MCFSA-Net: A multi-scale channel fusion and spatial activation network for retinal vessel segmentation

As the only vascular tissue that can be directly viewed in vivo, retinal vessels are medically important in assisting the diagnosis of ocular and cardiovascular diseases. They generally appear as different morphologies and uneven thickness in fundus images. Therefore, the single-scale segmentation method may fail to capture abundant morphological features, suffering from the deterioration in vessel segmentation, especially for tiny vessels. To alleviate this issue, we propose a multi-scale channel fusion and spatial activation network (MCFSA-Net) for retinal vessel segmentation with emphasis on tiny ones. Specifically, the Hybrid Convolution-DropBlock (HC-Drop) is first used to extract deep features of vessels and construct multi-scale feature maps by progressive down-sampling. Then, the Channel Cooperative Attention Fusion (CCAF) module is designed to handle different morphological vessels in a multi-scale manner. Finally, the Global Spatial Activation (GSA) module is introduced to aggregate global feature information for improving the attention on tiny vessels in the spatial domain and realizing effective segmentation for them. Experiments are carried out on three datasets including DRIVE, CHASE_DB1, and STARE. Our retinal vessel segmentation method achieves Accuracy of 96.95%, 97.57%, and 97.83%, and F1 score of 82.67%, 81.82%, and 82.95% in the above datasets, respectively. Qualitative and quantitative analysis show that the proposed method outperforms current advanced vessel segmentation methods, especially for tiny vessels.     

Accurate Image Analysis of the Retina Using Hessian Matrix and Binarisation of Thresholded Entropy with Application of Texture Mapping

In this paper, we demonstrate a comprehensive method for segmenting the retinal vasculature in camera images of the fundus. This is of interest in the area of diagnostics for eye diseases that affect the blood vessels in the eye. In a departure from other state-of-the-art methods, vessels are first pre-grouped together with graph partitioning, using a spectral clustering technique based on morphological features. Local curvature is estimated over the whole image using eigenvalues of Hessian matrix in order to enhance the vessels, which appear as ridges in images of the retina. The result is combined with a binarized image, obtained using a threshold that maximizes entropy, to extract the retinal vessels from the background. Speckle type noise is reduced by applying a connectivity constraint on the extracted curvature based enhanced image. This constraint is varied over the image according to each region''s predominant blood vessel size. The resultant image exhibits the central light reflex of retinal arteries and veins, which prevents the segmentation of whole vessels. To address this, the earlier entropy-based binarization technique is repeated on the original image, but crucially, with a different threshold to incorporate the central reflex vessels. The final segmentation is achieved by combining the segmented vessels with and without central light reflex. We carry out our approach on DRIVE and REVIEW, two publicly available collections of retinal images for research purposes. The obtained results are compared with state-of-the-art methods in the literature using metrics such as sensitivity (true positive rate), selectivity (false positive rate) and accuracy rates for the DRIVE images and measured vessel widths for the REVIEW images. Our approach out-performs the methods in the literature.     

Retinal Vessel Segmentation: An Efficient Graph Cut Approach with Retinex and Local Phase

Our application concerns the automated detection of vessels in retinal images to improve understanding of the disease mechanism, diagnosis and treatment of retinal and a number of systemic diseases. We propose a new framework for segmenting retinal vasculatures with much improved accuracy and efficiency. The proposed framework consists of three technical components: Retinex-based image inhomogeneity correction, local phase-based vessel enhancement and graph cut-based active contour segmentation. These procedures are applied in the following order. Underpinned by the Retinex theory, the inhomogeneity correction step aims to address challenges presented by the image intensity inhomogeneities, and the relatively low contrast of thin vessels compared to the background. The local phase enhancement technique is employed to enhance vessels for its superiority in preserving the vessel edges. The graph cut-based active contour method is used for its efficiency and effectiveness in segmenting the vessels from the enhanced images using the local phase filter. We have demonstrated its performance by applying it to four public retinal image datasets (3 datasets of color fundus photography and 1 of fluorescein angiography). Statistical analysis demonstrates that each component of the framework can provide the level of performance expected. The proposed framework is compared with widely used unsupervised and supervised methods, showing that the overall framework outperforms its competitors. For example, the achieved sensitivity (0:744), specificity (0:978) and accuracy (0:953) for the DRIVE dataset are very close to those of the manual annotations obtained by the second observer.     

