Elena Loli Piccolomini
Current Organizations / Institutes
The organizations/institutes from the scholar's latest article
Previous Organizations / Institutes
The organizations / institutes from the scholar's other articles in the past ten years
Elena Loli Piccolomini has a total of 62 co-authors. Here are the top co-authors by number of shared publications:
- Fabiana Zama
University of Bologna
24 shared publications - Davide Evangelista
Department of Computer Science and Engineering, University of Bologna, Bologna, Italy
14 shared publications - Elena Morotti
University of Bologna
13 shared publications - Germana Landi
Department of Mathematics, University of Bologna, Bologna, Italy
12 shared publications - Damiana Lazzaro
Department of Mathematics, University of Bologna, Bologna, Italy
5 shared publications - James. G. Nagy
Department of Mathematics, Emory University, Atlanta, GA 30322 USA
5 shared publications
Latest Publications
- Open Access
A Diffusion-Based Generative Prior Approach to Sparse-view Computed Tomography
The reconstruction of X-rays CT images from sparse or limited-angle geometries is a highly challenging task. The lack of data typically results in artifacts in the reconstructed image and may even lead to object distortions. For this reason, the use of deep generative models in this context has great interest and potential success. In the Deep Generative Prior (DGP) framework, the use of diffusion-based generative models is combined with an iterative optimization algorithm for the reconstruction of CT images from sinograms acquired under sparse geometries, to maintain the explainability of a model-based approach while introducing the generative power of a neural network. There are therefore several aspects that can be further investigated within these frameworks to improve reconstruction quality, such as image generation, the model, and the iterative algorithm used to solve the minimization problem, for which we propose modifications with respect to existing approaches. The results obtained even under highly sparse geometries are very promising, although further research is clearly needed in this direction.
Open AccessA Diffusion-Based Generative Prior Approach to Sparse-view Computed Tomography
The reconstruction of X-rays CT images from sparse or limited-angle geometries is a highly challenging task. The lack of data typically results in artifacts in the reconstructed image and may even lead to object distortions. For this reason, the use of deep generative models in this context has great interest and potential success. In the Deep Generative Prior (DGP) framework, the use of diffusion-based generative models is combined with an iterative optimization algorithm for the reconstruction of CT images from sinograms acquired under sparse geometries, to maintain the explainability of a model-based approach while introducing the generative power of a neural network. There are therefore several aspects that can be further investigated within these frameworks to improve reconstruction quality, such as image generation, the model, and the iterative algorithm used to solve the minimization problem, for which we propose modifications with respect to existing approaches. The results obtained even under highly sparse geometries are very promising, although further research is clearly needed in this direction.
- Open Access
- 9 February 2026
- Published by Springer Nature in Journal of Scientific Computing
- Vol. 106 (3) , 74
Adaptive Weighted Total Variation Boosted by Learning Techniques in Few-View Tomographic Imaging
This study presents the development of a spatially adaptive weighting strategy for Total Variation regularization, aimed at addressing under-determined linear inverse problems. The method relies on the rapid computation of an accurate approximation of the true image (or its gradient magnitude) through a neural network. Our approach operates without requiring prior knowledge of the noise intensity in the data and avoids the iterative recomputation of weights. Additionally, the paper includes a theoretical analysis of the proposed method, establishing its validity as a regularization approach. This framework integrates advanced neural network capabilities within a regularization context, thereby making the results of the networks interpretable. The results are promising as they enable high-quality reconstructions from limited-view tomographic measurements.
- 9 February 2026
- Published by Springer Nature in Journal of Scientific Computing
- Vol. 106 (3) , 74
Open AccessAdaptive Weighted Total Variation Boosted by Learning Techniques in Few-View Tomographic Imaging
This study presents the development of a spatially adaptive weighting strategy for Total Variation regularization, aimed at addressing under-determined linear inverse problems. The method relies on the rapid computation of an accurate approximation of the true image (or its gradient magnitude) through a neural network. Our approach operates without requiring prior knowledge of the noise intensity in the data and avoids the iterative recomputation of weights. Additionally, the paper includes a theoretical analysis of the proposed method, establishing its validity as a regularization approach. This framework integrates advanced neural network capabilities within a regularization context, thereby making the results of the networks interpretable. The results are promising as they enable high-quality reconstructions from limited-view tomographic measurements.
