B-spline Model Research Articles

Discretization of Non-uniform Rational B-Spline (NURBS) Models for Meshless Isogeometric Analysis

We present an algorithm for fast generation of quasi-uniform and variable-spacing nodes on domains whose boundaries are represented as computer-aided design (CAD) models, more specifically non-uniform rational B-splines (NURBS). This new algorithm enables the solution of partial differential equations within the volumes enclosed by these CAD models using (collocation-based) meshless numerical discretizations. Our hierarchical algorithm first generates quasi-uniform node sets directly on the NURBS surfaces representing the domain boundary, then uses the NURBS representation in conjunction with the surface nodes to generate nodes within the volume enclosed by the NURBS surface. We provide evidence for the quality of these node sets by analyzing them in terms of local regularity and separation distances. Finally, we demonstrate that these node sets are well-suited (both in terms of accuracy and numerical stability) for meshless radial basis function generated finite differences discretizations of the Poisson, Navier-Cauchy, and heat equations. Our algorithm constitutes an important step in bridging the field of node generation for meshless discretizations with isogeometric analysis.

Dynamic CBCT imaging using prior model-free spatiotemporal implicit neural representation (PMF-STINR)

Objective. Dynamic cone-beam computed tomography (CBCT) can capture high-spatial-resolution, time-varying images for motion monitoring, patient setup, and adaptive planning of radiotherapy. However, dynamic CBCT reconstruction is an extremely ill-posed spatiotemporal inverse problem, as each CBCT volume in the dynamic sequence is only captured by one or a few x-ray projections, due to the slow gantry rotation speed and the fast anatomical motion (e.g. breathing). Approach. We developed a machine learning-based technique, prior-model-free spatiotemporal implicit neural representation (PMF-STINR), to reconstruct dynamic CBCTs from sequentially acquired x-ray projections. PMF-STINR employs a joint image reconstruction and registration approach to address the under-sampling challenge, enabling dynamic CBCT reconstruction from singular x-ray projections. Specifically, PMF-STINR uses spatial implicit neural representations to reconstruct a reference CBCT volume, and it applies temporal INR to represent the intra-scan dynamic motion of the reference CBCT to yield dynamic CBCTs. PMF-STINR couples the temporal INR with a learning-based B-spline motion model to capture time-varying deformable motion during the reconstruction. Compared with the previous methods, the spatial INR, the temporal INR, and the B-spline model of PMF-STINR are all learned on the fly during reconstruction in a one-shot fashion, without using any patient-specific prior knowledge or motion sorting/binning. Main results. PMF-STINR was evaluated via digital phantom simulations, physical phantom measurements, and a multi-institutional patient dataset featuring various imaging protocols (half-fan/full-fan, full sampling/sparse sampling, different energy and mAs settings, etc). The results showed that the one-shot learning-based PMF-STINR can accurately and robustly reconstruct dynamic CBCTs and capture highly irregular motion with high temporal (∼ 0.1 s) resolution and sub-millimeter accuracy. Significance. PMF-STINR can reconstruct dynamic CBCTs and solve the intra-scan motion from conventional 3D CBCT scans without using any prior anatomical/motion model or motion sorting/binning. It can be a promising tool for motion management by offering richer motion information than traditional 4D-CBCTs.

Bayesian workflow for time-varying transmission in stratified compartmental infectious disease transmission models.