应用深度学习分割光学显微镜下的细胞图像

目的 为了在细胞培养过程中便捷地分析细胞的数目和形态.方法 本文将深度学习应用到细胞识别中,实现了一种可以通过普通光学显微镜拍照,并直接在培养皿中进行细胞识别计数的方法.结果 通过构建U-Net网络结构,并对贴壁细胞和悬浮细胞图像进行标记训练,来实现贴壁细胞和悬浮细胞的分割计数.同时,用该算法绘制细胞生长曲线以及计算抑...     

A New Approach to Segment Both Main and Peripheral Retinal Vessels Based on Gray-Voting and Gaussian Mixture Model

Vessel segmentation in retinal fundus images is a preliminary step to clinical diagnosis for some systemic diseases and some eye diseases. The performances of existing methods for segmenting small vessels which are usually of more importance than the main vessels in a clinical diagnosis are not satisfactory in clinical use. In this paper, we present a method for both main and peripheral vessel segmentation. A local gray-level change enhancement algorithm called gray-voting is used to enhance the small vessels, while a two-dimensional Gabor wavelet is used to extract the main vessels. We fuse the gray-voting results with the 2D-Gabor filter results as pre-processing outcome. A Gaussian mixture model is then used to extract vessel clusters from the pre-processing outcome, while small vessels fragments are obtained using another gray-voting process, which complements the vessel cluster extraction already performed. At the last step, we eliminate the fragments that do not belong to the vessels based on the shape of the fragments. We evaluated the approach with two publicly available DRIVE (Staal et al., 2004) and STARE (Hoover et at., 2000) datasets with manually segmented results. For the STARE dataset, when using the second manually segmented results which include much more small vessels than the first manually segmented results as the “gold standard,” this approach achieved an average sensitivity, accuracy and specificity of 65.0%, 92.1% and 97.0%, respectively. The sensitivities of this approach were much higher than those of the other existing methods, with comparable specificities; these results thus demonstrated that this approach was sensitive to detection of small vessels.     

GVC-Net: Global Vascular Context Network for Cerebrovascular Segmentation Using Sparse Labels

ObjectivesCerebrovascular disease is a serious threat to human health. Because of its high mortality and disability rate, early diagnosis and prevention are very important. The performance of existing cerebrovascular segmentation methods based on deep learning depends on the integrity of labels. However, manual labels are usually of low quality and poor connectivity at small blood vessels, which directly affects the cerebrovascular segmentation results.Material and methodIn this paper, we propose a new segmentation network to segment cerebral vessels from MRA images by using sparse labels. The long-distance dependence between vascular structures is captured by the global vascular context module, and the topology is constrained by the hybrid loss function to segment the cerebral vessels with good connectivity.ResultExperiments show that our method performed with a sensitivity, precision, dice similarity coefficient, intersection over union and centerline dice similarity coefficient of 61.24%, 75.58%, 67.66%, 51.13% and 83.79% respectively.ConclusionThe obtained results reveal that the proposed cerebrovascular segmentation network has better segmentation performance for cerebrovascular segmentation under sparse labels, and can suppress the noise of background to a certain extent.     

