Semi-automated evaluation tool for retinal vasculopathy

Optical coherence tomography-based retinal vessel analysis for the evaluation of hypertensive vasculopathy

PURPOSE

Evaluation of retinal vessels in cardiovascular disease traditionally relies upon funduscopy, but more recently digital photo analysis has expanded the spectrum. As spectral domain optical coherence tomography (OCT) allows an in-vivo assessment of retinal tissue and its vessels on a histological scale, our study aimed at using this tool for the analysis of the retinal vasculature.

METHODS

Circumferential peripapillary OCT scans (3DOCT-2000; Topcon Inc., Tokyo, Japan), with centration on the optic nerve head, were taken from 20 eyes (20 participants) with normal blood pressure and 20 eyes (20 participants) with arterial hypertension above 120 mmHg (mean blood pressure). The diameter of all vessels intersecting the scan line was measured in the OCT and used to calculate central vessel equivalents, and the A/V ratios were calculated. Bland-Altman analysis was performed to evaluate reliability. Correlation coefficients were determined for reliability of the method as well as with the individual mean arterial blood pressures.

RESULTS

Forty eyes (40 participants) were included in the study. Mean arterial blood pressure was 96±4 mmHg in the control group and 132±7 mmHg in the hypertonic group. Mean A/V ratio as determined from OCT scans was 0.82±0.13 (normotonic) versus 0.62±0.11 (hypertonic). A Pearson's correlation coefficient of 0.67 (p<0.001) was determined between A/V ratio and blood pressure.

CONCLUSIONS

Our results highlight the feasibility of retinal vessel measurements in spectral domain OCT. A relation between mean arterial blood pressure and OCT-based A/V ratio was established. Further research will elucidate influencing factors and provide a broader basis for therapeutic approaches.

Semi-automated retinal vessel analysis in nonmydriatic fundus photography

PURPOSE

Funduscopic assessment of the retinal vessels may be used to assess the health status of microcirculation and as a component in the evaluation of cardiovascular risk factors. Typically, the evaluation is restricted to morphological appreciation without strict quantification. Our purpose was to develop and validate a software tool for semi-automated quantitative analysis of retinal vasculature in nonmydriatic fundus photography.

METHODS

matlab software was used to develop a semi-automated image recognition and analysis tool for the determination of the arterial-venous (A/V) ratio in the central vessel equivalent on 45° digital fundus photographs. Validity and reproducibility of the results were ascertained using nonmydriatic photographs of 50 eyes from 25 subjects recorded from a 3DOCT device (Topcon Corp.). Two hundred and thirty-three eyes of 121 healthy subjects were evaluated to define normative values.

RESULTS

A software tool was developed using image thresholds for vessel recognition and vessel width calculation in a semi-automated three-step procedure: vessel recognition on the photograph and artery/vein designation, width measurement and calculation of central retinal vessel equivalents. Mean vessel recognition rate was 78%, vessel class designation rate 75% and reproducibility between 0.78 and 0.91. Mean A/V ratio was 0.84. Application on a healthy norm cohort showed high congruence with prior published manual methods. Processing time per image was one minute.

CONCLUSIONS

Quantitative geometrical assessment of the retinal vasculature may be performed in a semi-automated manner using dedicated software tools. Yielding reproducible numerical data within a short time leap, this may contribute additional value to mere morphological estimates in the clinical evaluation of fundus photographs.

Reliable monitoring system for arteriovenous ratio computation

The degree of narrowing or widening in retinal vessels related to several cardiovascular diseases such as hypertension or diabetes may be measured by the arteriovenous ratio (AVR), that is, the relation between the artery and vein retinal vessel widths. Nevertheless, its lack of reproducibility, due mainly to a laborious manual calculation and the dependence of the vessels selected for its estimation, hinders its use in daily medical practice. This variation makes difficult to monitor the patient's condition over time. This paper describes a reliable AVR monitoring system which computes automatically the AVR from several images of the same patient acquired at different times using the same vessels measured at the same points. The system has been evaluated in a large data set of 158 pairs of images and good correlation results between medical experts and the system have been achieved.

Retinal artery and venular caliber grading: a semi-automated evaluation tool

Retinal imaging can facilitate the measurement and quantification of subtle variations and abnormalities in retinal vasculature. Retinal vascular imaging may thus offer potential as a noninvasive research tool to probe the role and pathophysiology of the microvasculature, and as a cardiovascular risk prediction tool. In order to perform this, an accurate method must be provided that is statistically sound and repeatable. This paper presents the methodology of such a system that assists physicians in measuring vessel caliber (i.e., diameters or width) from digitized fundus photographs. The system involves texture and edge information to measure and quantify vessel caliber. The graphical user interfaces are developed to allow retinal image graders to select individual vessel area that automatically returns the vessel calibers for noisy images. The accuracy of the method is validated using the measured caliber from graders and an existing method. The system provides very high accuracy vessel caliber measurement which is also reproducible with high consistency.

Retinal vessel diameter measurement using unsupervised linear discriminant analysis

An automatic vessel diameter measurement technique based on linear discriminant analysis (LDA) has been proposed. After estimating the vessel wall, the vessel cross-section profile is divided into three regions: two corresponding to the background and one to the vessel. The algorithm was tested on more than 5000 cross-sections of retinal vessels from the REVIEW dataset through comparative study with the state-of-the-art techniques. Cross-correlation analyses were performed to determine the degree to which the proposed technique was close to the ground truth. The results indicate that proposed algorithm consistently performed better than most of other techniques and was highly correlated with the manual measurement as the reference diameter. The proposed method does not require any supervision and is suitable for automatic analysis.

Development of an automated system to classify retinal vessels into arteries and veins

There are some evidence of the association between the calibre of the retinal blood vessels and hypertension. Computer-assisted procedures have been proposed to measure the calibre of retinal blood vessels from high-resolution photopraphs. Most of them are in fact semi-automatic. Our objective in this paper is twofold, to develop a totally automated system to classify retinal vessels into arteries and veins and to compare the measurements of the arteriolar-to-venular diameter ratio (AVR) computed from the system with those computed from observers. Our classification method consists of four steps. First, we obtain the vascular tree structure using a segmentation algorithm. Then, we extract the profiles. After that, we select the best feature vectors to distinguish between veins and arteries. Finally, we use a clustering algorithm to classify each detected vessel as an artery or a vein. Our results show that compared with an observer-based method, our method achieves high sensitivity and specificity in the automated detection of retinal arteries and veins. In addition the system is robust enough independently of the radii finally chosen, which makes it more trustworthy in its clinical application. We conclude that the system represents an automatic method of detecting arteries and veins to measure the calibre of retinal microcirculation across digital pictures of the eye fundus.