Dataset Information

Comparison of Common Retinal Vessel Caliber Measurement Software and a Conversion Algorithm.

ABSTRACT:

Purpose

To compare three commonly used retinal vessel caliber measurement software systems, and propose an algorithm for conversion between measurement systems.

Methods

We used 120 retinal photographs to evaluate the agreement between three commonly used software (Retinal Analysis [RA], Integrative Vessel Analysis [IVAN], and Singapore I Vessel Assessment [SIVA]). Bland-Altman plots were used to evaluate agreement of retinal arteriolar (central retinal artery equivalent, CRAE) and venular (central retinal vein equivalent, CRVE) calibers. Pearson's correlation was used to assess the associations between systemic factors and retinal vessel calibers, and Z-test was used to compare the strength of the correlation coefficients across the three software systems. An algorithm was created to convert measurements, with paired t-test performed to evaluate the differences between SIVA-measured retinal calibers and SIVA-approximates converted from RA- and IVAN-measurements using the algorithm.

Results

Differences between SIVA- and RA-measured calibers (CRAE: mean difference [MD] = -21.8 ?m, 95% limits of agreement [LOA], -47.3 to 3.7 ?m; CRVE: MD = -7.7 ?m, 95% LOA, -28.0 to 12.6 ?m), SIVA- and IVAN-measured calibers (CRAE: MD = -6.7 ?m, 95% LOA, -23.8 to 10.4 ?m; CRVE: MD = -18.2 ?m 95% LOA, -36.7 to 0.4 ?m) were large. However, the strength of correlations between systemic factors with SIVA-measured retinal calibers was not significantly different to that measured using RA and IVAN (P ? 0.332). SIVA-approximates converted from RA and IVAN measurements using the proposed algorithm was not significantly different from SIVA-measured calibers (P ? 0.20).

Conclusion

Absolute measurements of retinal vessel calibers vary between three common software systems but associations with systemic factors were similar.

Translational relevance

The proposed algorithm allowed conversions of RA and IVAN measurements to SIVA-approximates. This conversion is important for future data pooling and establishment of normative values for retinal vascular caliber measurements.

SUBMITTER: Yip W

PROVIDER: S-EPMC5063055 | biostudies-literature | 2016 Oct

REPOSITORIES: biostudies-literature

ACCESS DATA

Publications

Comparison of Common Retinal Vessel Caliber Measurement Software and a Conversion Algorithm.

Yip WanFen W Tham Yih Chung YC Hsu Wynne W Lee Mong Li ML Klein Ronald R Klein Barbara B Ikram Mohammad Kamran MK Wong Tien Yin TY Cheung Carol Yim-Lui CY

Translational vision science & technology 20161012 5

<h4>Purpose</h4>To compare three commonly used retinal vessel caliber measurement software systems, and propose an algorithm for conversion between measurement systems.<h4>Methods</h4>We used 120 retinal photographs to evaluate the agreement between three commonly used software (Retinal Analysis [RA], Integrative Vessel Analysis [IVAN], and Singapore I Vessel Assessment [SIVA]). Bland-Altman plots were used to evaluate agreement of retinal arteriolar (central retinal artery equivalent, CRAE) and ...[more]

PMID: 27752402

Similar Datasets

Project description:BackgroundChanges in the retinal vessel caliber are associated with a variety of major diseases, namely diabetes, hypertension and atherosclerosis. The clinical assessment of these changes in fundus images is tiresome and prone to errors and thus automatic methods are desirable for objective and precise caliber measurement. However, the variability of blood vessel appearance, image quality and resolution make the development of these tools a non-trivial task.MetholodogyA method for the estimation of vessel caliber in eye fundus images via vessel cross-sectional intensity profile model fitting is herein proposed. First, the vessel centerlines are determined and individual segments are extracted and smoothed by spline approximation. Then, the corresponding cross-sectional intensity profiles are determined, post-processed and ultimately fitted by newly proposed parametric models. These models are based on Difference-of-Gaussians (DoG) curves modified through a multiplying line with varying inclination. With this, the proposed models can describe profile asymmetry, allowing a good adjustment to the most difficult profiles, namely those showing central light reflex. Finally, the parameters of the best-fit model are used to determine the vessel width using ensembles of bagged regression trees with random feature selection.Results and conclusionsThe performance of our approach is evaluated on the REVIEW public dataset by comparing the vessel cross-sectional profile fitting of the proposed modified DoG models with 7 and 8 parameters against a Hermite model with 6 parameters. Results on different goodness of fitness metrics indicate that our models are constantly better at fitting the vessel profiles. Furthermore, our width measurement algorithm achieves a precision close to the observers, outperforming state-of-the art methods, and retrieving the highest precision when evaluated using cross-validation. This high performance supports the robustness of the algorithm and validates its use in retinal vessel width measurement and possible integration in a system for retinal vasculature assessment.

Project description:ImportanceMicrovascular phenotypes, which can be assessed using retinal imaging, may be informative about the life course pathogenesis of hearing loss.ObjectiveTo investigate whether differences in retinal vessel caliber (specifically wider venules and narrower arterioles) are associated with hearing threshold and hearing loss in mid-childhood and midlife.Design, setting, and participantsA population-based cross-sectional study (Child Health CheckPoint) was nested within the Longitudinal Study of Australian Children. A total of 1281 children and 1255 attending parents were assessed using retinal microvasculature and air conduction audiometry data at a main assessment center in 7 large cities in Australia.Main outcomes and measuresAir conduction audiometry was used to calculate the high Fletcher index (mean threshold of 1, 2, and 4 kHz), and bilateral hearing loss was defined as a high Fletcher index greater than 15 dB hearing level in the better-hearing ear. Retinal arteriolar and venular caliber were measured from fundus photographs using validated computer-based software. Linear and logistic regression quantified the associations of retinal vessel caliber with hearing threshold and hearing loss, respectively.ResultsOf the 1281 included children (mean age, 11.4 years; 49.1% boys), the mean (SD) high Fletcher index was 7.9 (5.8) dB hearing level. Of the 1255 included adults (mean age, 43.8 years; 86.6% women), the mean (SD) high Fletcher index was 13.0 (6.8) dB hearing level; 109 of 1281 children (8.5%) and 328 of 1255 adults (26.1%) had hearing loss. In adults, each 1-SD (18.6-?m) wider retinal venular caliber (worse) was associated with higher (worse) hearing threshold at lower individual frequencies (eg, 2 kHz: ??=?0.63; 95% CI, 0.10-1.17) and overall high Fletcher index (eg, 2 kHz: ??=?0.52; 95% CI, 0.07-0.96), as well as a 1.20-fold (95% CI, 1.03-1.40) higher odds of hearing loss. In children, patterns of venular associations were similar but smaller and less certain. Narrower retinal arteriolar caliber (worse) was associated with a 1.16-fold (95% CI, 1.00-1.37) higher odds of hearing loss in adults (per 1-SD [14.0-?m] narrower arteriolar caliber) but not in children.Conclusions and relevanceAdverse retinal microvascular characteristics are associated with hearing loss by midlife, with venular associations possibly emerging by age 11 to 12 years. Microvascular health may contribute to the pathogenesis of hearing loss across the life course, warranting replication and mechanistic studies to inform causal inference and prevention efforts.

Dataset Information

Comparison of Common Retinal Vessel Caliber Measurement Software and a Conversion Algorithm.

Purpose

Methods

Results

Conclusion

Translational relevance

Publications

Comparison of Common Retinal Vessel Caliber Measurement Software and a Conversion Algorithm.

Similar Datasets

OmicsDI is part of the ELIXIR infrastructure

Tweets