Clinicopathological and immunohistochemical study of 29 cases of solid-pseudopapillary neoplasms of the pancreas in patients under 20 years of age along with detailed review of literature

Background

Multiplex immunohistochemistry (mIHC) permits the labeling of six or more distinct cell types within a single histologic tissue section. The classification of each cell type requires detection of uniquely colored chromogens localized to cells expressing biomarkers of interest. The most comprehensive and reproducible method to evaluate such slides is to employ digital pathology and image analysis pipelines to whole-slide images (WSIs). Our suite of deep learning tools quantitatively evaluates the expression of six biomarkers in mIHC WSIs. These methods address the current lack of readily available methods to evaluate more than four biomarkers and circumvent the need for specialized instrumentation to spectrally separate different colors. The use case application for our methods is a study that investigates tumor immune interactions in pancreatic ductal adenocarcinoma (PDAC) with a customized mIHC panel.

Methods

Six different colored chromogens were utilized to label T-cells (CD3, CD4, CD8), B-cells (CD20), macrophages (CD16), and tumor cells (K17) in formalin-fixed paraffin-embedded (FFPE) PDAC tissue sections. We leveraged pathologist annotations to develop complementary deep learning-based methods: (1) ColorAE is a deep autoencoder which segments stained objects based on color; (2) U-Net is a convolutional neural network (CNN) trained to segment cells based on color, texture and shape; and (3) ensemble methods that employ both ColorAE and U-Net, collectively referred to as ColorAE:U-Net. We assessed the performance of our methods using: structural similarity and DICE score to evaluate segmentation results of ColorAE against traditional color deconvolution; F1 score, sensitivity, positive predictive value, and DICE score to evaluate the predictions from ColorAE, U-Net, and ColorAE:U-Net ensemble methods against pathologist-generated ground truth. We then used prediction results for spatial analysis (nearest neighbor).

Results

We observed that (1) the performance of ColorAE is comparable to traditional color deconvolution for single-stain IHC images (note: traditional color deconvolution cannot be used for mIHC); (2) ColorAE and U-Net are complementary methods that detect six different classes of cells with comparable performance; (3) combinations of ColorAE and U-Net in ensemble methods outperform ColorAE and U-Net alone; and (4) ColorAE:U-Net ensemble methods can be employed for detailed analysis of the tumor microenvironment (TME).

Summary

We developed a suite of scalable deep learning methods to analyze 6 distinctly labeled cell populations in mIHC WSIs. We evaluated our methods and found that they reliably detected and classified cells in the PDAC tumor microenvironment. We also utilized the ColorAE:U-Net ensemble method to analyze 3 mIHC WSIs with nearest neighbor spatial analysis. We demonstrate a proof of concept that these methods can be employed to quantitatively describe the spatial distribution of immune cells within the tumor microenvironment. These complementary deep learning methods are readily deployable for use in clinical research studies.

     

Unsupervised Retinal Vessel Segmentation Using Combined Filters

Image segmentation of retinal blood vessels is a process that can help to predict and diagnose cardiovascular related diseases, such as hypertension and diabetes, which are known to affect the retinal blood vessels’ appearance. This work proposes an unsupervised method for the segmentation of retinal vessels images using a combined matched filter, Frangi’s filter and Gabor Wavelet filter to enhance the images. The combination of these three filters in order to improve the segmentation is the main motivation of this work. We investigate two approaches to perform the filter combination: weighted mean and median ranking. Segmentation methods are tested after the vessel enhancement. Enhanced images with median ranking are segmented using a simple threshold criterion. Two segmentation procedures are applied when considering enhanced retinal images using the weighted mean approach. The first method is based on deformable models and the second uses fuzzy C-means for the image segmentation. The procedure is evaluated using two public image databases, Drive and Stare. The experimental results demonstrate that the proposed methods perform well for vessel segmentation in comparison with state-of-the-art methods.     

