arXiv subjects

Michele Piana

Publications and source records attributed to Michele Piana.

At least 19 recordsLinked to original sources

arXiv2026

Count-based spectral component imaging (CCI) of solar flares in X-rays

X-ray emission in solar flares is produced by both multi-thermal plasma and accelerated electrons. Classical imaging approaches reconstruct X-ray intensity maps which contain contributions from multiple spectral components (e.g., hot, superhot, and non-thermal), and do not allow retrieving the morphology of the different components separately. We introduce a novel imaging technique, called "Count-based spectral Component Imaging (CCI)", to jointly reconstruct spatially resolved emission measure maps of the thermal components, and the electron flux distribution of the non-thermal component from data provided by the Spectrometer/Telescope for Imaging X-rays (STIX) aboard Solar Orbiter. We formulate a linear model linking the Differential Emission Measure (DEM), approximated by two thermal components, and the non-thermal electron flux to the observed counts. The resulting inverse problem is solved with the Richardson-Lucy algorithm. We apply CCI to STIX observations of SOL2024-10-01T22 and compare it with the previously developed Spectral Component Imaging (SCI) method, as well as classical imaging approaches. The reconstructed thermal and non-thermal components show good agreement with those obtained using SCI. This proof-of-concept study shows that CCI obtains results consistent with SCI but with fewer inputs. In contrast with SCI, CCI can also be applied to hard X-ray focusing optics imaging.

astro-ph.SR↗

arXiv2025

PRESOL: a web-based computational setting for feature-based flare forecasting

Solar flares are the most explosive phenomena in the solar system and the main trigger of the events' chain that starts from Coronal Mass Ejections and leads to geomagnetic storms with possible impacts on the infrastructures at Earth. Data-driven solar flare forecasting relies on either deep learning approaches, which are operationally promising but with a low explainability degree, or machine learning algorithms, which can provide information on the physical descriptors that mostly impact the prediction. This paper describes a web-based technological platform for the execution of a computational pipeline of feature-based machine learning methods that provide predictions of the flare occurrence, feature ranking information, and assessment of the prediction performances.

astro-ph.SR↗

arXiv2025

When algebra twinks system biology: a conjecture on the structure of Gröbner bases in complex chemical reaction networks

We address the challenge of identifying all real positive steady states in chemical reaction networks (CRNs) governed by mass-action kinetics. Traditional numerical methods often require specific initial guesses and may fail to find all the solutions in systems exhibiting multistability. Gröbner bases offer an algebraic framework that systematically transforms polynomial equations into simpler forms, facilitating comprehensive solution enumeration. In this work, we propose a conjecture that CRNs with at most pairwise interactions yield Gröbner bases possessing a near-"triangular" structure, under appropriate assumptions. We illustrate this phenomenon using examples from a gene regulatory network and the Wnt signaling pathway, where the Gröbner basis approach reliably captures all real positive solutions. Our computational experiments reveal the potential of Gröbner bases to overcome limitations of local numerical methods for finding the steady states of complex biological systems, making them a powerful tool for understanding dynamical processes across diverse biochemical models.

q-bio.MN↗

arXiv2025

CLEAN and multi-scale CLEAN for STIX in Solar Orbiter

CLEAN is a well-established deconvolution approach to Fourier imaging at both radio wavelwengths and hard X-ray energies. However, specifically for hard X-ray imaging, CLEAN suffers two significant drawbacks: a rather limited degree of automation, and a tendency to under-resolution. This paper introduces a multi-scale version of CLEAN specifically tailored to the reconstruction of images from measurements observed by the Spectrometer/Telescope for Imaging X-rays (STIX) on-board Solar Orbiter. Using synthetic STIX data, this study shows that multi-scale CLEAN may represent a reliable solution to the two previously mentioned CLEAN limitations. Further, this paper shows the performances of CLEAN and its multi-scale release in reconstructing experimental real scenarios characterized by complex emission morphologies.

