Geometrical Consistency Modeling on B-Spline Parameter Domain for 3D Face Reconstruction From Limited Number of Wild Images.
Ontology highlight
ABSTRACT:
SUBMITTER: Peng W
PROVIDER: S-EPMC8079323 | biostudies-literature |
REPOSITORIES: biostudies-literature
Similar Datasets
Project description:BackgroundMathematical models for revealing the dynamics and interactions properties of biological systems play an important role in computational systems biology. The inference of model parameter values from time-course data can be considered as a "reverse engineering" process and is still one of the most challenging tasks. Many parameter estimation methods have been developed but none of these methods is effective for all cases and can overwhelm all other approaches. Instead, various methods have their advantages and disadvantages. It is worth to develop parameter estimation methods which are robust against noise, efficient in computation and flexible enough to meet different constraints.ResultsTwo parameter estimation methods of combining spline theory with Linear Programming (LP) and Nonlinear Programming (NLP) are developed. These methods remove the need for ODE solvers during the identification process. Our analysis shows that the augmented cost function surfaces used in the two proposed methods are smoother; which can ease the optima searching process and hence enhance the robustness and speed of the search algorithm. Moreover, the cores of our algorithms are LP and NLP based, which are flexible and consequently additional constraints can be embedded/removed easily. Eight system biology models are used for testing the proposed approaches. Our results confirm that the proposed methods are both efficient and robust.ConclusionsThe proposed approaches have general application to identify unknown parameter values of a wide range of systems biology models.
| S-EPMC3750107 | biostudies-literature
Project description:Reconstruction of perceived faces from brain signals is a hot topic in brain decoding and an important application in the field of brain-computer interfaces. Existing methods do not fully consider the multiple facial attributes represented in face images, and their different activity patterns at multiple brain regions are often ignored, which causes the reconstruction performance very poor. In the current study, we propose an algorithmic framework that efficiently combines multiple face-selective brain regions for precise multi-attribute perceived face reconstruction. Our framework consists of three modules: a multi-task deep learning network (MTDLN), which is developed to simultaneously extract the multi-dimensional face features attributed to facial expression, identity and gender from one single face image, a set of linear regressions (LR), which is built to map the relationship between the multi-dimensional face features and the brain signals from multiple brain regions, and a multi-conditional generative adversarial network (mcGAN), which is used to generate the perceived face images constrained by the predicted multi-dimensional face features. We conduct extensive fMRI experiments to evaluate the reconstruction performance of our framework both subjectively and objectively. The results show that, compared with the traditional methods, our proposed framework better characterizes the multi-attribute face features in a face image, better predicts the face features from brain signals, and achieves better reconstruction performance of both seen and unseen face images in both visual effects and quantitative assessment. Moreover, besides the state-of-the-art intra-subject reconstruction performance, our proposed framework can also realize inter-subject face reconstruction to a certain extent.
| S-EPMC9643433 | biostudies-literature
Project description:Atomic force microscopy (AFM) can visualize the dynamics of single biomolecules under near-physiological conditions. However, the scanning tip probes only the molecular surface with limited resolution, missing details required to fully deduce functional mechanisms from imaging alone. To overcome such drawbacks, we developed a computational framework to reconstruct 3D atomistic structures from AFM surface scans, employing simulation AFM and automatized fitting to experimental images. We provide applications to AFM images ranging from single molecular machines, protein filaments, to large-scale assemblies of 2D protein lattices, and demonstrate how the obtained full atomistic information advances the molecular understanding beyond the original topographic AFM image. We show that simulation AFM further allows for quantitative molecular feature assignment within measured AFM topographies. Implementation of the developed methods into the versatile interactive interface of the BioAFMviewer software, freely available at www.bioafmviewer.com, presents the opportunity for the broad Bio-AFM community to employ the enormous amount of existing structural and modeling data to facilitate the interpretation of resolution-limited AFM images.