Biological Image Segmentation Using Region-Scalable Fitting Energy with B-Spline Level Set Implementation and Watershed

ObjectivesImage segmentation plays an important role in the analysis and understanding of the cellular process. However, this task becomes difficult when there is intensity inhomogeneity between regions, and it is more challenging in the presence of the noise and clustered cells. The goal of the paper is propose an image segmentation framework that tackles the above cited problems.Material and methodsA new method composed of two steps is proposed: First, segment the image using B-spline level set with Region-Scalable Fitting (RSF) active contour model, second apply the Watershed algorithm based on new object markers to refine the segmentation and separate clustered cells. The major contributions of the paper are: 1) Use of a continuous formulation of the level set in the B-spline basis, 2) Develop the energy function and its derivative by introducing the RSF model to deal with intensity inhomogeneity, 3) For the Watershed, propose a relevant choice of markers that considers the cell properties.ResultsExperimental results are performed on widely used synthetic images, in addition to simulated and real biological images, without and with additive noise. They attest the high quality of segmentation of the proposed method in terms of quantitative and qualitative evaluation.ConclusionThe proposed method is able to tackle many difficulties at the same time: overlapped intensities, noise, different cell sizes and clustered cells. It provides an efficient tool for image segmentation especially biological ones.     

CoordConv-Unet: Investigating CoordConv for Organ Segmentation

ObjectivesConvolutional neural networks (CNNs) have established state-of-the-art performance in computer vision tasks such as object detection and segmentation. One of the major remaining challenges concerns their ability to capture consistent spatial and anatomically plausible attributes in medical image segmentation. To address this issue, many works advocate to integrate prior information at the level of the loss function. However, prior-based losses often suffer from local solutions and training instability. The CoordConv layers are extensions of convolutional neural network wherein convolution is conditioned on spatial coordinates. The objective of this paper is to investigate CoordConv as a proficient substitute to convolutional layers for medical image segmentation tasks when trained under prior-based losses.MethodsThis work introduces CoordConv-Unet which is a novel structure that can be used to accommodate training under anatomical prior losses. The proposed architecture demonstrates a dual role relative to prior constrained CNN learning: it either demonstrates a regularizing role that stabilizes learning while maintaining system performance, or improves system performance by allowing the learning to be more stable and to evade local minima.ResultsTo validate the performance of the proposed model, experiments are conducted on two well-known public datasets from the Decathlon challenge: a mono-modal MRI dataset dedicated to segmentation of the left atrium, and a CT image dataset whose objective is to segment the spleen, an organ characterized with varying size and mild convexity issues.ConclusionResults show that, despite the inadequacy of CoordConv when trained with the regular dice baseline loss, the proposed CoordConv-Unet structure can improve significantly model performance when trained under anatomically constrained prior losses.     

Suitability of UK Biobank Retinal Images for Automatic Analysis of Morphometric Properties of the Vasculature

PurposeTo assess the suitability of retinal images held in the UK Biobank - the largest retinal data repository in a prospective population-based cohort - for computer assisted vascular morphometry, generating measures that are commonly investigated as candidate biomarkers of systemic disease.MethodsNon-mydriatic fundus images from both eyes of 2,690 participants - people with a self-reported history of myocardial infarction (n=1,345) and a matched control group (n=1,345) - were analysed using VAMPIRE software. These images were drawn from those of 68,554 UK Biobank participants who underwent retinal imaging at recruitment. Four operators were trained in the use of the software to measure retinal vascular tortuosity and bifurcation geometry.ResultsTotal operator time was approximately 360 hours (4 minutes per image). 2,252 (84%) of participants had at least one image of sufficient quality for the software to process, i.e. there was sufficient detection of retinal vessels in the image by the software to attempt the measurement of the target parameters. 1,604 (60%) of participants had an image of at least one eye that was adequately analysed by the software, i.e. the measurement protocol was successfully completed. Increasing age was associated with a reduced proportion of images that could be processed (p=0.0004) and analysed (p<0.0001). Cases exhibited more acute arteriolar branching angles (p=0.02) as well as lower arteriolar and venular tortuosity (p<0.0001).ConclusionsA proportion of the retinal images in UK Biobank are of insufficient quality for automated analysis. However, the large size of the UK Biobank means that tens of thousands of images are available and suitable for computational analysis. Parametric information measured from the retinas of participants with suspected cardiovascular disease was significantly different to that measured from a matched control group.     