astro-ph.SR↗

arXiv2025

tiDAS: a time invariant approximation of the Delay and Sum algorithm for biomedical ultrasound PSF reconstructions

Ultrasound imaging is a real-time diagnostic modality that reconstructs acoustic signals into visual representations of internal body structures. A key component in this process is beamforming, with the Delay and Sum (DAS) algorithm being a standard due to its balance between simplicity and effectiveness. However, the computational cost of DAS can be a limiting factor, especially in real-time scenarios where fast frame reconstruction is essential. In this work, we introduce a time-invariant approximation of the DAS algorithm (tiDAS), designed to accelerate the reconstruction process without compromising image quality. By adopting a one-dimensional, row-wise convolutional formulation, tiDAS significantly reduces computational complexity while preserving the core properties of the original model. This approach not only enables faster image reconstruction but also provides a structured foundation for the application of deconvolution methods aimed at enhancing resolution. Synthetic experiments demonstrate that tiDAS achieves a favorable trade-off between speed and accuracy, making it a promising tool for improving the efficiency of real-time ultrasound imaging.

math.NA↗

arXiv2025

AI-based modular warning machine for risk identification in proximity healthcare

"DHEAL-COM - Digital Health Solutions in Community Medicine" is a research and technology project funded by the Italian Department of Health for the development of digital solutions of interest in proximity healthcare. The activity within the DHEAL-COM framework allows scientists to gather a notable amount of multi-modal data whose interpretation can be performed by means of machine learning algorithms. The present study illustrates a general automated pipeline made of numerous unsupervised and supervised methods that can ingest such data, provide predictive results, and facilitate model interpretations via feature identification.

cs.LG↗

arXiv2025

Solving Implicit Inverse Problems with Homotopy-Based Regularization Path

Implicit inverse problems, in which noisy observations of a physical quantity are used to infer a nonlinear functional applied to an associated function, are inherently ill posed and often exhibit non uniqueness of solutions. Such problems arise in a range of domains, including the identification of systems governed by Ordinary and Partial Differential Equations (ODEs/PDEs), optimal control, and data assimilation. Their solution is complicated by the nonlinear nature of the underlying constraints and the instability introduced by noise. In this paper, we propose a homotopy based optimization method for solving such problems. Beginning with a regularized constrained formulation that includes a sparsity promoting regularization term, we employ a gradient based algorithm in which gradients with respect to the model parameters are efficiently computed using the adjoint state method. Nonlinear constraints are handled through a Newton Raphson procedure. By solving a sequence of problems with decreasing regularization, we trace a solution path that improves stability and enables the exploration of multiple candidate solutions. The method is applied to the latent dynamics discovery problem in simulation, highlighting performance as a function of ground truth sparsity and semi convergence behavior.

math.NA↗

arXiv2025

Probabilistic approach to longitudinal response prediction: application to radiomics from brain cancer imaging

Longitudinal imaging analysis tracks disease progression and treatment response over time, providing dynamic insights into treatment efficacy and disease evolution. Radiomic features extracted from medical imaging can support the study of disease progression and facilitate longitudinal prediction of clinical outcomes. This study presents a probabilistic model for longitudinal response prediction, integrating baseline features with intermediate follow-ups. The probabilistic nature of the model naturally allows to handle the instrinsic uncertainty of the longitudinal prediction of disease progression. We evaluate the proposed model against state-of-the-art disease progression models in both a synthetic scenario and using a brain cancer dataset. Results demonstrate that the approach is competitive against existing methods while uniquely accounting for uncertainty and controlling the growth of problem dimensionality, eliminating the need for data from intermediate follow-ups.