Compartmental models that describe infectious disease transmission across subpopulations are central for assessing the impact of non-pharmaceutical interventions, behavioral changes and seasonal effects on the spread of respiratory infections. We present a Bayesian workflow for such models, including four features: (1) an adjustment for incomplete case ascertainment, (2) an adequate sampling distribution of laboratory-confirmed cases, (3) a flexible, time-varying transmission rate, and (4) a stratification by age group. Within the workflow, we benchmarked the performance of various implementations of two of these features (2 and 3). For the second feature, we used SARS-CoV-2 data from the canton of Geneva (Switzerland) and found that a quasi-Poisson distribution is the most suitable sampling distribution for describing the overdispersion in the observed laboratory-confirmed cases. For the third feature, we implemented three methods: Brownian motion, B-splines, and approximate Gaussian processes (aGP). We compared their performance in terms of the number of effective samples per second, and the error and sharpness in estimating the time-varying transmission rate over a selection of ordinary differential equation solvers and tuning parameters, using simulated seroprevalence and laboratory-confirmed case data. Even though all methods could recover the time-varying dynamics in the transmission rate accurately, we found that B-splines perform up to four and ten times faster than Brownian motion and aGPs, respectively. We validated the B-spline model with simulated age-stratified data. We applied this model to 2020 laboratory-confirmed SARS-CoV-2 cases and two seroprevalence studies from the canton of Geneva. This resulted in detailed estimates of the transmission rate over time and the case ascertainment. Our results illustrate the potential of the presented workflow including stratified transmission to estimate age-specific epidemiological parameters. The workflow is freely available in the R package HETTMO, and can be easily adapted and applied to other infectious diseases.

Pemodelan Regresi Semiparametrik B Spline (Studi Kasus: Pengaruh Harga Emas dan Minyak Mentah Dunia Terhadap Indeks Harga Saham Gabungan)

<p dir="ltr"><span>The increases of the world gold and crude oil prices have a big role as a main factor that effect composite stock price index, the effect can make investors to buy stock from Bursa Efek Indonesia. Regression semiparametric used in this research for a purpose to get combined parametric and nonparametric with B Spline approach. B Spline is a development of spline to overcome weaknesses in making singular matrix at a high order spline with many knot points and close together. Variable parametric component is composite stock price index with crude oil price, and variable nonparametric component is composite stock price index with gold price that got obtained from January 2015 until December 2022. The result from this research is best regression semiparametric B-Spline modelling can be obtained using some combination of order and knot points. The optimal point is obtained on 2nd order using 4 knot point (1.135;1.319,15;1.320,75;1.323,25) with a minimum GCV value is 100.227,8. The best measure of goodness with a coefficient of determination value (R-Square) obtained a value 78,8%, because the value is more than 67% make it as a strong model. MAPE value is 3,37% that has a value less than 10 %, make this model have a perfect forecasting ability.</span></p><p><span id="docs-internal-guid-09fba3ae-7fff-a25a-8197-7dd90ea8b1e1"><span>Keywords: </span><span>Gold; Crude Oil; Composite Stock Price Index; Semiparametric B Spline; GCV</span></span></p>

Effect of PEDOT:PSS optical properties at the frontal interface on electrical performance in MAPbI3 perovskite solar cells

This article presents a thorough analysis of perovskite-based solar cells (PSCs) by integrating optical and electrical simulations. The investigation includes simulations of both optical and electrical characteristics of a PSC configuration featuring a MAPbI3 active layer, PEDOT:PSS as the hole transport layer (HTL) at the front interface, and PC60BM and BCP at the back interface. Optical simulations utilized the optical admittance method and transfer matrix method, with optical constants such as refractive index (n) and extinction coefficient (k) derived from transmittance measurements of the fabricated layers. Electrical simulations were performed using the Solar Cell Capacitance Simulator One Dimension (SCAPS-1D) software, focusing on the influence of optical losses due to total reflection at the interfaces. Discrepancies in short-circuit current density (Jsc) of about 3 mA/cm2 were revealed between simulations employing optical constants of PEDOT:PSS determined via Tauc-Lorentz-Drude (TLD) and B-spline (BSPL) model fitting to transmittance data. Optimal parameters for achieving the highest power conversion efficiency (PCE) were identified, with PEDOT:PSS layer thicknesses below 15 nm and MAPbI3 layer thicknesses above 305 nm. The maximum efficiency ranged between 10.42 % and 12.10 %, close to conventional experimental perovskite solar cells with the same structure. A key observation highlighted the overestimation of Jsc and PCE when simulated total reflectance was neglected in electrical simulations. These findings underscore the significance of incorporating optical data into electrical simulations, offering critical insights for PSC optimization. Overall, this study enhances our understanding of the intricate relationship between optical and electrical parameters, essential for advancing high-performance PSC development.

