1,720,989 research outputs found
Sparse Regularized CT Reconstruction: An Optimization Perspective
No full textIn Computed Tomography (CT), decreasing the X-rays dose is essential to reduce the negative effects of radiation exposure on the human health. One possible way to accomplish it is to reduce the number of projections acquired, hence the name of sparse CT. Traditional methods for image reconstruction cannot recover reliable images in this case: the lack of information due to the missed projections produces strong artifacts. Alternatively, optimization frameworks are flexible models where incorporated regularization functions impose regularity constraints on the solution, thus avoiding unwanted artifacts and contrasting noise propagation. Since the iterative methods solving the optimization problem calculate more accurate solutions as iterations (and computational time) increase, it is possible to choose a better reconstructed image at the expense of execution time, or viceversa. Parallel implementations of the iterative solvers significantly reduce the computational time, allowing for a large number of iterations in a prefixed short time.Here, the effectiveness of the optimization approach is shown on the case study of 3D reconstruction of breast images from tomosynthesis with tests on real projection data
Fostering fashion retail experiences through virtual reality and voice assistants
No full textThis paper discusses the potential of using vocal commands in a virtual reality (VR) fashion store. In fact, online fashion shopping has bloomed in the last ten years, as technological developments are continuously fostering the evolution of fashion e-commerce and branding strategies. The advance in virtual reality devices, which are approaching the consumers' sphere, cannot but further support such trend.However, such commercial opportunity turns into the challenge of making VR-based shopping experiences enjoyable and easy-to-use to the whole class of users. To this aim, in this paper we resort to one of the most desirable ways a non-expert would use to interact with a new environment: voice. For this reason, the current study explores the benefits of speaking and verbally interacting with a VR assistant, which embodies a salesman at the service of customers. Motivated by an increasing acceptance of voice assistants, we designed and implemented an immersive VR experience where the Amazon Alexa virtual assistant is integrated and exploited, to build a proof of concept. To evaluate our proposal, we selected a specific group of fashion-experts, i.e. demanding and non tech-savvy, which tested our application and appraised the perceived comfort and appreciation of the virtual experience. The preliminary results suggest how working on the VR interface and interaction modalities could open the door to a new wave of fashion e-commerce platforms, supporting a widespread adoption of VR into everyday routines
RISING: A new framework for model-based few-view CT image reconstruction with deep learning
Full text linkMedical image reconstruction from low-dose tomographic data is an active research field, recently revolutionized by the advent of deep learning. In fact, deep learning typically yields superior results than classical optimization approaches, but unstable results have been reported both numerically and theoretically in the literature. This paper proposes RISING, a new framework for sparse-view tomographic image reconstruction combining an early-stopped Rapid Iterative Solver with a subsequent Iteration Network-based Gaining step. In our two-step approach, the first phase executes very few iterations of a regularized model-based algorithm, whereas the second step completes the missing iterations by means of a convolutional neural network. The proposed method is ground-truth free; it exploits the computational speed and flexibility of a data-driven approach, but it also imposes sparsity constraints to the solution as in the model-based setting. Experiments performed both on a digitally created and on a real abdomen data set confirm the numerical and visual accuracy of the reconstructed RISING images in short computational times. These features make the framework promising to be used on real systems for clinical exams
A Model-Based Optimization Framework for Iterative Digital Breast Tomosynthesis Image Reconstruction
Full text linkDigital Breast Tomosynthesis is an X-ray imaging technique that allows a volumetric reconstruction of the breast, from a small number of low-dose two-dimensional projections. Although it is already used in the clinical setting, enhancing the quality of the recovered images is still a subject of research. The aim of this paper was to propose and compare, in a general optimization framework, three slightly different models and corresponding accurate iterative algorithms for Digital Breast Tomosynthesis image reconstruction, characterized by a convergent behavior. The suggested model-based implementations are specifically aligned to Digital Breast Tomosynthesis clinical requirements and take advantage of a Total Variation regularizer. We also tune a fully-automatic strategy to set a proper regularization parameter. We assess our proposals on real data, acquired from a breast accreditation phantom and a clinical case. The results confirm the effectiveness of the presented framework in reconstructing breast volumes, with particular focus on the masses and microcalcifications, in few iterations and in enhancing the image quality in a prolonged execution
Reconstruction of 3D X-Rays CT images from reduced samplings by a scaled gradient projection algorithm
