Analysis of cornea curvature using radial basis functions – Part I: Methodology

Griffiths, Graham W.; Płociniczak, Łukasz; Schiesser, William E.

doi:10.1016/j.compbiomed.2016.08.011

Cited by 31 publications

(15 citation statements)

References 29 publications

Supporting

Mentioning

Contrasting

Unclassified

Order By: Relevance

“…The cornea serves as the protective, outermost layer of the eye and is responsible for the transmission and refraction of incident light beams that are in turn focused onto the retina by the lens ( Eghrari et al, 2015 ; Meek and Knupp, 2015 ; Griffiths et al, 2016 ). Its near-perfect spherical anterior surface, together with the index of refraction change at the air/tear film interface, account for approximately 80% of the total refractive power of the human eye ( Ruberti and Zieske, 2008 ).…”

Section: Introductionmentioning

confidence: 99%

3D bioprinting of a corneal stroma equivalent

Isaacson

Swioklo

Connon

2018

Experimental Eye Research

308

243

View full text Add to dashboard Cite

Corneal transplantation constitutes one of the leading treatments for severe cases of loss of corneal function. Due to its limitations, a concerted effort has been made by tissue engineers to produce functional, synthetic corneal prostheses as an alternative recourse. However, successful translation of these therapies into the clinic has not yet been accomplished. 3D bioprinting is an emerging technology that can be harnessed for the fabrication of biological tissue for clinical applications. We applied this to the area of corneal tissue engineering in order to fabricate corneal structures that resembled the structure of the native human corneal stroma using an existing 3D digital human corneal model and a suitable support structure. These were 3D bioprinted from an in-house collagen-based bio-ink containing encapsulated corneal keratocytes. Keratocytes exhibited high cell viability both at day 1 post-printing (>90%) and at day 7 (83%). We established 3D bio-printing to be a feasible method by which artificial corneal structures can be engineered.

show abstract

Section: Introductionmentioning

confidence: 99%

3D bioprinting of a corneal stroma equivalent

Isaacson

Swioklo

Connon

2018

Experimental Eye Research

308

243

View full text Add to dashboard Cite

show abstract

“…The PUNN technique also achieved a good performance, yielding a score of 0.801 for the AUC and 0.579 for MS, but using a higher number of connections, 11. The last technique, SUNN, gave the worst AUC and MS performance and used the highest number of connections, 19.…”

Section: Resultsmentioning

confidence: 99%

“…Our study proposal included three ANNs that differed according to the basis function used: product unit neural network (PUNN) [15], sigmoid unit neural network (SUNN) [8], and finally, the radial basis function neural network (RBFNN) [16]. All these methods have been widely used in biomedicine since 1990 and are still in use today: see [17][18][19] for RBFNN, [20][21][22] for MLP or SUNN and [23,24] for PUNN. Finally, all these ANN models have been proven to be universal approximators [8].…”

Section: Introductionmentioning

confidence: 99%

Using machine learning methods to determine a typology of patients with HIV-HCV infection to be treated with antivirals

et al. 2020

View full text Add to dashboard Cite

Several European countries have established criteria for prioritising initiation of treatment in patients infected with the hepatitis C virus (HCV) by grouping patients according to clinical characteristics. Based on neural network techniques, our objective was to identify those factors for HIV/HCV co-infected patients (to which clinicians have given careful consideration before treatment uptake) that have not being included among the prioritisation criteria. This study was based on the Spanish HERACLES cohort (NCT02511496) (April-September 2015, 2940 patients) and involved application of different neural network models with different basis functions (product-unit, sigmoid unit and radial basis function neural networks) for automatic classification of patients for treatment. An evolutionary algorithm was used to determine the architecture and estimate the coefficients of the model. This machine learning methodology found that radial basis neural networks provided a very simple model in terms of the number of patient characteristics to be considered by the classifier (in this case, six), returning a good overall classification accuracy of 0.767 and a minimum sensitivity (for the classification of the minority class, untreated patients) of 0.550. Finally, the area under the ROC curve was 0.802, which proved to be exceptional. The parsimony of the model makes it especially attractive, using just eight connections. The independent variable "recent PWID" is compulsory due to its importance. The simplicity of the model means that it is possible to analyse the relationship between patient characteristics and the probability of belonging to the treated group.

show abstract

“…In Kansa's method RBFs are applied in global fashion however this usage gives rise to ill‐conditioned interpolation matrix when large data sets are used. To overcome this issue, local RBF meshless methods are developed [34–39].…”

Section: Rbfs and Hybrid Kernelmentioning

confidence: 99%

A local hybrid kernel meshless method for numerical solutions of two‐dimensional fractional cable equation in neuronal dynamics

Oruç¹

2020

Numerical Methods Partial

View full text Add to dashboard Cite

This study deals with obtaining numerical solutions of two-dimensional (2D) fractional cable equation in neuronal dynamics by using a recently introduced meshless method. In solution process at first stage, time derivatives that are appeared in the considered problem are discretized by using finite difference method. Then a meshless method based on hybridization of Gaussian and cubic kernels is developed in local fashion. The problem is solved both on regular and irregular domians. L ∞ and RMS error norms are calculated and compared with other numerical methods in literature as well as exact solutions. Also, obtained condition numbers are monitored. Numerical simulations show that local hybrid kernel meshless method is a thriving method for solving 2D fractional cable equation on regular and irregular domians. KEYWORDS 2D fractional cable equation, irregular domain, local hybrid kernel meshless method 1 INTRODUCTION Fractional calculus and fractional differential equations have attracted more attention recently due to their ability of handling many problems from various branches of physics, engineering, and chemistry in a more realistic approach [1, 2]. It has been recognized that fractional derivative has more superiorities than integer order derivative. For instance fractional derivatives can be used to describe memory and hereditary properties of physical materials [3-5]. This feature was not identified in integer order derivatives. There are a lot of applications of fractional calculus and fractional partial differential equations (PEDs) in different branches of science such as viscoelasticity, physics, chemistry, fluid mechanics, control, continuous-time random walks, and finance [6]. Some classic books about fractional calculus and its applications are [7-10].

show abstract

Analysis of cornea curvature using radial basis functions – Part I: Methodology

Cited by 31 publications

References 29 publications

3D bioprinting of a corneal stroma equivalent

3D bioprinting of a corneal stroma equivalent

Using machine learning methods to determine a typology of patients with HIV-HCV infection to be treated with antivirals

A local hybrid kernel meshless method for numerical solutions of two‐dimensional fractional cable equation in neuronal dynamics

Contact Info

Product

Resources

About