Deformable 3D/3D CT-to-digital-tomosynthesis image registration in image-guided bronchoscopy interventions

Traditional navigational bronchoscopy procedures rely on preprocedural computed tomography (CT) and intraoperative chest radiography and cone-beam CT (CBCT) to biopsy peripheral lung lesions. This navigational approach is challenging due to the projective nature of radiography, and the high radiation dose, long imaging time, and large footprints of CBCT. Digital tomosynthesis (DTS) is considered an attractive alternative combining the advantages of radiography and CBCT. Only the depth resolution cannot match a full CBCT image due to the limited angle acquisition. To address this issue, preoperative CT is a good auxiliary in guiding bronchoscopy interventions. Nevertheless, CT-to-body divergence caused by anatomic changes and respiratory motion, hinders the effective use of CT imaging. To mitigate CT-to-body divergence, we propose a novel deformable 3D/3D CT-to-DTS registration algorithm employing a multistage, multiresolution approach and using affine and elastic B-spline transformation models with bone and lung mask images. A multiresolution strategy with a Gaussian image pyramid and a multigrid strategy within the B-spline model are applied. The normalized correlation coefficient is included in the cost function for the affine model and a multimetric weighted cost function is used for the B-spline model, with weights determined heuristically. Tested on simulated and real patient bronchoscopy data, the algorithm yields promising results. Assessed qualitatively by visual inspection and quantitatively by computing the Dice coefficient (DC) and the average symmetric surface distance (ASSD), the algorithm achieves mean DC of 0.82±0.05 and 0.74±0.05, and mean ASSD of 0.65±0.29mm and 0.93±0.43mm for simulated and real data, respectively. This algorithm lays the groundwork for CT-aided intraoperative DTS imaging in image-guided bronchoscopy interventions with future studies focusing on automated metric weight setting.

B-spline polynomials models for analyzing growth patterns of Guzerat young bulls in field performance tests.

The aim of this study was to identify suitable polynomial regression for modeling the average growth trajectory and to estimate the relative development of the rib eye area, scrotal circumference, and morphometric measurements of Guzerat young bulls. A total of 45 recently weaned males, aged 325.8±28.0 days and weighing 219.9±38.05 kg, were evaluated. The animals were kept on Brachiaria brizantha pastures, received multiple supplementations, and were managed under uniform conditions for 294 days, with evaluations conducted every 56 days. The average growth trajectory was adjusted using ordinary polynomials, Legendre polynomials, and quadratic B-splines. The coefficient of determination, mean absolute deviation, mean square error, the value of the restricted likelihood function, Akaike information criteria, and consistent Akaike information criteria were applied to assess the quality of the fits. For the study of allometric growth, the power model was applied. Ordinary polynomial and Legendre polynomial models of the fifth order provided the best fits. B-splines yielded the best fits in comparing models with the same number of parameters. Based on the restricted likelihood function, Akaike's information criterion, and consistent Akaike's information criterion, the B-splines model with six intervals described the growth trajectory of evaluated animals more smoothly and consistently. In the study of allometric growth, the evaluated traits exhibited negative heterogeneity (b<1) relative to the animals' weight (p<0.01), indicating the precocity of Guzerat cattle for weight gain on pasture. Complementary studies of growth trajectory and allometry can help identify when an animal's weight changes and thus assist in decision-making regarding management practices, nutritional requirements, and genetic selection strategies to optimize growth and animal performance.

Modelling the lactation curve in Alpine × Beetal crossbred dairy goats using random regression models fitted with Legendre polynomial and B-spline functions.