| S-EPMC8959186 | biostudies-literature
Project description:We present the attenuated spline reconstruction technique (aSRT) which provides an innovative algorithm for single photon emission computed tomography (SPECT) image reconstruction. aSRT is based on an analytic formula of the inverse attenuated Radon transform. It involves the computation of the Hilbert transforms of the linear attenuation function and of two sinusoidal functions of the so-called attenuated sinogram These computations are achieved by employing the attenuation information provided by computed tomography (CT) scans and by utilizing custom-made cubic spline interpolation. The purpose of this work is: (i) to present the mathematics of aSRT, (ii) to reconstruct simulated and real SPECT/CT data using aSRT and (iii) to evaluate aSRT by comparing it to filtered backprojection (FBP) and to ordered subsets expectation minimization (OSEM) reconstruction algorithms. Simulation studies were performed by using an image quality phantom and an appropriate attenuation map. Reconstructed images were generated for 45, 90 and 180 views over 360 degrees with 20 realizations and involved Poisson noise of three different levels (NL), namely 100% (NL1), 50% (NL2) and 10% (NL3) of the total counts, respectively. Moreover, real attenuated SPECT sinograms were reconstructed from a real study of a Jaszczak phantom, as well as from a real clinical myocardial SPECT/CT study. Comparisons between aSRT, FBP and OSEM reconstructions were performed using contrast, bias and image roughness. The results suggest that aSRT can efficiently produce accurate attenuation-corrected reconstructions for simulated and real phantoms, as well as for clinical data. In particular, in the case of the clinical myocardial study, aSRT produced reconstructions with higher cold contrast than both FBP and OSEM. aSRT, by incorporating the attenuation correction within itself, may provide an improved alternative to FBP. This is particularly promising for 'cold' regions as those occurring in myocardial ischaemia.
| S-EPMC6283982 | biostudies-literature
Project description:The drastic improvement in data collection and acquisition technologies has enabled scientists to collect a great amount of data. With the growing dataset size, typically comes a growing complexity of data structures and of complex models to account for the data structures. How to estimate the parameters of complex models has put a great challenge on current statistical methods. This paper proposes a blockwise consistency approach as a potential solution to the problem, which works by iteratively finding consistent estimates for each block of parameters conditional on the current estimates of the parameters in other blocks. The blockwise consistency approach decomposes the high-dimensional parameter estimation problem into a series of lower-dimensional parameter estimation problems, which often have much simpler structures than the original problem and thus can be easily solved. Moreover, under the framework provided by the blockwise consistency approach, a variety of methods, such as Bayesian and frequentist methods, can be jointly used to achieve a consistent estimator for the original high-dimensional complex model. The blockwise consistency approach is illustrated using two high-dimensional problems, variable selection and multivariate regression. The results of both problems show that the blockwise consistency approach can provide drastic improvements over the existing methods. Extension of the blockwise consistency approach to many other complex models is straightforward.
| S-EPMC8026010 | biostudies-literature
Project description:Individuals with Down syndrome (DS) are widely believed to possess considerable socialization strengths. However, the findings on social cognition capabilities are controversial. In the present study, we investigated whether individuals with DS exhibit shortage in face tuning, one of the indispensable components of social cognition. For this purpose, we implemented a recently developed Face-n-Food paradigm with food-plate images composed of food ingredients such as fruits and vegetables. The key benefit of such face-like non-face images is that single elements do not facilitate face processing. In a spontaneous recognition task, 25 children with DS aged 9 to 18 years were presented with a set of Face-n-Food images bordering on the Giuseppe Arcimboldo style. The set of images was administered in a predetermined order from the least to most resembling a face. In DS individuals, thresholds for recognition of the Face-n-Food images as a face were drastically higher as compared not only with typically developing controls, but also with individuals with autistic spectrum disorders and Williams-Beuren syndrome. This outcome represents a significant step toward better conceptualization of the visual social world in DS and neurodevelopmental disorders in general.