Segmentation of organs-at-risk in cervical cancer CT images with a convolutional neural network

PurposeWe introduced and evaluated an end-to-end organs-at-risk (OARs) segmentation model that can provide accurate and consistent OARs segmentation results in much less time.MethodsWe collected 105 patients’ Computed Tomography (CT) scans that diagnosed locally advanced cervical cancer and treated with radiotherapy in one hospital. Seven organs, including the bladder, bone marrow, left femoral head, right femoral head, rectum, small intestine and spinal cord were defined as OARs. The annotated contours of the OARs previously delineated manually by the patient’s radiotherapy oncologist and confirmed by the professional committee consisted of eight experienced oncologists before the radiotherapy were used as the ground truth masks. A multi-class segmentation model based on U-Net was designed to fulfil the OARs segmentation task. The Dice Similarity Coefficient (DSC) and 95th Hausdorff Distance (HD) are used as quantitative evaluation metrics to evaluate the proposed method.ResultsThe mean DSC values of the proposed method are 0.924, 0.854, 0.906, 0.900, 0.791, 0.833 and 0.827 for the bladder, bone marrow, femoral head left, femoral head right, rectum, small intestine, and spinal cord, respectively. The mean HD values are 5.098, 1.993, 1.390, 1.435, 5.949, 5.281 and 3.269 for the above OARs respectively.ConclusionsOur proposed method can help reduce the inter-observer and intra-observer variability of manual OARs delineation and lessen oncologists’ efforts. The experimental results demonstrate that our model outperforms the benchmark U-Net model and the oncologists’ evaluations show that the segmentation results are highly acceptable to be used in radiation therapy planning.     

CTANet: Confidence-Based Threshold Adaption Network for Semi-Supervised Segmentation of Uterine Regions from MR Images for HIFU Treatment

ObjectivesThe accurate preoperative segmentation of the uterus and uterine fibroids from magnetic resonance images (MRI) is an essential step for diagnosis and real-time ultrasound guidance during high-intensity focused ultrasound (HIFU) surgery. Conventional supervised methods are effective techniques for image segmentation. Recently, semi-supervised segmentation approaches have been reported in the literature. One popular technique for semi-supervised methods is to use pseudo-labels to artificially annotate unlabeled data. However, many existing pseudo-label generations rely on a fixed threshold used to generate a confidence map, regardless of the proportion of unlabeled and labeled data.Materials and MethodsTo address this issue, we propose a novel semi-supervised framework called Confidence-based Threshold Adaptation Network (CTANet) to improve the quality of pseudo-labels. Specifically, we propose an online pseudo-labels method to automatically adjust the threshold, producing high-confident unlabeled annotations and boosting segmentation accuracy. To further improve the network's generalization to fit the diversity of different patients, we design a novel mixup strategy by regularizing the network on each layer in the decoder part and introducing a consistency regularization loss between the outputs of two sub-networks in CTANet.ResultsWe compare our method with several state-of-the-art semi-supervised segmentation methods on the same uterine fibroids dataset containing 297 patients. The performance is evaluated by the Dice similarity coefficient, the precision, and the recall. The results show that our method outperforms other semi-supervised learning methods. Moreover, for the same training set, our method approaches the segmentation performance of a fully supervised U-Net (100% annotated data) but using 4 times less annotated data (25% annotated data, 75% unannotated data).ConclusionExperimental results are provided to illustrate the effectiveness of the proposed semi-supervised approach. The proposed method can contribute to multi-class segmentation of uterine regions from MRI for HIFU treatment.     

