et al., 2023). DR can be diagnosed with the help of a laser or through a surgical procedure known as vitrectomy which inhibits the changes and helps to retain the vision. ...
Diabetic Retinopathy (DR) is a major type of eye defect that is caused by abnormalities in the blood vessels within the retinal tissue. Early detection by automatic approach using modern methodologies helps prevent consequences like vision loss. So, this research has developed an effective segmentation approach known as Level-set Based Adaptive-active Contour Segmentation (LBACS) to segment the images by improving the boundary conditions and detecting the edges using Level Set Method with Improved Boundary Indicator Function (LSMIBIF) and Adaptive-Active Counter Model (AACM). For evaluating the DR system, the information is collected from the publically available datasets named as Indian Diabetic Retinopathy Image Dataset (IDRiD) and Diabetic Retinopathy Database 1 (DIARETDB 1). Then the collected images are pre-processed using a Gaussian filter, edge detection sharpening, Contrast enhancement, and Luminosity enhancement to eliminate the noises/interferences, and data imbalance that exists in the available dataset. After that, the noise-free data are processed for segmentation by using the Level set-based active contour segmentation technique. Then, the segmented images are given to the feature extraction stage where Gray Level Co-occurrence Matrix (GLCM), Local ternary, and binary patterns are employed to extract the features from the segmented image. Finally, extracted features are given as input to the classification stage where Long Short-Term Memory (LSTM) is utilized to categorize various classes of DR. The result analysis evidently shows that the proposed LBACS-LSTM achieved better results in overall metrics. The accuracy of the proposed LBACS-LSTM for IDRiD and DIARETDB 1 datasets is 99.43% and 97.39%, respectively which is comparably higher than the existing approaches such as Three-dimensional semantic model, Delimiting Segmentation Approach Using Knowledge Learning (DSA-KL), K-Nearest Neighbor (KNN), Computer aided method and Chronological Tunicate Swarm Algorithm with Stacked Auto Encoder (CTSA-SAE).
... The choroid is where blood vessels develop. Many scientific research projects have introduced DL models for segmenting the retinal blood vessels, such as convolutional neural network (CNN), artificial neural network (ANN), auto-encoders (AEs), fully convolutional networks (FCN), and U-Net [31,32]. During the analysis of medical images, the U-Net design is considered a great and powerful architecture, especially in relation to retinal vascular segmentation. ...
Retinal blood vessel segmentation is a valuable tool for clinicians to diagnose conditions such as atherosclerosis, glaucoma, and age-related macular degeneration. This paper presents a new framework for segmenting blood vessels in retinal images. The framework has two stages: a multi-layer preprocessing stage and a subsequent segmentation stage employing a U-Net with a multi-residual attention block. The multi-layer preprocessing stage has three steps. The first step is noise reduction, employing a U-shaped convolutional neural network with matrix factorization (CNN with MF) and detailed U-shaped U-Net (D_U-Net) to minimize image noise, culminating in the selection of the most suitable image based on the PSNR and SSIM values. The second step is dynamic data imputation, utilizing multiple models for the purpose of filling in missing data. The third step is data augmentation through the utilization of a latent diffusion model (LDM) to expand the training dataset size. The second stage of the framework is segmentation, where the U-Nets with a multi-residual attention block are used to segment the retinal images after they have been preprocessed and noise has been removed. The experiments show that the framework is effective at segmenting retinal blood vessels. It achieved Dice scores of 95.32, accuracy of 93.56, precision of 95.68, and recall of 95.45. It also achieved efficient results in removing noise using CNN with matrix factorization (MF) and D-U-NET according to values of PSNR and SSIM for (0.1, 0.25, 0.5, and 0.75) levels of noise. The LDM achieved an inception score of 13.6 and an FID of 46.2 in the augmentation step.
... Transfer-learningbased FCNs were suggested for retinal vessel segmentation in [44]. Furthermore, a comprehensive review of multiple CNN-based retinal vessel segmentation networks is presented in [45]. These diverse strategies and studies exemplify the ongoing dedication and progress in segmentation of the retinal vessels, aimed at improving medical diagnosis and treatment. ...
Blinding eye diseases are often correlated with altered retinal morphology, which can be clinically identified by segmenting retinal structures in fundus images. However, current methodologies often fall short in accurately segmenting delicate vessels. Although deep learning has shown promise in medical image segmentation, its reliance on repeated convolution and pooling operations can hinder the representation of edge information, ultimately limiting overall segmentation accuracy. In this paper, we propose a lightweight pixel-level CNN named LMBiS-Net for the segmentation of retinal vessels with an exceptionally low number of learnable parameters \textbf{(only 0.172 M)}. The network used multipath feature extraction blocks and incorporates bidirectional skip connections for the information flow between the encoder and decoder. Additionally, we have optimized the efficiency of the model by carefully selecting the number of filters to avoid filter overlap. This optimization significantly reduces training time and enhances computational efficiency. To assess the robustness and generalizability of LMBiS-Net, we performed comprehensive evaluations on various aspects of retinal images. Specifically, the model was subjected to rigorous tests to accurately segment retinal vessels, which play a vital role in ophthalmological diagnosis and treatment. By focusing on the retinal blood vessels, we were able to thoroughly analyze the performance and effectiveness of the LMBiS-Net model. The results of our tests demonstrate that LMBiS-Net is not only robust and generalizable but also capable of maintaining high levels of segmentation accuracy. These characteristics highlight the potential of LMBiS-Net as an efficient tool for high-speed and accurate segmentation of retinal images in various clinical applications.