The current study sought to genetically assess the lactation curve of Alpine × Beetal crossbred goats through the application of random regression models (RRM). The objective was to estimate genetic parameters of the first lactation test-day milk yield (TDMY) for devising a practical breeding strategy within the nucleus breeding programme. In order to model variations in lactation curves, 25,998 TDMY records were used in this study. For the purpose of estimating genetic parameters, orthogonal Legendre polynomials (LEG) and B-splines (BS) were examined in order to generate suitable and parsimonious models. A single-trait RRM technique was used for the analysis. The average first lactation TDMY was 1.22 ± 0.03 kg and peak yield (1.35 ± 0.02 kg) was achieved around the 7th test day (TD). The present investigation has demonstrated the superiority of the B-spline model for the genetic evaluation of Alpine × Beetal dairy goats. The optimal random regression model was identified as a quadratic B-spline function, characterized by six knots to represent the central trend. This model effectively captured the patterns of additive genetic influences, animal-specific permanent environmental effects (c2 ) and 22 distinct classes of (heterogeneous) residual variance. Additive variances and heritability (h2 ) estimates were lower in the early lactation, however, moderate across most parts of the lactation studied, ranging from 0.09 ± 0.04 to 0.33 ± 0.06. The moderate heritability estimates indicate the potential for selection using favourable combinations of test days throughout the lactation period. It was also observed that a high proportion of total variance was attributed to the animal's permanent environment. Positive genetic correlations were observed for adjacent TDMY values, while the correlations became less pronounced for more distant TDMY values. Considering better fitting of the lactation curve, the use of B-spline functions for genetic evaluation of Alpine × Beetal goats using RRM is recommended.

Developing stem taper of Shorea robusta in the far-western Terai of Nepal

Tree taper functions expressed in terms of height and diameter at breast height (BDH) can provide accurate and timely information on current growing stock. Taper equations are very important for calculation of growing stock in forest inventories, however, in the context of Nepal, these are still unavailable at the required level. The study aimed to develop taper equations, so that those can be used to predict the diameter anywhere along the stem, and estimate tree volumes at desired sections. The input data was a destructive sampling method of 81 sample trees of Shorea robusta distributed in ten locations of the far western Terai of Nepal (Kailali and Kanchanpur districts).&#x0D; Using two independent B-Spline and 5th-degree polynomial taper models, the upper stem diameters were imputed. Both models were applied on the whole dataset, irrespective of DBH size, to get common fitted taper models. Later, the same models were tested for three different DBH classes to compare and evaluate the best-fit model. &#x0D; Taper models, developed under the B-spline polynomial model of 3rd degree, were found to be highly dependent on the tree (DBH) sizes. Thus, better models could be developed by classifying the whole dataset based on different DBH classes. On the other hand, developed models under the 5th degree polynomial taper model did not exhibit their dependency on the tree (DBH) sizes and a better model was found for the unclassified datasets, i.e. for all DBH sizes.

The Cluster Analysis by Using Nonparametric Cubic B-Spline Modeling for Longitudinal Data

Longitudinal data is becoming increasingly common, especially in the medical and economic fields, and various methods have been analyzed and developed to analyze this type of data.&#x0D; In this research, the focus was on compiling and analyzing this data, as cluster analysis plays an important role in identifying and grouping co-expressed subfiles over time and employing them on the nonparametric smoothing cubic B-spline model, which is characterized by providing continuous first and second derivatives, resulting in a smoother curve with fewer abrupt changes in slope. It is also more flexible and can pick up on more complex patterns and fluctuations in the data.&#x0D; The longitudinal balanced data profile was compiled into subgroups by penalizing the pairwise distances between the coefficients of the cubic B-spline model using one of the common penalize functions, the Minimax Concave Penalty function (MCP). This method, in turn, works to determine the number of clusters through one of the model selection criteria, Bayesian information criteria (BIC), and we used optimization methods to solve their equations. Therefore, we applied the alternative direction method of the ADMM multiplier algorithm to reach approximate solutions to find the estimators of the nonparametric model using R statistical software.Longitudinally balanced data were generated in the simulation study, as the number of subjects was 60 and the number of repeats (time) was 10 for each subject. The simulation was iterated 100 times, and it showed that employing the MCP partial methods on the cubic model can group profiles into clusters, which is the aim of this paper.&#x0D; &#x0D; Paper type: Research paper.

