A Novel Dual-supervised Convolutional Network for Retinal Vessel Segmentation

Purpose Retinal blood vessel image segmentation is an important step in ophthalmological analysis. However, it is difficult to segment small vessels accurately because of low contrast and complex feature information of blood vessels. The objective of this study is to develop an improved retinal blood vessel segmentation structure (WA-Net) to overcome these challenges. Methods This paper mainly focuses on the width of deep learning. The channels of the ResNet block were broadened to propagate more low-level features, and the identity mapping pathway was slimmed to maintain parameter complexity. A residual atrous spatial pyramid module was used to capture the retinal vessels at various scales. We applied weight normalization to eliminate the impacts of the mini-batch and improve segmentation accuracy. The experiments were performed on the DRIVE and STARE datasets. To show the generalizability of WA-Net, we performed cross-training between datasets. Results The global accuracy and specificity within datasets were 95.66% and 96.45% and 98.13% and 98.71%, respectively. The accuracy and area under the curve of the interdataset diverged only by 1%∼2% compared with the performance of the corresponding intradataset. Conclusion All the results show that WA-Net extracts more detailed blood vessels and shows superior performance on retinal blood vessel segmentation tasks.

Retinal fundus image is a crucial tool for ophthalmologists to diagnose eye-related diseases. These images provide visual information of the interior layer of the retina structures such as optic disc, optic cup, blood vessels and macula that can assist ophthalmologist in determining the health of an eye. Segmentation of blood vessels in fundus images is one of the most fundamental phase in detecting diseases such as diabetic retinopathy. However, the ambiguity of the retina structures in the retinal fundus images presents a challenge for researcher to segment the blood vessels. Extensive pre-processing and training of the images is necessary for precise segmentation, which is very intricate and laborious. This paper proposes the implementation of object-oriented-based metadata (OOM) structures of each pixel in the retinal fundus images. These structures comprise of additional metadata towards the conventional red, green, and blue data for each pixel within the images. The segmentation of the blood vessels in the retinal fundus images are performed by considering these additional metadata that enunciates the location, color spaces, and neighboring pixels of each individual pixel. From the results, it is shown that accurate segmentation of retinal fundus blood vessels can be achieved by purely employing straightforward thresholding method via the OOM structures without extensive pre-processing image processing technique or data training.

Fractional and B-COSFIRE filter based approach for efficient segmentation of retinal blood vessels

An efficient retinal blood vessel segmentation in eye fundus images by using optimized top-hat and homomorphic filtering

<span>Segmentation of blood vessels (BVs) from retinal image is one of the important steps in developing a computer-assisted retinal diagnosis system and has been widely researched especially for implementing automatic BV segmentation methods. This paper proposes an improvement to an existing retinal BV (RBV) segmentation method by combining the trainable B-COSFIRE filter with adaptive thresholding methods. The proposed method can automatically configure its selectivity given a prototype pattern to be detected. Its segmentation performance is comparable to many published methods with the advantage of robustness against noise on retinal background. Instead of using grid search to find the optimal threshold value for a whole dataset, adaptive thresholding (AT) is used to determine the threshold for each retinal image. Two AT methods investigated in this study were ISODATA and Otsu’s method. The proposed method was validated using 40 images from two benchmark datasets for retinal BV segmentation validation, namely DRIVE and STARE. The validation results indicated that the segmentation performance of the proposed unsupervised method is comparable to the original B-COSFIRE method and other published methods, without requiring the availability of ground truth data for new dataset. The Sensitivity and Specificity values achieved for DRIVE and STARE are 0.7818, 0.9688, 0.7957 and 0.9648, respectively.</span>

Automated retinal blood vessel segmentation in fundus images provides important evidence to ophthalmologists in coping with prevalent ocular diseases in an efficient and non-invasive way. However, segmenting blood vessels in fundus images is a challenging task, due to the high variety in scale and appearance of blood vessels and the high similarity in visual features between the lesions and retinal vascular. Inspired by the way that the visual cortex adaptively responds to the type of stimulus, we propose a Stimulus-Guided Adaptive Transformer Network (SGAT-Net) for accurate retinal blood vessel segmentation. It entails a Stimulus-Guided Adaptive Module (SGA-Module) that can extract local-global compound features based on inductive bias and self-attention mechanism. Alongside a light-weight residual encoder (ResEncoder) structure capturing the relevant details of appearance, a Stimulus-Guided Adaptive Pooling Transformer (SGAP-Former) is introduced to reweight the maximum and average pooling to enrich the contextual embedding representation while suppressing the redundant information. Moreover, a Stimulus-Guided Adaptive Feature Fusion (SGAFF) module is designed to adaptively emphasize the local details and global context and fuse them in the latent space to adjust the receptive field (RF) based on the task. The evaluation is implemented on the largest fundus image dataset (FIVES) and three popular retinal image datasets (DRIVE, STARE, CHASEDB1). Experimental results show that the proposed method achieves a competitive performance over the other existing method, with a clear advantage in avoiding errors that commonly happen in areas with highly similar visual features. The sourcecode is publicly available at: https://github.com/Gins-07/SGAT.