- 27 March 2025
- Published by Society for Industrial & Applied Mathematics (SIAM) in SIAM Journal on Scientific Computing
- Vol. 47 (2) , C369-C398
A Data-Dependent Regularization Method Based on the Graph Laplacian
We investigate a variational method for ill-posed problems, named [Formula: see text], which embeds a graph Laplacian operator in the regularization term. The novelty of this method lies in constructing the graph Laplacian based on a preliminary approximation of the solution, which is obtained using any existing reconstruction method [Formula: see text] from the literature. As a result, the regularization term is both dependent on and adaptive to the observed data and noise. We demonstrate that [Formula: see text] is a regularization method and rigorously establish both its convergence and stability properties. We present selected numerical experiments in two-dimensional computed tomography, wherein we integrate the [Formula: see text] method with various reconstruction techniques [Formula: see text], including filtered back projection (graphLa+FBP), standard Tikhonov (graphLa+Tik), total variation (graphLa+TV), and a trained deep neural network (graphLa+Net). The [Formula: see text] approach significantly enhances the quality of the approximated solutions for each method [Formula: see text]. Notably, graphLa+Net outperforms, offering a robust and stable application of deep neural networks in solving inverse problems. Reproducibility of computational results. This paper has been awarded the “SIAM Reproducibility Badge: Code and data available” as a recognition that the authors have followed reproducibility principles valued by SISC and the scientific computing community. Code and data that allow readers to reproduce the results in this paper are available at https://github.com/devangelista2/GraphLaPlus and in the supplementary materials ( GraphLaPlus-main.zip [5.12MB]). [Formula: see text]
- 27 March 2025
- Published by Society for Industrial & Applied Mathematics (SIAM) in SIAM Journal on Scientific Computing
- Vol. 47 (2) , C369-C398
A Data-Dependent Regularization Method Based on the Graph Laplacian
We investigate a variational method for ill-posed problems, named [Formula: see text], which embeds a graph Laplacian operator in the regularization term. The novelty of this method lies in constructing the graph Laplacian based on a preliminary approximation of the solution, which is obtained using any existing reconstruction method [Formula: see text] from the literature. As a result, the regularization term is both dependent on and adaptive to the observed data and noise. We demonstrate that [Formula: see text] is a regularization method and rigorously establish both its convergence and stability properties. We present selected numerical experiments in two-dimensional computed tomography, wherein we integrate the [Formula: see text] method with various reconstruction techniques [Formula: see text], including filtered back projection (graphLa+FBP), standard Tikhonov (graphLa+Tik), total variation (graphLa+TV), and a trained deep neural network (graphLa+Net). The [Formula: see text] approach significantly enhances the quality of the approximated solutions for each method [Formula: see text]. Notably, graphLa+Net outperforms, offering a robust and stable application of deep neural networks in solving inverse problems. Reproducibility of computational results. This paper has been awarded the “SIAM Reproducibility Badge: Code and data available” as a recognition that the authors have followed reproducibility principles valued by SISC and the scientific computing community. Code and data that allow readers to reproduce the results in this paper are available at https://github.com/devangelista2/GraphLaPlus and in the supplementary materials ( GraphLaPlus-main.zip [5.12MB]). [Formula: see text]
- Open Access
- 22 March 2025
- Published by Elsevier in Computerized Medical Imaging and Graphics
- Vol. 123, 102530
Deep Guess acceleration for explainable image reconstruction in sparse-view CT
- 22 March 2025
- Published by Elsevier in Computerized Medical Imaging and Graphics
- Vol. 123, 102530
Open AccessDeep Guess acceleration for explainable image reconstruction in sparse-view CT
- 29 January 2025
- Published by Society for Industrial & Applied Mathematics (SIAM) in SIAM Journal on Scientific Computing
- Vol. 47 (1) , C77-C99
To Be or Not to Be Stable, That Is the Question: Understanding Neural Networks for Inverse Problems
The 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. Reproducibility of computational results. This paper has been awarded the “SIAM Reproducibility Badge: Code and data available” as a recognition that the authors have followed reproducibility principles valued by SISC and the scientific computing community. Code and data that allow readers to reproduce the results in this paper are available at https://github.com/loibo/ToBeOrNotToBeStable and in the supplementary material ( ToBeOrNotToBeStable.zip [3.76MB]). [Formula: see text]
- 29 January 2025
- Published by Society for Industrial & Applied Mathematics (SIAM) in SIAM Journal on Scientific Computing
- Vol. 47 (1) , C77-C99
To Be or Not to Be Stable, That Is the Question: Understanding Neural Networks for Inverse Problems
The 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. Reproducibility of computational results. This paper has been awarded the “SIAM Reproducibility Badge: Code and data available” as a recognition that the authors have followed reproducibility principles valued by SISC and the scientific computing community. Code and data that allow readers to reproduce the results in this paper are available at https://github.com/loibo/ToBeOrNotToBeStable and in the supplementary material ( ToBeOrNotToBeStable.zip [3.76MB]). [Formula: see text]
- Open Access
Adaptive Weighted Total Variation boosted by learning techniques in few-view tomographic imaging
This study presents the development of a spatially adaptive weighting strategy for Total Variation regularization, aimed at addressing under-determined linear inverse problems. The method leverages the rapid computation of an accurate approximation of the true image (or its gradient magnitude) through a neural network. Our approach operates without requiring prior knowledge of the noise intensity in the data and avoids the iterative recomputation of weights. Additionally, the paper includes a theoretical analysis of the proposed method, establishing its validity as a regularization approach. This framework integrates advanced neural network capabilities within a regularization context, thereby making the results of the networks interpretable. The results are promising as they enable high-quality reconstructions from limited-view tomographic measurements.