stat.AP↗

arXiv2025

DISARM++: Beyond scanner-free harmonization

Harmonization of T1-weighted MR images across different scanners is crucial for ensuring consistency in neuroimaging studies. This study introduces a novel approach to direct image harmonization, moving beyond feature standardization to ensure that extracted features remain inherently reliable for downstream analysis. Our method enables image transfer in two ways: (1) mapping images to a scanner-free space for uniform appearance across all scanners, and (2) transforming images into the domain of a specific scanner used in model training, embedding its unique characteristics. Our approach presents strong generalization capability, even for unseen scanners not included in the training phase. We validated our method using MR images from diverse cohorts, including healthy controls, traveling subjects, and individuals with Alzheimer's disease (AD). The model's effectiveness is tested in multiple applications, such as brain age prediction (R2 = 0.60 \pm 0.05), biomarker extraction, AD classification (Test Accuracy = 0.86 \pm 0.03), and diagnosis prediction (AUC = 0.95). In all cases, our harmonization technique outperforms state-of-the-art methods, showing improvements in both reliability and predictive accuracy. Moreover, our approach eliminates the need for extensive preprocessing steps, such as skull-stripping, which can introduce errors by misclassifying brain and non-brain structures. This makes our method particularly suitable for applications that require full-head analysis, including research on head trauma and cranial deformities. Additionally, our harmonization model does not require retraining for new datasets, allowing smooth integration into various neuroimaging workflows. By ensuring scanner-invariant image quality, our approach provides a robust and efficient solution for improving neuroimaging studies across diverse settings. The code is available at this link.

cs.CV↗

arXiv2025

Physics-informed features in supervised machine learning

Supervised machine learning involves approximating an unknown functional relationship from a limited dataset of features and corresponding labels. The classical approach to feature-based machine learning typically relies on applying linear regression to standardized features, without considering their physical meaning. This may limit model explainability, particularly in scientific applications. This study proposes a physics-informed approach to feature-based machine learning that constructs non-linear feature maps informed by physical laws and dimensional analysis. These maps enhance model interpretability and, when physical laws are unknown, allow for the identification of relevant mechanisms through feature ranking. The method aims to improve both predictive performance in regression tasks and classification skill scores by integrating domain knowledge into the learning process, while also enabling the potential discovery of new physical equations within the context of explainable machine learning.

stat.ML↗

arXiv2025

Segmentation variability and radiomics stability for predicting Triple-Negative Breast Cancer subtype using Magnetic Resonance Imaging

Most papers caution against using predictive models for disease stratification based on unselected radiomic features, as these features are affected by contouring variability. Instead, they advocate for the use of the Intraclass Correlation Coefficient (ICC) as a measure of stability for feature selection. However, the direct effect of segmentation variability on the predictive models is rarely studied. This study investigates the impact of segmentation variability on feature stability and predictive performance in radiomics-based prediction of Triple-Negative Breast Cancer (TNBC) subtype using Magnetic Resonance Imaging. A total of 244 images from the Duke dataset were used, with segmentation variability introduced through modifications of manual segmentations. For each mask, explainable radiomic features were selected using the Shapley Additive exPlanations method and used to train logistic regression models. Feature stability across segmentations was assessed via ICC, Pearson's correlation, and reliability scores quantifying the relationship between feature stability and segmentation variability. Results indicate that segmentation accuracy does not significantly impact predictive performance. While incorporating peritumoral information may reduce feature reproducibility, it does not diminish feature predictive capability. Moreover, feature selection in predictive models is not inherently tied to feature stability with respect to segmentation, suggesting that an overreliance on ICC or reliability scores for feature selection might exclude valuable predictive features.

stat.AP↗

arXiv2025

Solar flares as electron accelerators: toward a resolution of the acceleration efficiency issue

A major open issue concerning the active Sun is the effectiveness with which magnetic reconnection accelerates electrons in flares. A paper published by {\em{Nature}} in 2022 used microwave observations to conclude that the Sun is an almost ideal accelerator, energizing nearly all electrons within a coronal volume to nonthermal energies. Shortly thereafter, a paper published in {\em{Astrophysical Journal Letters}} used hard X-ray measurements \emph{of the same event} to reach the contradictory conclusion that less than 1\% of the available electrons were accelerated. Here we address this controversy by using spatially resolved observations of hard X-ray emission and a spectral inversion method to determine the evolution of the electron spectrum throughout the flare. So we estimated the density of the medium where electrons accelerate and, from this, the ratio of accelerated to ambient electron densities. Results show that this ratio never exceeds a percent or so in the cases analyzed.

