A Novel Approach to Generate a Virtual Population of Human Coronary Arteries for <i>In Silico</i> Clinical Trials of Stent Design

Pleouras, Dimitrios S.; Sakellarios, Antonis I.; Rigas, George; Karanasiou, Georgia S.; Tsompou, Panagiota; Karanasiou, Gianna; Kigka, Vassiliki I.; Kyriakidis, Savvas; Pezoulas, Vasileios C.; Gois, George; Tachos, Nikolaos S.; Ramos, Aidonis; Pelosi, Gualtiero; Rocchiccioli, Silvia; Michalis, Lampros K.; Fotiadis, Dimitrios I.

doi:10.1109/ojemb.2021.3082328

Cited by 10 publications

(9 citation statements)

References 24 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…It is evident that while there are articles that evaluate data augmentation methods for image data, there is a dearth of literature that comprehensively assesses data augmentation techniques for numerical data in the clinical trials field [17,18]. A recent study tried to increase the quantity of data derived from a limited sample size [19]. This study aimed to create a simulated population of human coronary arteries for the purpose of conducting in silico clinical trials on stent design.…”

Section: Discussionmentioning

confidence: 99%

Variational Autoencoders for Data Augmentation in Clinical Studies

Papadopoulos,

Karalis

2023

Applied Sciences

View full text Add to dashboard Cite

Sample size estimation is critical in clinical trials. A sample of adequate size can provide insights into a given population, but the collection of substantial amounts of data is costly and time-intensive. The aim of this study was to introduce a novel data augmentation approach in the field of clinical trials by employing variational autoencoders (VAEs). Several forms of VAEs were developed and used for the generation of virtual subjects. Various types of VAEs were explored and employed in the production of virtual individuals, and several different scenarios were investigated. The VAE-generated data exhibited similar performance to the original data, even in cases where a small proportion of them (e.g., 30–40%) was used for the reconstruction of the generated data. Additionally, the generated data showed even higher statistical power than the original data in cases of high variability. This represents an additional advantage for the use of VAEs in situations of high variability, as they can act as noise reduction. The application of VAEs in clinical trials can be a useful tool for decreasing the required sample size and, consequently, reducing the costs and time involved. Furthermore, it aligns with ethical concerns surrounding human participation in trials.

show abstract

Section: Discussionmentioning

confidence: 99%

Variational Autoencoders for Data Augmentation in Clinical Studies

Papadopoulos,

Karalis

2023

Applied Sciences

View full text Add to dashboard Cite

show abstract

“…This introduces an added difficulty of modifying the computational mesh for each virtual patient. Because of this, most ISCTs involving patient meshes generate the mesh from patient-specific image data and simulate variability through variation in, for example, orthopaedic implant positioning [4], plaque growth over time on the arteries [230], and blood pressure and thrombus formation parameters applied on the mesh [257]. Note that the intracranial flow diverter trial used unmodified patient-specific images to generate the vessel meshes and as such cannot be considered a sampled virtual population.…”

Section: Virtual Populationmentioning

confidence: 99%

Advancing treatment of retinal disease through in silico trials

2023

View full text Add to dashboard Cite

Treating retinal diseases to prevent sight loss is an increasingly important challenge. Thanks to the configuration of the eye, the retina can be examined relatively easily in situ. Owing to recent technological development in scanning devices, much progress has been made in understanding the structure of the retina and characterising retinal biomarkers. However, treatment options remain limited and are often of low efficiency and efficacy.In recent years, the concept of in silico clinical trials has been adopted by many pharmaceutical companies to optimise and accelerate the development of therapeutics. In silico clinical trials rely on the use of mathematical models based on the physical and biochemical mechanisms underpinning a biological system. With appropriate simplifications and assumptions, one can generate computer simulations of various treatment regimens, new therapeutic molecules, delivery strategies and so forth, rapidly and at a fraction of the cost required for the equivalent experiments. Such simulations have the potential not only to hasten the development of therapies and strategies but also tooptimise the use of existing therapeutics.In this paper, we review the state-of-the-art in in silico models of the retina for mathematicians, biomedical scientists and clinicians, highlighting the challenges to developing in silico clinical trials. Throughout this paper, we highlight key findings from in silico models about the physiology of the retina in health and disease. We describe the main building blocks of in silico clinical trials and identify challenges to developing in silico clinical trials of retinal diseases.

show abstract

“…Several microvascular metrics, such as vessel density and fractal dimension, have been suggested to quantify the quality of the microvasculature on OCTAs 17 . Using those metrics, several microvascular changes have been not only linked with ageing and diseased retinae 22;39;55;56;60 but also with cerebrovascular changes and cardiovascular diseases 28;38;45 . For the latter two, virtual populations have been developed, but similar work is yet to be done for the retinal vasculature or for the linked cerebral-retinal vasculature 32 .…”

Section: Introductionmentioning

confidence: 99%

Linking Structure and Function: Image-Based Virtual Populations of the Retinal Vasculature

Hernandez,

Madhusudhan,

Zheng

et al. 2023

Preprint

View full text Add to dashboard Cite

PurposeThis study explores the relationship between microvascular parameters as delineated by optical coherence tomography angiography (OCTA) and retinal perfusion. We introduce a versatile framework to examine the interplay between the retinal vasculature structure and function, generating virtual vasculatures from central retinal vessels to macular capillaries. Alongside this, we develop a haemodynamics model which tests the associations between vascular morphology and retinal perfusion.MethodsThe generation of the vasculature is based on the distribution of four clinical parameters pertaining to the dimension and blood pressure of the central retinal vessels, constructive constrained optimisation and Voronoi diagram. Arterial and venous trees are generated in the temporal retina and connected through three layers of capillaries at different depths in the macula. The correlations between total retinal blood flow and macular flow fraction and vascular morphology are derived as Spearman rank coefficients and uncertainty from input parameters is quantified.ResultsA virtual cohort of 200 healthy vasculatures were generated. Mean and standard deviation for retinal blood flow and macular flow ratio were 19.15±7.34 μL/min and 4.52±1.19 %. Retinal blood flow was correlated with vessel area density, vessel diameter index, fractal dimension and vessel calibre index. The macular flow fraction was not correlated with any morphological metrics.ConclusionsThe proposed framework is able to reproduce vascular networks in the macula that are morphologically and functionally similar to real vasculature. The framework provides quantitative insights into how macular perfusion can be affected by changes in vascular morphology delineated on OCTA.

show abstract

A Novel Approach to Generate a Virtual Population of Human Coronary Arteries for In Silico Clinical Trials of Stent Design

Cited by 10 publications

References 24 publications

Variational Autoencoders for Data Augmentation in Clinical Studies

Variational Autoencoders for Data Augmentation in Clinical Studies

Advancing treatment of retinal disease through in silico trials

Linking Structure and Function: Image-Based Virtual Populations of the Retinal Vasculature

Contact Info

Product

Resources

About