For proper diagnosis and treatment of various retinal conditions, retinal blood vessel segmentation is crucial. Delineation of vessels with varying thicknesses is critical for detecting disease symptoms. However, this task is challenging due to inadequate contextual information, complex vessel morphology, and lesion confusion. Many recent works employed several variations of CNNs with U-Net as baseline model for segmenting blood vessels from the fundus images. However, the existing methods still lack in generalizing the vessels well enough, indicating scope for improvement in this challenging problem of vessel segmentation. We introduce a novel Multi-Scale Residual (MSR) U-Net model in this study replacing convolution block and skip connections with an improved Multi-Scale Residual (MSR) convolution block and Bottleneck residual paths (B-Res paths) respectively. Specifically, STARE, DRIVE, and CHASE_DB1 datasets of fundus images are used to validate the proposed segmentation method. Our experimental results consistently showcase better/comparable performances when compared with current approaches, achieving higher area under receiver operator characteristic (AUC), accuracy, and F1 score. in segmenting blood vessels of varying thicknesses, even in scenarios with diverse contextual information, the presence of coexisting lesions, and complex vessel morphologies.

Automated retinal blood vessel segmentation is a fundamental component in computer aided retinal disease screening system and diagnosis. This paper presents a novel method of Hausdorff symmetry operator for automatic centerline pixel selection towards retinal blood vessel segmentation. Centerline pixels are determined by considering geometrical symmetry (distance and orientation) and Hausdorff distance based point set matching at the centerline pixel. This is performed in subpixel resolution to achieve higher accuracy. Then K-means clustering is applied to remove false centerline pixels. The selected centerline pixels act as seed points to be used in region growing to segment the retinal blood vessels. Our proposed method is evaluated on DRIVE and STARE databases. The experimental results demonstrate that the performance of the proposed method is comparable with state-of-the-art techniques. The advantages of the proposed method include its ability to correctly segment thin blood vessels, vessels containing light reflex, and disc area is not misclassified as vessels.

Contents Abstract Acknowledgements 1 Introduction 1.1 Motivation 1.2 Summary of main achievements 1.3 Publications 1.4 Overview of the thesis 2 Background 2.1 Computational and mathematical approaches for retinal feature extraction 2.1.1 Basics and Notations 2.1.2 Scale-space representation of image data 2.1.3 Coherence enhancing diffusion 2.1.4 Hessian based vesselness for vessel segmentation 2.1.5 Optimally oriented flux as a descriptor for tubular structures 2.1.6 Thin plate spline 2.2 Anterior visual system 2.2.1 Visual pathway 2.2.2 Retina anatomy and structures 2.2.3 Retinal blood supply 2.2.4 Optic nerve head 2.3 Retinal imaging techniques 2.3.1 Fundus photography 2.3.2 Stereo fundus photography 2.3.3 Confocal scanning laser ophthalmoscopy 2.3.4 Heidelberg retina tomograph 2.3.5 Optical coherence tomography. 2.4 Retina in neurological disorders and OCT parameters 2.4.1 Retina in MS 2.4.2 Retina in NMOSD 2.4.3 Retina in IIH 2.5 Data and optical coherence tomography device used in our research 3 Retinal blood vessel segmentation 3.1 Previous approaches in retinal blood vessel segmentation 3.2 Semi-automated tool for detection of blood vessel inner and outer diameter in cSLOimages 3.2.1 Double- Gaussian profile analysis 3.2.2 Validation 3.2.3 Results of a clinical study 3.3 Automated detection of the entire retinal vasculature in cSLO images 3.3.1 Approach 1. Extended 2D Morlet filtering with principal curvature enhancement 3.3.2 Approach 2. Improved vesselness response at vessel crossings 3.3.3 Approach3. New vesselness response based on OOF 3.3.4 Experimental results 4 RPE lower boundary segmentation for ONH volume computation 4.1 Previous approaches in RPE lower boundary segmentation 4.2 Algorithm description 4.2.1 RPE Region 4.2.2 RPE Initial Pixels 4.2.3 RPE Curve 4.3 Validation 4.4 Results of two clinical studies 5 BMO points detection for ONH center and ONH volume computation 5.1 Previous approaches in ONH volume computation 5.2 Algorithm description 5.2.1 Detection of ILM, ONL, and RPE lower boundary 5.2.2 Modified TPS fitting 5.2.3 Volume reduction 5.2.4 Vessel suppression 5.2.5 BMO points detection using textural information in a grow-cut setting 5.3 Validation 5.4 Results of a clinical study 6 Discussion 6.1 Semi-automated tool for detection of blood vessel inner and outer diameter in cSLOimages 6.2 Detection of the entire retinal vasculature in cSLO images 6.3 RPE lower boundary segmentation for ONH volume computation 6.4 BMO points detection for ONH center and ONH volume computation 7 Conclusion and Outlook Bibliography Selbstandigkeitserklarung Zusammenfassung

FRE-GAN : Full-resolution efficient convolutional generative adversarial network for retinal vessel segmentation.

