Computerized Analysis of Retinal Vessel Width and Tortuosity in Premature Infants

Wilson, Clare; Cocker, Kenneth D.; Moseley, Merrick J.; Paterson, Carl; Clay, Simon; Schulenburg, W E; Mills, Monte D.; Ells, Anna L.; Parker, Kim H.; Quinn, Graham E.; Fielder, Alistair R.; Ng, Jeffrey

doi:10.1167/iovs.07-1353

Cited by 165 publications

(150 citation statements)

References 21 publications

Supporting

Mentioning

147

Contrasting

Unclassified

Order By: Relevance

“…20 In particular, retinal arterial tortuosity and venous dilation at the posterior pole are important findings to diagnose plus disease in ROP. 5 To the best of our knowledge, the difference of A/V ratio between preterm birth and full-tern birth matched with age and sex was not reported yet. In the present study, the mean A/V ratio in the preterm group was significantly less than that in the full-term group.…”

Section: Discussionmentioning

confidence: 90%

“…Plus disease, an indicator of ROP severity, may present a constellation of signs including retinal arterial tortuosity and venous dilation at the posterior pole, vitreous haze, and iris rigidity. 5 In several studies, investigators have used vessel width to determine the presence of severe ROP or to predict later disease. [6][7][8] For instance, Grunwald et al 8 documented that the rate of increase in retinal venule width was useful in identifying infants at risk for severe ROP.…”

Section: Introductionmentioning

confidence: 99%

See 1 more Smart Citation

Cup-to-disc and arteriole-to-venule ratios in preterm birth

Kim

Choi

et al. 2015

Eye

View full text Add to dashboard Cite

Aims To investigate the influence of preterm birth on the optic disc and retinal vessels by measurements of cup-to-disc (C/D) ratio and arteriole-to-venule (A/V) ratio. Methods Eighty-three eyes of 42 preterm births were included. In the age-and sexmatched control group, 83 eyes of 42 full-term births were used. Fundus color photographs were taken. ImageJ software was used to calculate C/D and A/V ratios from the fundus images.Results Fundus photographs were taken at 8.01 ± 2.22 years of age for the preterm group and 8.01 ± 2.13 years of age for the control group. The mean gestational age of the preterm group was 27 4 / 7 weeks (range, 24-34 weeks). The preterm group had significantly larger C/D ratio and smaller A/V ratio (mean ± standard deviation: 0.46 ± 0.12 and 0.59 ± 0.08, respectively) than the control group (0.36 ± 0.07 and 0.68 ± 0.07, respectively) after spherical equivalent refractive error was adjusted. Conclusions Preterm birth is significantly associated with larger C/D ratio and smaller A/V ratio. These findings show the effect of preterm birth on the development of optic disc and retinal vessel development.

show abstract

Section: Discussionmentioning

confidence: 90%

Section: Introductionmentioning

confidence: 99%

Cup-to-disc and arteriole-to-venule ratios in preterm birth

Kim

Choi

et al. 2015

Eye

View full text Add to dashboard Cite

show abstract

“…Although several tortuosity measurement techniques (Lotmar et al;1979;Heneghan et al;Martinez-Perez et al;Azegrouz et al;Wilson et al;Bribiesca;Lisowska et al; have been proposed, results obtained suggest the need for further improvement. The Arc-chord ratio techniques (Lotmar et al;1979;Heneghan et al;Martinez-Perez et al;Azegrouz et al; failed to differentiate varying vessels when they have the same length but different number of vessel twists.…”

Section: Introductionmentioning

confidence: 99%

“…Vessel tortuosity was computed as the ratio of the actual vessel length to the length of the underlying chord (Lotmar et al;1979;Heneghan et al;Martinez-Perez et al;Wilson et al;. This technique assumes a vessel to be non-tortuous if it is straight line and tortuous while the radius of curvature is longer than the chord length of the vessel.…”

Section: Introductionmentioning

confidence: 99%

Automatic Retinal Vessel Detection and Tortuosity Measurement

Mapayi¹,

Tapamo²,

Viriri³

et al. 2016

Image Anal Stereol

View full text Add to dashboard Cite

As retinopathies continue to be major causes of visual loss and blindness worldwide, early detection and management of these diseases will help achieve significant reduction of blindness cases. However, an efficient automatic retinal vessel segmentation approach remains a challenge. Since efficient vessel network detection is a very important step needed in ophthalmology for reliable retinal vessel characterization, this paper presents the study on the combination of difference image and k-means clustering for the segmentation of retinal vessels. Stationary points in the vessel center-lines are used to model the detection of twists in the vessel segments. The combination of arc-chord ratio with stationary points is used to compute tortuosity index. Experimental results show that the proposed k-means combined with difference image achieved a robust segmentation of retinal vessels. A maximum average accuracy of 0.9556 and a maximum average sensitivity of 0.7581 were achieved on DRIVE database while a maximum average accuracy of 0.9509 and a maximum average sensitivity of 0.7666 were achieved on STARE database. When compared with the previously proposed techniques on DRIVE and STARE databases, the proposed technique yields higher mean sensitivity and mean accuracy rates in the same range of very good specificity. In a related development, a non-normalized tortuosity index that combined distance metric and the vessel twist frequency proposed in this paper also achieved a strong correlation of 0.80 with the expert ground truth.

show abstract

“…Vessel tortuosity descriptors are typically computed via an extensive pipeline (including manual interventions) of image pre-processing, segmentation, thinning and splitting of the vascular network, after which tortuosity values are computed from the extracted vessel centerlines [2,3,5,6]. In such pipelines, errors introduced in each processing step may accumulate, and information might get lost along the way.…”

Section: Introductionmentioning

confidence: 99%

Curvature Based Biomarkers for Diabetic Retinopathy via Exponential Curve Fits in SE(2)

Bekkers

Zhang

Duits

et al. 2015

Proceedings of the Ophthalmic Medical Image Analysis Second International Workshop

View full text Add to dashboard Cite

Abstract. We propose a robust and fully automatic method for the analysis of vessel tortuosity. Our method does not rely on pre-segmentation of vessels, but instead acts directly on retinal image data. The method is based on theory of best-fit exponential curves in the roto-translation group SE(2). We lift 2D images to 3D functions called orientation scores by including an orientation dimension in the domain. In the extended domain of positions and orientations (identified with SE(2)) we study exponential curves, whose spatial projections have constant curvature. By locally fitting such curves to data in orientation scores, via our new iterative stabilizing refinement method, we are able to assign to each location a curvature and confidence value. These values are then used to define global tortuosity measures. The method is validated on synthetic and retinal images. We show that the tortuosity measures can serve as effective biomarkers for diabetes and different stages of diabetic retinopathy.

show abstract

Computerized Analysis of Retinal Vessel Width and Tortuosity in Premature Infants

Cited by 165 publications

References 21 publications

Cup-to-disc and arteriole-to-venule ratios in preterm birth

Cup-to-disc and arteriole-to-venule ratios in preterm birth

Automatic Retinal Vessel Detection and Tortuosity Measurement

Curvature Based Biomarkers for Diabetic Retinopathy via Exponential Curve Fits in SE(2)

Contact Info

Product

Resources

About