Developing Iran's empirical zenith wet delay model (IR-ZWD)

The presence of water vapor in the lower atmosphere can introduce errors in satellite-based geodetic observations. Accurate modeling of this part of atmospheric delay is particularly challenging due to the considerable variations of water vapor. Therefore, constructing a reasonable model to predict Zenith Wet Delay (ZWD) can improve the accuracy of geodetic observations and positioning techniques. In this study, we aim at constructing a regional ZWD model for Iran and nearby regions (called the IR-ZWD model) using base functions with local support. The mode is based on the five-year outputs of the Empirical Reanalysis Fifth generation (ERA5) data with the spatial resolution of about 0.25° from 2017 to 2021. The B-spline base functions are used to effectively represent local spatial changes in the spectral domain and to decrease the number of unknown parameters. A B-spline model with the order and surface resolution of about 3 and 5 (scalar values) is found to be efficient, which has an equivalent spatial resolution of ∼0.5°. Temporal variations are accounted for by applying a constant term, along with periodic components with annual, semi-annual, 3-, and 4-monthly periods. Our results demonstrate that the proposed model has a mean Root Mean Squared Error (RMSE) of about 0.035 m within Iran, which represents an improvement of approximately 12.5% compared to the commonly used global empirical models such as GPT3w, GTrop, and HGPT2. The correlation coefficient value of 0.55 is found between IR-ZWD and ERA5 data, which is about 10% higher than that of, e.g., GPT3w and GTrop. The IR-ZWD model is also evaluated against five radiosonde stations and ZWD from the Jason-3 satellite mission. In both cases, the results indicate that IR-ZWD can reduce the RMSE and MAE values of about 10%, and it improves the correlation coefficient value about 9%.

Learning Spline Models with the EM Algorithm for Shape Recognition

This paper demonstrates how cubic Spline (B-Spline) models can be used to recognize 2-dimension nonrigid handwritten isolated characters. Each handwritten character is represented by a set of nonoverlapping uniformly distributed landmarks. The Spline models are constructed by utilizing cubic order of polynomial to model the shapes under study. The approach is a two-stage process. The first stage is learning, we construct a mixture of spline class parameters to capture the variations in spline coefficients using the apparatus Expectation Maximization algorithm. The second stage is recognition, here we use the Fréchet distance to compute the variations between the spline models and test spline shape for recognition. We test the approach on a set of handwritten Arabic letters

Atomic structure and annealing-induced reordering of ε-Ga2O3: A Rutherford backscattering/channeling and spectroscopic ellipsometry study

The crystallographic structure of thin Ga2O3 layers grown by metal–organic vapour phase epitaxy on Al2O3 substrate was analyzed by Rutherford Backscattering Spectrometry/Channeling (RBS/C) angular yield scans performed around the c-axis of as-grown Ga2O3. The measured widths and minimum yields of the scan curves for the Ga and O component were compared to calculations based on the continuum steering potential model. The results obtained are consistent with a crystal structure containing oxygen atoms arranged in a 4H hexagonal closely packed lattice and Ga atoms preferentially occupying octahedral interstitial sites in the 4H cells - a structure closely related to the ε-Ga2O3 polymorph. After high-temperature annealing remarkable structural transformation is detected via significant changes in the RBS/C spectra. This effect is related to the hexagonal-monoclinic, i.e., ε-β phase transformation of Ga2O3. Spectroscopic ellipsometry spectra of as-grown and annealed samples can be best fitted using a vertically graded single-layer B-spline model. Significant differences in the dielectric functions were found, showing bandgap reduction for long term annealing. These features are related to the ε-β polymorphic transformation, variation of the preferred crystallographic orientation upon annealing, and differences in residual strain and defect structure determined by the annealing conditions.