Open AccessAdaptive Weighted Total Variation boosted by learning techniques in few-view tomographic imaging
This study presents the development of a spatially adaptive weighting strategy for Total Variation regularization, aimed at addressing under-determined linear inverse problems. The method leverages the rapid computation of an accurate approximation of the true image (or its gradient magnitude) through a neural network. Our approach operates without requiring prior knowledge of the noise intensity in the data and avoids the iterative recomputation of weights. Additionally, the paper includes a theoretical analysis of the proposed method, establishing its validity as a regularization approach. This framework integrates advanced neural network capabilities within a regularization context, thereby making the results of the networks interpretable. The results are promising as they enable high-quality reconstructions from limited-view tomographic measurements.
- 1 January 2025
- Published by Springer Nature
- p. 360-367
Robust Non-convex Model-Based Approach for Deep Learning-Based Image Processing
- 1 January 2025
- Published by Springer Nature
- p. 360-367
Robust Non-convex Model-Based Approach for Deep Learning-Based Image Processing
- Open Access
Deep Guess acceleration for explainable image reconstruction in sparse-view CT
Sparse-view Computed Tomography (CT) is an emerging protocol designed to reduce X-ray dose radiation in medical imaging. Traditional Filtered Back Projection algorithm reconstructions suffer from severe artifacts due to sparse data. In contrast, Model-Based Iterative Reconstruction (MBIR) algorithms, though better at mitigating noise through regularization, are too computationally costly for clinical use. This paper introduces a novel technique, denoted as the Deep Guess acceleration scheme, using a trained neural network both to quicken the regularized MBIR and to enhance the reconstruction accuracy. We integrate state-of-the-art deep learning tools to initialize a clever starting guess for a proximal algorithm solving a non-convex model and thus computing an interpretable solution image in a few iterations. Experimental results on real CT images demonstrate the Deep Guess effectiveness in (very) sparse tomographic protocols, where it overcomes its mere variational counterpart and many data-driven approaches at the state of the art. We also consider a ground truth-free implementation and test the robustness of the proposed framework to noise.
Open AccessDeep Guess acceleration for explainable image reconstruction in sparse-view CT
Sparse-view Computed Tomography (CT) is an emerging protocol designed to reduce X-ray dose radiation in medical imaging. Traditional Filtered Back Projection algorithm reconstructions suffer from severe artifacts due to sparse data. In contrast, Model-Based Iterative Reconstruction (MBIR) algorithms, though better at mitigating noise through regularization, are too computationally costly for clinical use. This paper introduces a novel technique, denoted as the Deep Guess acceleration scheme, using a trained neural network both to quicken the regularized MBIR and to enhance the reconstruction accuracy. We integrate state-of-the-art deep learning tools to initialize a clever starting guess for a proximal algorithm solving a non-convex model and thus computing an interpretable solution image in a few iterations. Experimental results on real CT images demonstrate the Deep Guess effectiveness in (very) sparse tomographic protocols, where it overcomes its mere variational counterpart and many data-driven approaches at the state of the art. We also consider a ground truth-free implementation and test the robustness of the proposed framework to noise.
- Open Access
- 30 June 2023
- Published by MDPI AG in Journal of Imaging
- Vol. 9 (7) , 133
Ambiguity in Solving Imaging Inverse Problems with Deep-Learning-Based Operators
In 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.
- 30 June 2023
- Published by MDPI AG in Journal of Imaging
- Vol. 9 (7) , 133
Open AccessAmbiguity in Solving Imaging Inverse Problems with Deep-Learning-Based Operators
In 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.
- Open Access
Ambiguity in solving imaging inverse problems with deep learning based operators
In 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 to 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.
Open AccessAmbiguity in solving imaging inverse problems with deep learning based operators
In 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 to 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.