Habitat-Net: Segmentation of habitat images using deep learning

Understanding environmental factors that influence forest health, as well as the occurrence and abundance of wildlife, is a central topic in forestry and ecology. However, the manual processing of field habitat data is time-consuming and months are often needed to progress from data collection to data interpretation. To shorten the time to process the data we propose here Habitat-Net: a novel deep learning application based on Convolutional Neural Networks (CNN) to segment habitat images of tropical rainforests. Habitat-Net takes color images as input and after multiple layers of convolution and deconvolution, produces a binary segmentation of the input image. We worked on two different types of habitat datasets that are widely used in ecological studies to characterize the forest conditions: canopy closure and understory vegetation. We trained the model with 800 canopy images and 700 understory images separately and then used 149 canopy and 172 understory images to test the performance of Habitat-Net. We compared the performance of Habitat-Net to the performance of a simple threshold based method, manual processing by a second researcher and a CNN approach called U-Net, upon which Habitat-Net is based. Habitat-Net, U-Net and simple thresholding reduced total processing time to milliseconds per image, compared to 45 s per image for manual processing. However, the higher mean Dice coefficient of Habitat-Net (0.94 for canopy and 0.95 for understory) indicates that accuracy of Habitat-Net is higher than that of both the simple thresholding (0.64, 0.83) and U-Net (0.89, 0.94). Habitat-Net will be of great relevance for ecologists and foresters, who need to monitor changes in their forest structures. The automated workflow not only reduces the time, it also standardizes the analytical pipeline and, thus, reduces the degree of uncertainty that would be introduced by manual processing of images by different people (either over time or between study sites).     

An efficient algorithm for retinal blood vessel segmentation using h-maxima transform and multilevel thresholding

Retinal blood vessel detection and analysis play vital roles in early diagnosis and prevention of several diseases, such as hypertension, diabetes, arteriosclerosis, cardiovascular disease and stroke. This paper presents an automated algorithm for retinal blood vessel segmentation. The proposed algorithm takes advantage of powerful image processing techniques such as contrast enhancement, filtration and thresholding for more efficient segmentation. To evaluate the performance of the proposed algorithm, experiments were conducted on 40 images collected from DRIVE database. The results show that the proposed algorithm yields an accuracy rate of 96.5%, which is higher than the results achieved by other known algorithms.     

A Morphological Hessian Based Approach for Retinal Blood Vessels Segmentation and Denoising Using Region Based Otsu Thresholding

Diabetic Retinopathy (DR) harm retinal blood vessels in the eye causing visual deficiency. The appearance and structure of blood vessels in retinal images play an essential part in the diagnoses of an eye sicknesses. We proposed a less computational unsupervised automated technique with promising results for detection of retinal vasculature by using morphological hessian based approach and region based Otsu thresholding. Contrast Limited Adaptive Histogram Equalization (CLAHE) and morphological filters have been used for enhancement and to remove low frequency noise or geometrical objects, respectively. The hessian matrix and eigenvalues approach used has been in a modified form at two different scales to extract wide and thin vessel enhanced images separately. Otsu thresholding has been further applied in a novel way to classify vessel and non-vessel pixels from both enhanced images. Finally, postprocessing steps has been used to eliminate the unwanted region/segment, non-vessel pixels, disease abnormalities and noise, to obtain a final segmented image. The proposed technique has been analyzed on the openly accessible DRIVE (Digital Retinal Images for Vessel Extraction) and STARE (STructured Analysis of the REtina) databases along with the ground truth data that has been precisely marked by the experts.     

Retinal Vessel Width Measurement at Branchings Using an Improved Electric Field Theory-Based Graph Approach

The retinal vessel width relationship at vessel branch points in fundus images is an important biomarker of retinal and systemic disease. We propose a fully automatic method to measure the vessel widths at branch points in fundus images. The method is a graph-based method, in which a graph construction method based on electric field theory is applied which specifically deals with complex branching patterns. The vessel centerline image is used as the initial segmentation of the graph. Branching points are detected on the vessel centerline image using a set of detection kernels. Crossing points are distinguished from branch points and excluded. The electric field based graph method is applied to construct the graph. This method is inspired by the non-intersecting force lines in an electric field. At last, the method is further improved to give a consistent vessel width measurement for the whole vessel tree. The algorithm was validated on 100 artery branchings and 100 vein branchings selected from 50 fundus images by comparing with vessel width measurements from two human experts.     