A Machine-Learning-Based Approach for Natural Gas Futures Curve Modeling

This work studies the term structure dynamics in the natural gas futures market, focusing on the Dutch Title Transfer Facility (TTF) daily futures prices. At first, using the whole dataset, we compared the in-sample fitting performance of three models: the four-factor dynamic Nelson–Siegel–Svensson (4F-DNSS) model, the five-factor dynamic De Rezende–Ferreira (5F-DRF) model, and the B-spline model. Our findings suggest that B-spline is the method that achieves the best in-line fitting results. Then, we turned our attention to forecasting, using data from 20 January 2011 to 13 May 2022 as the training set and the remaining data, from 16 May to 13 June 2022, for day-ahead predictions. In this second part of the work we combined the above mentioned models (4F-DNSS, 5F-DRF and B-spline) with a Nonlinear Autoregressive Neural Network (NAR-NN), asking the NAR-NN to provide parameter tuning. All the models provided accurate out-of-sample prediction; nevertheless, based on extensive statistical tests, we conclude that, as in the previous case, B-spline (combined with an NAR-NN) ensured the best out-of-sample prediction.

Adaptive isogeometric methods with C1 (truncated) hierarchical splines on planar multi-patch domains

Isogeometric analysis is a powerful paradigm which exploits the high smoothness of splines for the numerical solution of high order partial differential equations. However, the tensor-product structure of standard multivariate B-spline models is not well suited for the representation of complex geometries, and to maintain high continuity on general domains special constructions on multi-patch geometries must be used. In this paper, we focus on adaptive isogeometric methods with hierarchical splines, and extend the construction of [Formula: see text] isogeometric spline spaces on multi-patch planar domains to the hierarchical setting. We replace the hypothesis of local linear independence for the basis of each level by a weaker assumption, which still ensures the linear independence of hierarchical splines. We also develop a refinement algorithm that guarantees that the assumption is fulfilled by [Formula: see text] splines on certain suitably graded hierarchical multi-patch mesh configurations, and prove that it has linear complexity. The performance of the adaptive method is tested by solving the Poisson and the biharmonic problems.

Customizable adaptive regularization techniques for B-spline modeling

B-spline models are a powerful way to represent scientific data sets with a functional approximation. However, these models can suffer from spurious oscillations when the data to be approximated are not uniformly distributed. Model regularization (i.e., smoothing) has traditionally been used to minimize these oscillations; unfortunately, it is sometimes impossible to sufficiently remove unwanted artifacts without smoothing away key features of the data set. In this article, we present a method of model regularization that preserves significant features of a data set while minimizing artificial oscillations. Our method varies the strength of a smoothing parameter throughout the domain automatically, removing artifacts in poorly-constrained regions while leaving other regions unchanged. The proposed method selectively incorporates regularization terms based on first and second derivatives to maintain model accuracy while minimizing numerical artifacts. The behavior of our method is validated on a collection of two- and three-dimensional data sets produced by scientific simulations. In addition, a key tuning parameter is highlighted and the effects of this parameter are presented in detail. This paper is an extension of our previous conference paper at the 2022 International Conference on Computational Science (ICCS) (Lenz et al., 2022) [1].

PENERAPAN SMOOTHING B-SPLINES PADA HUBUNGAN ANTARA PERTUMBUHAN EKONOMI DAN TINGKAT KEBAHAGIAAN

This study aimed to model the smoothing of B-splines on the relationship between happiness and economic growth. The method used in this research is smoothing B-splines, which were in the process of determining knot s and smoothing parameters (λ) based on the minimum GCV. The data used in the study came from Badan Pusat Statistik-Statistics Indonesia. The results of this study concluded that the smoothing of B-splines is quite good at modeling the relationship between the level of happiness (response variable) and economic growth (predictor variable). The smoothing B-splines model can explain the variation in the level of happiness by 71.583 percent.

Tracking Control for Output Probability Density Function of Stochastic Systems Using FPD Method

Output probability density function (PDF) tracking control of stochastic systems has always been a challenging problem in both theoretical development and engineering practice. Focused on this challenge, this work proposes a novel stochastic control framework so that the output PDF can track a given time-varying PDF. Firstly, the output PDF is characterised by the weight dynamics following the B-spline model approximation. As a result, the PDF tracking problem is transferred to a state tracking problem for weight dynamics. In addition, the model error of the weight dynamics is described by the multiplicative noises to more effectively establish its stochastic dynamics. Moreover, to better reflect the practical applications in the real world, the given tracking target is set to be time-varying rather than static. Thus, an extended fully probabilistic design (FPD) is developed based on the conventional FPD to handle multiplicative noises and to track the time-varying references in a superior way. Finally, the proposed control framework is verified by a numerical example, and a comparison simulation with the linear-quadratic regulator (LQR) method is also included to illustrate the superiority of our proposed framework.