| S-EPMC6305370 | biostudies-literature
Project description:4D reconstruction of dynamic positron emission tomography (dPET) data can improve the signal-to-noise ratio in reconstructed image sequences by fitting smooth temporal functions to the voxel time-activity-curves (TACs) during the reconstruction, though the optimal choice of function remains an open question. We propose a spline-residue model, which describes TACs as weighted sums of convolutions of the arterial input function with cubic B-spline basis functions. Convolution with the input function constrains the spline-residue model at early time-points, potentially enhancing noise suppression in early time-frames, while still allowing a wide range of TAC descriptions over the entire imaged time-course, thus limiting bias. Spline-residue based 4D-reconstruction is compared to that of a conventional (non-4D) maximum a posteriori (MAP) algorithm, and to 4D-reconstructions based on adaptive-knot cubic B-splines, the spectral model and an irreversible two-tissue compartment ('2C3K') model. 4D reconstructions were carried out using a nested-MAP algorithm including spatial and temporal roughness penalties. The algorithms were tested using Monte-Carlo simulated scanner data, generated for a digital thoracic phantom with uptake kinetics based on a dynamic [18F]-Fluromisonidazole scan of a non-small cell lung cancer patient. For every algorithm, parametric maps were calculated by fitting each voxel TAC within a sub-region of the reconstructed images with the 2C3K model. Compared to conventional MAP reconstruction, spline-residue-based 4D reconstruction achieved??>50% improvements for five of the eight combinations of the four kinetics parameters for which parametric maps were created with the bias and noise measures used to analyse them, and produced better results for 5/8 combinations than any of the other reconstruction algorithms studied, while spectral model-based 4D reconstruction produced the best results for 2/8. 2C3K model-based 4D reconstruction generated the most biased parametric maps. Inclusion of a temporal roughness penalty function improved the performance of 4D reconstruction based on the cubic B-spline, spectral and spline-residue models.
| S-EPMC5983307 | biostudies-literature
Project description:This dataset contains the regression parameters derived by analyzing segmented brain MRI images (gray matter and white matter) from a large population of healthy subjects, using a multivariate adaptive regression splines approach. A total of 1919 MRI datasets ranging in age from 1-75 years from four publicly available datasets (NIH, C-MIND, fCONN, and IXI) were segmented using the CAT12 segmentation framework, writing out gray matter and white matter images normalized using an affine-only spatial normalization approach. These images were then subjected to a six-step DARTEL procedure, employing an iterative non-linear registration approach and yielding increasingly crisp intermediate images. The resulting six datasets per tissue class were then analyzed using multivariate adaptive regression splines, using the CerebroMatic toolbox. This approach allows for flexibly modelling smoothly varying trajectories while taking into account demographic (age, gender) as well as technical (field strength, data quality) predictors. The resulting regression parameters described here can be used to generate matched DARTEL or SHOOT templates for a given population under study, from infancy to old age. The dataset and the algorithm used to generate it are publicly available at https://irc.cchmc.org/software/cerebromatic.php.
| S-EPMC5752094 | biostudies-literature
Project description:ObjectiveFace transplantation replaces substantial defects with anatomically identical donor tissues; preoperative vascular assessment relies on noninvasive imaging to separate and characterize the external carotid vessels and branches. The objective is to describe and illustrate vascular considerations for face transplantation candidates.MethodsNovel noninvasive imaging using computed tomography and magnetic resonance imaging over 3 spatial dimensions plus time was developed and tested in 4 face transplant candidates. Precontrast images assessed bones and underlying metal. Contrast media was used to delineate and separate arteries from veins. For computed tomography, acquisition over multiple time points enabled the computation of tissue perfusion metrics. Time-resolved magnetic resonance angiography was performed to separate arterial and venous phases.ResultsThe range of circulation times for the external carotid system was 6 to 14 seconds from arterial blush to loss of venous enhancement. Precontrast imaging provided a roadmap of bones and metal. Among the 4 patients, 3 had surgical clips, metal implants, or both within 1 cm of major vessels considered for surgery. Contrast-enhanced wide area detector computed tomographic data acquired in the axial mode separated these structures and provided arterial and venous images for planning the surgical anastomoses. Magnetic resonance imaging was able to distinguish between the large vessels from the external carotid systems.ConclusionsVascular imaging maps are challenging in face transplantation because of the rapid circulation times and artifact from the initial injury, prior reconstructive attempts, or both. Nevertheless, face transplant candidates require high spatial and temporal resolution vascular imaging to determine those vessels appropriate for surgical anastomoses.
| S-EPMC3240129 | biostudies-literature
Project description:We present two new fisheye image datasets for training object and face detection models: VOC-360 and Wider-360. The fisheye images are created by post-processing regular images collected from two well-known datasets, VOC2012 and Wider Face, using a model for mapping regular to fisheye images implemented in Matlab. VOC-360 contains 39,575 fisheye images for object detection, segmentation, and classification. Wider-360 contains 63,897 fisheye images for face detection. These datasets will be useful for developing face and object detectors as well as segmentation modules for fisheye images while the efforts to collect and manually annotate true fisheye images are underway.
| S-EPMC6920438 | biostudies-literature