Dataset Information

Modelling of retinal vasculature based on genetically tuned parametric L-system.

ABSTRACT: Structures of retinal blood vessels are of great importance in diagnosis and treatment of diseases that affect the eyes. Parametric Lindenmayer system (L-system) is one of the powerful rule-based methods that has a great capability for generating tree-like structures using simple rewriting rules. In this study, a novel framework, which can be used to model the retinal vasculature based on available images, has been proposed. This framework presents a solution to special instance of a general open problem, the L-system inverse problem, in which L-system rules should be obtained based on images representing a particular tree-like structure. In this study, genetic algorithm with a novel objective function based on feature matching and an L-system grammar comparison has been used along with nonlinear regression to solve the parametric L-system inverse problem. The resulting L-system growth rules have been employed to predict inaccessible vascular branches. Graphical and quantitative comparison between model results and target structures of different case studies reveals that the proposed framework can be used to generate the structure of retinal blood vessels accurately. Even in the cases lacking sufficient image data, it can provide acceptable predictions.

SUBMITTER: Aghamirmohammadali SMA

PROVIDER: S-EPMC5990753 | biostudies-other | 2018 May

REPOSITORIES: biostudies-other

ACCESS DATA

Publications

Modelling of retinal vasculature based on genetically tuned parametric L-system.

Aghamirmohammadali Seyed Mohammad Ali SMA Bozorgmehry Boozarjomehry Ramin R Abdekhodaie Mohammad M

Royal Society open science 20180509 5

Structures of retinal blood vessels are of great importance in diagnosis and treatment of diseases that affect the eyes. Parametric Lindenmayer system (L-system) is one of the powerful rule-based methods that has a great capability for generating tree-like structures using simple rewriting rules. In this study, a novel framework, which can be used to model the retinal vasculature based on available images, has been proposed. This framework presents a solution to special instance of a general ope ...[more]

PMID: 29892362

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:Full quantification of Positron Emission Tomography (PET) requires an arterial input function (AIF) for measurement of certain targets, or using particular radiotracers, or for the quantification of specific outcome measures. The AIF represents the measurement of radiotracer concentrations in the arterial blood plasma over the course of the PET examination. Measurement of the AIF is prone to error as it is a composite measure created from the combination of multiple measurements of different samples with different equipment, each of which can be sources of measurement error. Moreover, its measurement requires a high degree of temporal granularity for early time points, which necessitates a compromise between quality and quantity of recorded samples. For these reasons, it is often desirable to fit models to this data in order to improve its quality before using it for quantification of radiotracer binding in the tissue. The raw observations of radioactivity in arterial blood and plasma samples are derived from radioactive decay, which is measured as a number of recorded counts. Count data have several specific properties, including the fact that they cannot be negative as well as a particular mean-variance relationship. Poisson regression is the most principled modelling strategy for working with count data, as it both incorporates and exploits these properties. However, no previous studies to our knowledge have taken this approach, despite the advantages of greater efficiency and accuracy which result from using the appropriate distributional assumptions. Here, we implement a Poisson regression modelling approach for the AIF as proof-of-concept of its application. We applied both parametric and non-parametric models for the input function curve. We show that a negative binomial distribution is a more appropriate error distribution for handling overdispersion. Furthermore, we extend this approach to a hierarchical non-parametric model which is shown to be highly resilient to missing data. We thus demonstrate that Poisson regression is both feasible and effective when applied to AIF data, and propose that this is a promising strategy for modelling blood count data for PET in future.

Project description:PurposeTo evaluate the applicability and estimate the radiobiological parameters of linear-quadratic Poisson tumour control probability (TCP) model for primary prostate cancer patients for two relevant target structures (prostate gland and GTV). The TCP describes the dose-response of prostate after definitive radiotherapy (RT). Also, to analyse and identify possible significant correlations between clinical and treatment factors such as planned dose to prostate gland, dose to GTV, volume of prostate and mpMRI-GTV based on multivariate logistic regression model.MethodsThe study included 129 intermediate and high-risk prostate cancer patients (cN0 and cM0), who were treated with image-guided intensity modulated radiotherapy (IMRT)?±?androgen deprivation therapy with a median follow-up period of 81.4 months (range 42.0-149.0) months. Tumour control was defined as biochemical relapse free survival according to the Phoenix definition (BRFS). MpMRI-GTV was delineated retrospectively based on a pre-treatment multi-parametric MR imaging (mpMRI), which was co-registered to the planning CT. The clinical treatment planning procedure was based on prostate gland, delineated on CT imaging modality. Furthermore, we also fitted the clinical data to TCP model for the two considered targets for the 5-year follow-up after radiation treatment, where our cohort was composed of a total number of 108 patients, of which 19 were biochemical relapse (BR) patients.ResultsFor the median follow-up period of 81.4 months (range 42.0-149.0) months, our results indicated an appropriate ?/??=?1.3 Gy for prostate gland and ?/??=?2.9 Gy for mpMRI-GTV. Only for prostate gland, EQD2 and gEUD2Gy were significantly lower in the biochemical relapse (BR) group compared to the biochemical control (BC) group. Fitting results to the linear-quadratic Poisson TCP model for prostate gland and ?/??=?1.3 Gy were D50?=?66.8 Gy with 95% CI [64.6 Gy, 69.0 Gy], and ??=?3.8 with 95% CI [2.6, 5.2]. For mpMRI-GTV and ?/??=?2.9 Gy, D50 was 68.1 Gy with 95% CI [66.1 Gy, 70.0 Gy], and ??=?4.5 with 95% CI [3.0, 6.1]. Finally, for the 5-year follow-up after the radiation treatment, our results for the prostate gland were: D50?=?64.6 Gy [61.6 Gy, 67.4 Gy], ??=?3.1 [2.0, 4.4], ?/??=?2.2 Gy (95% CI was undefined). For the mpMRI-GTV, the optimizer was unable to deliver any reasonable results for the expected clinical D50 and ?/?. The results for the mpMRI-GTV were D50?=?50.1 Gy [44.6 Gy, 56.0 Gy], ??=?0.8 [0.5, 1.2], ?/??=?0.0 Gy (95% CI was undefined). For a follow-up time of 5 years and a fixed ?/??=?1.6 Gy, the TCP fitting results for prostate gland were D50?=?63.9 Gy [60.8 Gy, 67.0 Gy], ??=?2.9 [1.9, 4.1], and for mpMRI-GTV D50?=?56.3 Gy [51.6 Gy, 61.1 Gy], ??=?1.3 [0.8, 1.9].ConclusionThe linear-quadratic Poisson TCP model was better fit when the prostate gland was considered as responsible target than with mpMRI-GTV. This is compatible with the results of the comparison of the dose distributions among BR and BC groups and with the results achieved with the multivariate logistic model regarding gEUD2Gy. Probably limitations of mpMRI in defining the GTV explain these results. Another explanation could be the relatively homogeneous dose prescription and the relatively low number of recurrences. The failure to identify any benefit for considering mpMRI-GTV as the target responsible for the clinical response is confirmed when considering a fixed ?/??=?1.6 Gy, a fixed follow-up time for biochemical response at 5 years or Gleason score differentiation.

Dataset Information

Modelling of retinal vasculature based on genetically tuned parametric L-system.

Publications

Modelling of retinal vasculature based on genetically tuned parametric L-system.

Similar Datasets

OmicsDI is part of the ELIXIR infrastructure

Tweets