Assessment of blood vessels in retinal images is an important factor for many medical disorders. The changes in the retinal vessels due to the pathologies can be easily identified by segmenting the retinal vessels. Segmentation of retinal vessels is done to identify the early diagnosis of the disease like glaucoma, diabetic retinopathy, macular degeneration, hypertensive retinopathy and arteriosclerosis. In this paper, we propose two automatic blood vessel segmentation methods. The first proposed algorithm starts with the extraction of blood vessel centerline pixels. The final segmentation is obtained using an iterative region growing method that merges the contents of several binary images resulting from vessel width dependent modified morphological filters on normalized retinal images. In the second proposed algorithm the blood vessel is segmented using normalized modified morphological operations and neuro fuzzy classifier. Normalized morphological operations are used to enhance the vessels and neuro fuzzy classifier is used to segment retinal blood vessels. These methods are applied on the publicly available DRIVE database and the experimental results obtained by using green channel images have been presented and their results are compared with recently published methods. The results demonstrate that our algorithms are very effective methods to detect retinal blood vessels. DOI: http://dx.doi.org/10.11591/ijece.v4i3.5829

Accurate segmentation of retinal blood vessels plays a vital role in medical image analysis for the diagnosis and management of eye diseases, as most health conditions affect the retinal vascular network.Despite progress made in recent decades, issues such as complex textures, vessel discontinuities, and unidentified areas remain unresolved, particularly in segmenting fine veins and handling low-contrast images.This method integrates three advanced techniques for retinal vessel segmentation.Initially, it applies Adaptive Gradient Domain Guided Image Filtering (AGD-GIF) for preprocessing.Subsequently, it utilizes an efficient feature extraction method called the proposed Cascading Residual Graph Convolutional Network (CRGCN).Finally, segmentation is performed using an enhanced Mask Region-Based Convolutional Neural Network with a Parrot Optimizer (Improved Mask R-CNN-PO), ensuring precision and reliability in detecting retinal vessels from medical images.When tested on the CHASE_DB1 datasets, the proposed model achieves specificity of 99.53%, accuracy of 99.65%, and an AUC of 99%.Additionally, it attains an accuracy of 99.63% and F1 scores of 99.59%.

In this research, retinal blood vessel fundus images will be segmented. Moreover, bifurcation point of the segmented blood vessel images will be determined. The data used for this research was obtained from fundus image database of DRIVE (Digital Retinal Images for Vessel Extraction) dataset. The preprocessing phases contain of several steps such as green channel extraction, histogram equalization and optic disc elimination. Meanwhile, the segmentation phase was performed by combining two filtering methods. These methods are median and derivative of Gaussian filter. Median filter was used to reduce the noise on retinal fundus image such as hard and soft exudates as well as dot and blot hemorrhages. Combination of these two filtering methods were also employed to determine the bifurcation point of segmented blood vessel image. The bifurcation points and the result from blood vessel segmentation were among two of the unique parameters of retinal fundus image. These parameters will be used eventually as unique features of the advanced research which is a biometric system to identify an individual based on his/her unique retinal pattern.

The retinal vessel segmentation task plays an important role in clinical diagnosis and treatment, especially in cardiovascular diseases such as diabetic retinopathy and hypertensive retinopathy. Recently, the fully convolutional neural network, as a popular learning-based segmentation method, has been demonstrated to yield highly segmentation performance in vessel wall segmentation tasks. However, the major network factors affecting the performance of segmentation are still not obvious. This paper uses the single-factor control variable method to investigates the effects of network architectures (FCN network and U-Net network) and other network factors (pooling times, patch size, number of skip connection, and network depth) on retinal blood vessel segmentation. Our experiments are performed on two public fundus image database DRIVE and STARE. The results show that U-net is better than FCN and skip connections, proper pooling times, dilated convolution is vital to obtain better performance of retinal vessel segmentation.

Segmentation of retinal blood vessels is an important diagnostic procedure in ophthalmology. In this paper we propose an automated blood vessels segmentation method that combines both supervised and un-supervised approaches. A novel descriptor named Local Haar Pattern (LHP) is proposed to describe retinal pixel of interest. The performance of the proposed method has been evaluated on three publicly available DRIVE, STARE and CHASE_DB1 datasets. The proposed method achieves an overall segmentation accuracy of 96%, 96% and 95% respectively on DRIVE, STARE, and CHASE DB1 datasets, which are better than the state-of-the-art methods.