Impact de la méthode de segmentation dans la caractérisation des adénocarcinomes pulmonaires en TEP-TDM au 18FDG

ObjectiveThe treatment of lung adenocarcinomas is conditioned by the presence of certain genetic abnormalities. Certain quantitative parameters obtained from FDG PET-CT, at the voxel scale, provide tumour shape and texture characteristics and might predict their mutational status. Our objective was to determine the impact of the segmentation method in the characterization of lung adenocarcinomas in FDG PET-CT.MethodsForty-nine patients with pulmonary adenocarcinomas were retrospectively included, with their initial FDG PET-CT image. The studied tumours were big, heterogeneous and difficult to segment automatically. The automatic FLAB algorithm was used with and without manual adjustment. The parameters were extracted and compared to the ALK, PDL1, and KRAS status, in order to compare the performances of the two segmentation methods. Their performance was determined by the ROC curve method.ResultsSeveral parameters were significant to predict genetic status (AUC > 0.65). The best performing parameters were different according to the genes studied and according to the resampling methods used. The results were less dependent on resampling in automatic segmentation without manual adjustment. The best performing parameters were volume dependent parameters for segmentation with manual adjustment, and texture parameters for automatic segmentation without adjustment.ConclusionThe study of texture parameters is more efficient in automatic segmentation that is not manually adjusted, and it is advantageous to use a manual adjustment when studying volume-dependent parameters in the case of very heterogeneous tumors.     

An efficient algorithm for retinal blood vessel segmentation using h-maxima transform and multilevel thresholding

Retinal blood vessel detection and analysis play vital roles in early diagnosis and prevention of several diseases, such as hypertension, diabetes, arteriosclerosis, cardiovascular disease and stroke. This paper presents an automated algorithm for retinal blood vessel segmentation. The proposed algorithm takes advantage of powerful image processing techniques such as contrast enhancement, filtration and thresholding for more efficient segmentation. To evaluate the performance of the proposed algorithm, experiments were conducted on 40 images collected from DRIVE database. The results show that the proposed algorithm yields an accuracy rate of 96.5%, which is higher than the results achieved by other known algorithms.     

Fast retinal vessel detection and measurement using wavelets and edge location refinement

The relationship between changes in retinal vessel morphology and the onset and progression of diseases such as diabetes, hypertension and retinopathy of prematurity (ROP) has been the subject of several large scale clinical studies. However, the difficulty of quantifying changes in retinal vessels in a sufficiently fast, accurate and repeatable manner has restricted the application of the insights gleaned from these studies to clinical practice. This paper presents a novel algorithm for the efficient detection and measurement of retinal vessels, which is general enough that it can be applied to both low and high resolution fundus photographs and fluorescein angiograms upon the adjustment of only a few intuitive parameters. Firstly, we describe the simple vessel segmentation strategy, formulated in the language of wavelets, that is used for fast vessel detection. When validated using a publicly available database of retinal images, this segmentation achieves a true positive rate of 70.27%, false positive rate of 2.83%, and accuracy score of 0.9371. Vessel edges are then more precisely localised using image profiles computed perpendicularly across a spline fit of each detected vessel centreline, so that both local and global changes in vessel diameter can be readily quantified. Using a second image database, we show that the diameters output by our algorithm display good agreement with the manual measurements made by three independent observers. We conclude that the improved speed and generality offered by our algorithm are achieved without sacrificing accuracy. The algorithm is implemented in MATLAB along with a graphical user interface, and we have made the source code freely available.