A Multi-Orientation Analysis Approach to Retinal Vessel Tracking

Bekkers, Erik J.; Duits, Remco; Berendschot, Tos T. J. M.; Romeny, Bart ter Haar

doi:10.1007/s10851-013-0488-6

Cited by 110 publications

(148 citation statements)

References 58 publications

(131 reference statements)

Supporting

Mentioning

143

Contrasting

Order By: Relevance

“…In our work, we rely on models of the vessels around the optic disc, made using the Edge Tracking in Orientation Scores (ETOS) algorithm [10], but in principle any model that provides the edges of vessels and detects their crossings and bifurcations can be used, for example [11,12,9]. The models are used to define an energy function (Section 2.1) that uses features extracted from both the image and the model (Section 2.2).…”

Section: Methodsmentioning

confidence: 99%

Retinal Artery/Vein Classification via Graph Cut Optimization

Eppenhof

Bekkers

Berendschot³

et al. 2015

Proceedings of the Ophthalmic Medical Image Analysis Second International Workshop

Self Cite

View full text Add to dashboard Cite

Abstract. In many diseases with a cardiovascular component, the geometry of microvascular blood vessels changes. These changes are specific to arteries and veins, and can be studied in the microvasculature of the retina using retinal photography. To facilitate large-scale studies of artery/vein-specific changes in the retinal vasculature, automated classification of the vessels is required. Here we present a novel method for artery/vein classification based on local and contextual feature analysis of retinal vessels. For each vessel, local information in the form of a transverse intensity profile is extracted. Crossings and bifurcations of vessels provide contextual information. The local and contextual features are integrated into a non-submodular energy function, which is optimized exactly using graph cuts. The method was validated on a ground truth data set of 150 retinal fundus images, achieving an accuracy of 88.0% for all vessels and 94.0% for the six arteries and six veins with highest caliber in the image.

show abstract

Section: Methodsmentioning

confidence: 99%

Retinal Artery/Vein Classification via Graph Cut Optimization

Eppenhof

Bekkers

Berendschot³

et al. 2015

Proceedings of the Ophthalmic Medical Image Analysis Second International Workshop

Self Cite

View full text Add to dashboard Cite

show abstract

“…cake wavelets [4]. The set of filter responses forms an orientation score and is regarded as a function on the space of positions and orientations R 2 S 1 .…”

Section: Orientation Score Transformationmentioning

confidence: 99%

Infrastructure for Retinal Image Analysis

Dashtbozorg

Abbasi-Sureshjani

Zhang

et al. 2016

Proceedings of the Ophthalmic Medical Image Analysis Third International Workshop

Self Cite

View full text Add to dashboard Cite

Abstract. This paper introduces a retinal image analysis infrastructure for the automatic assessment of biomarkers related to early signs of diabetes, hypertension and other systemic diseases. The developed application provides several tools, namely normalization, vessel enhancement and segmentation, optic disc and fovea detection, junction detection, bifurcation/crossing discrimination, artery/vein classification and red lesion detection. The pipeline of these methods allows the assessment of important biomarkers characterizing dynamic properties of retinal vessels, such as tortuosity, width, fractal dimension and bifurcation geometry features.

show abstract

“…This brain-inspired method is based on the theory of best-fit exponential curves in the roto-translation group SE (2) developed by Duits, Franken and Janssen [15]- [17], and, importantly, does not rely on explicit segmentation of the blood vessels. 2D images are lifted to 3D functions called "orientation scores" by adding an orientation dimension to the domain [18]. In this newly extended domain of positions and orientations (identified with SE (2)), we study the exponential curves whose curvatures are constant.…”

Section: Measurement Of Retinal Vascular Tortuositymentioning

confidence: 99%

Retinal Vascular Tortuosity in Hospitalized Patients with Type 2 Diabetes and Diabetic Retinopathy in China

Zhu¹,

Triest²,

Tong³

et al. 2016

JBiSE

View full text Add to dashboard Cite

Context: Diabetic patients are at high risk for microvascular complications of disease such as diabetic retinopathy (DR) and diabetic neuropathy. Imaging the retinal microvasculature offers a chance to measure quantitatively the microvascular changes in diabetic patients' onset and progression. However, the relation between retinal biomarkers and diabetic risk factors is unclear in Chinese hospitalized type 2 diabetic patients. Aims: To examine the associations of retinal vascular tortuosity with risk factors of type 2 diabetes and diabetic retinopathy in Chinese hospitalized patients. Patients and Methods: Our cross-sectional study includes 504 participants with type 2 diabetes hospitalized in the department of endocrinology in Shengjing hospital, Shenyang, China. Patients' socio-demographic, clinical and biological information was retrieved from their ID card, the interview, and the local hospital information system. Retinal photographs were taken by laser-scanning ophthalmoscopy of both eyes and checked if gradable for analysis. The weighted mean and standard deviation of tortuosity were calculated from the retinal photographs using a novel robust and fully automatic quantitative method. DR was assessed from the retinal photographs by the ophthalmologist according to the modified Airlie House classification into No DR and Any DR in our current study. Data were analyzed by SPSS Version 22 with Student's t test, Mann-Whitney U test, Chi-square test, and linear regression. Results:For the total participants (504) in this study, the weighted mean and standard deviation (SD) of tortuosity was 12.05 × 10 −3 (SD: 1.66 × 10 −3 ) and 24.31 × 10 −3 (SD: 3.69 × 10 −3 ), respectively. 386 (76.6%) patients were diagnosed with DR who had older age, long duration of diabetes, higher brachial ankle pulse wave velocity (baPWV), higher systolic blood pressure (SBP), higher diastolic blood pressure (DBP), and higher reHow to cite this paper: Zhu, S., van Triest, M., Tong, M., Lamers, T., Han, P., Qian, W. 144tinal vascular tortuosity values. In univariable linear regression analyses, older age, longer duration, higher baPWV, higher urine microalbuminuria, higher urine albumin/creatinine ratio, diagnosed with high blood pressure, thrombosis or Any DR, were significantly associated with both higher tortuosity measures (all P values < 0.05). In multivariable-adjusted linear regression analyses, age and diabetes duration (all P values < 0.05) were independently and positively associated with both tortuosity measures, after adjustment for low-density lipoprotein (LDL), high-density lipoprotein (HDL) and high blood pressure. Furthermore, after adding some kidney failure factors, the urine albumin/creatinine ratio was also an independent risk factor of vascular tortuosity. These associations remained even after including or excluding the factor of DR. Conclusions: Retinal vascular tortuosity is independently associated with older age, longer duration, and higher urine albumin/creatinine ratio in Chinese hospitalized type 2 di...

show abstract

A Multi-Orientation Analysis Approach to Retinal Vessel Tracking

Cited by 110 publications

References 58 publications

Retinal Artery/Vein Classification via Graph Cut Optimization

Retinal Artery/Vein Classification via Graph Cut Optimization

Infrastructure for Retinal Image Analysis

Retinal Vascular Tortuosity in Hospitalized Patients with Type 2 Diabetes and Diabetic Retinopathy in China

Contact Info

Product

Resources

About