Ariadne+: Deep Learning--Based Augmented Framework for the Instance Segmentation of Wires

In this article, an innovative algorithm for instance segmentation of wires called Ariadne+ is presented. Although vastly present in many manufacturing environments, the perception and manipulation of wires is still an open problem for robotic applications. Wires are deformable linear objects lacking of any specific shape, color, and feature. The proposed approach uses deep learning and standard computer vision techniques aiming at their reliable and time effective instance segmentation. A deep convolutional neural network is employed to generate a binary mask showing where wires are present in the input image, then the graph theory is applied to create the wire paths from the binary mask through an iterative approach that aims to maximize the graph coverage. In addition, the B-Spline model of each instance, useful in manipulation tasks, is provided. The approach has been validated quantitatively and qualitatively using a manually labeled test dataset and by comparing it against the original Ariadne algorithm. The timings performances of the approach have been also analyzed in depth.

Inference-Time Adaptation for Improved Transfer Ability and Generalization in Deformable Image Registration Deep Learning

<h3>Purpose/Objective(s)</h3> Deep learning has shown promise in many medical imaging tasks. One major obstacle in landing AI in clinic is the lack of performance assurance at test time to cope with the specific individual. Specifically, in the context of deformable image registration (DIR) problems, training and testing samples can differ in either image or motion characteristics or both, raising concerns about reliability from direct inference. This study aims to combine the efficiency and benefit of data-driven regularization from deep-learning based approaches, and the individual-centric perspective of classic optimization approach, to generate DIR solutions with high accuracy, robustness, and efficiency. <h3>Materials/Methods</h3> Our method utilizes a descriptor network to impose general feasibility prior on deformation vector fields (DVFs). The trained registration network is further adapted for each image pair at test time to optimize the individualized performance. The adaptation method was tested under various generalization domain shifts in cross-protocol, cross-platform, and cross-modality scenarios. For cross protocol, deep prior was generated by 750 CT-based DVFs, trained on 20 10-phase 4D CBCT and tested with SPARE synthesized CBCT sett; for cross platform, deep prior was generated from 100 CTA-based DVFs, trained on 10 .35T MRI, and tested on 1.5T cardiac MRI; for cross-modality, deep prior was generated by 750 CT-based DVF, trained on 02 4D CBCT, and test-time adapted for a pilot 4D lung MRI acquisition. Our method was compared against a manually tuned classic B-spline method in SimpleElastix and the network without adaptation. <h3>Results</h3> Our method achieved (2.11 +/- 1.61), (2.26 +/- 1.41), and (2.00 +/- 1.63) mm landmark-based registration errors on lung CBCT, cardiac MRI, and lung MRI, respectively. In a motion-compensated CBCT enhancement test, it achieved (102.1 +/- 7.96) HU root-mean-square error and (0.994 +/- 0.002) structural similarity index to the ground-truth CT. Our method improved the registration accuracy with respect to individual test input, with statistical significance with p value from superiority test in order of 1E-3 or less. The only exception was target registration error in midventricular and apical regions on cardiac MRI when compared against B-spline model where statistical significance can't be established. <h3>Conclusion</h3> We have demonstrated the efficacy to adjust trained registration network to unseen data acquired on a different protocol or scanner, with a different imaging platform, or even modality. The proposed paradigm enables applying deep learning registration method to atypical image presence or pilot imaging types when data is unavailable to support conventional network training. The test-time adaptation adjust optimization focus to the individual case at hand, providing confidence for clinical translation and adoption. The proposed rationale applies to other medical AI development where personalization and robustness at run time are critical.