Full text linkWe propose a scaled gradient projection algorithm for the reconstruction of 3D X-ray tomographic images from limited data. The problem arises from the discretization of an ill-posed integral problem and, due to the incompleteness of the data, has infinite possible solutions. Hence, by following a regularization approach, we formulate the reconstruction problem as the nonnegatively constrained minimization of an objective function given by the sum of a fit-to-data term and a smoothed differentiable Total Variation function. The problem is challenging for its very large size and because a good reconstruction is required in a very short time. For these reasons, we propose to use a gradient projection method, accelerated by exploiting a scaling strategy for defining gradient-based descent directions and generalized Barzilai–Borwein rules for the choice of the step-lengths. The numerical results on a 3D phantom are very promising since they show the ability of the scaling strategy to accelerate the convergence in the first iterations
Ambiguity in Solving Imaging Inverse Problems with Deep-Learning-Based Operators
Full text linkIn recent years, large convolutional neural networks have been widely used as tools for image deblurring, because of their ability in restoring images very precisely. It is well known that image deblurring is mathematically modeled as an ill-posed inverse problem and its solution is difficult to approximate when noise affects the data. Really, one limitation of neural networks for deblurring is their sensitivity to noise and other perturbations, which can lead to instability and produce poor reconstructions. In addition, networks do not necessarily take into account the numerical formulation of the underlying imaging problem when trained end-to-end. In this paper, we propose some strategies to improve stability without losing too much accuracy to deblur images with deep-learning-based methods. First, we suggest a very small neural architecture, which reduces the execution time for training, satisfying a green AI need, and does not extremely amplify noise in the computed image. Second, we introduce a unified framework where a pre-processing step balances the lack of stability of the following neural-network-based step. Two different pre-processors are presented. The former implements a strong parameter-free denoiser, and the latter is a variational-model-based regularized formulation of the latent imaging problem. This framework is also formally characterized by mathematical analysis. Numerical experiments are performed to verify the accuracy and stability of the proposed approaches for image deblurring when unknown or not-quantified noise is present; the results confirm that they improve the network stability with respect to noise. In particular, the model-based framework represents the most reliable trade-off between visual precision and robustness
Stunkard Figure Rating Scale and Sexuality During Pregnancy. A Longitudinal, Pilot Study
No full textBody image and body weight may be associated with sexuality in pregnant women.
Twenty pregnant women filled in the two-factor McCoy Female Questionnaire, the Stunkard Figure Rating Scale and the Beck's Depression Inventory Questionnaire. In the pregnant women, the number of intercourses/week and the McCoy Female Questionnaire score for sexuality significantly decreased. The Stunkard Figure Rating Scale evidenced that the "actual body" silhouette score increased during the third trimester of pregnancy and that the women worsened the feeling with their own body image.Changes in body appearance, during pregnancy, and the women's fear of being less attractive for their partners may have lasting effects on sexuality
A fast Total Variation-based iterative algorithm for digital breast tomosynthesis image reconstruction
No full textIn this work, we propose a fast iterative algorithm for the reconstruction of digital breast tomosynthesis images. The algorithm solves a regularization problem, expressed as the minimization of the sum of a least-squares term and a weighted smoothed version of the Total Variation regularization function.We use a Fixed Point method for the solution of the minimization problem, requiring the solution of a linear system at each iteration, whose coefficient matrix is a positive definite approximation of the Hessian of the objective function.We propose an efficient implementation of the algorithm, where the linear system is solved by a truncated Conjugate Gradient method. We compare the Fixed Point implementation with a fast first order method such as the Scaled Gradient Projection method, that does not require any linear system solution. Numerical experiments on a breast phantom widely used in tomographic simulations show that both the methods recover microcalcifications very fast while the Fixed Point is more efficient in detecting masses, when more time is available for the algorithm execution
TO BE OR NOT TO BE STABLE, THAT IS THE QUESTION: UNDERSTANDING NEURAL NETWORKS FOR INVERSE PROBLEMS
Full text linkThe solution of linear inverse problems arising, for example, in signal and image
processing is a challenging problem since the ill-conditioning amplifies, in the solution, the noise
present in the data. Recently introduced algorithms based on deep learning overwhelm the more
traditional model-based approaches in performance, but they typically suffer from instability with
respect to data perturbation. In this paper, we theoretically analyze the trade-off between stability
and accuracy of neural networks when used to solve linear imaging inverse problems for cases that
are not underdetermined. Moreover, we propose different supervised and unsupervised solutions to
increase the network stability and maintain a good accuracy, by means of regularization properties
inherited from a model-based iterative scheme during the network training. Extensive numerical
experiments on image deblurring confirm the theoretical results and the effectiveness of the proposed
deep learning--based approaches to handle noise on the data
- …