astro-ph.SR↗

arXiv2025

Artificial Intelligence Could Have Predicted All Space Weather Events Associated with the May 2024 Superstorm

Space weather, driven by solar flares and Coronal Mass Ejections (CMEs), poses significant risks to technological systems. Accurately forecasting these events and their impact on Earth's magnetosphere remains a challenge because of the complexity of solar-terrestrial interactions. This study applied artificial intelligence (AI) to predict the chain of events associated with the May $2024$ superstorm, including solar flares from NOAA active region 13644, Earth-directed CMEs, and a violent geomagnetic storm. Using magnetogram cut-outs, a Vision Transformer was able to classify the evolution of the active region morphologies, and a video-based deep learning method predicted the occurrence of solar flares; a physics-driven model improved the precision of CME travel-time prediction using coronal observations and solar wind measurements; and a data-driven method exploited these in situ measurements to sound alerts of the geomagnetic storm unrolled over time. The results showed unprecedented accuracy in predicting CME arrival with uncertainty as small as one minute. Moreover, these AI models outperformed traditional methods in predicting solar flares occurrences, onset, and recovery phases of the geomagnetic storm. These findings highlight the impressive potential of AI for space weather forecasting and as a tool to mitigate the impact of extreme solar events on critical infrastructure.

astro-ph.SR↗

arXiv2024

Deep Learning for Active Region Classification: A Systematic Study from Convolutional Neural Networks to Vision Transformers

A solar active region can significantly disrupt the Sun Earth space environment, often leading to severe space weather events such as solar flares and coronal mass ejections. As a consequence, the automatic classification of active region groups is the crucial starting point for accurately and promptly predicting solar activity. This study presents our results concerned with the application of deep learning techniques to the classification of active region cutouts based on the Mount Wilson classification scheme. Specifically, we have explored the latest advancements in image classification architectures, from Convolutional Neural Networks to Vision Transformers, and reported on their performances for the active region classification task, showing that the crucial point for their effectiveness consists in a robust training process based on the latest advances in the field.

astro-ph.SR↗

arXiv2024

Extended Drag-Based Model for better predicting the evolution of Coronal Mass Ejections

The solar wind drag-based model is a widely used framework for predicting the propagation of Coronal Mass Ejections (CMEs) through interplanetary space. This model primarily considers the aerodynamic drag exerted by the solar wind on CMEs. However, factors like magnetic forces, pressure gradients, and the internal dynamics within CMEs justify the need of introducing an additional small-scale acceleration term in the game. Indeed, by accounting for this extra acceleration, the extended drag-based model is shown to offer improved accuracy in describing the evolution of CMEs through the heliosphere and, in turn, in forecasting CME trajectories and arrival times at Earth. This enhancement is crucial for better predicting Space Weather events and mitigating their potential impacts on space-based and terrestrial technologies.

astro-ph.SR↗

arXiv2024

RIS: Regularized Imaging Spectroscopy for STIX on-board Solar Orbiter

Imaging spectroscopy, i.e., the generation of spatially resolved count spectra and of cubes of count maps at different energies, is one of the main goals of solar hard X-ray missions based on Fourier imaging. For these telescopes, so far imaging spectroscopy has been realized via the generation of either count maps independently reconstructed at the different energy channels, or electron flux maps reconstructed via deconvolution of the bremsstrahlung cross-section. Our aim is to introduce the Regularized Imaging Spectroscopy method (RIS), in which regularization implemented in the count space imposes a smoothing constraint across contiguous energy channels, without the need to deconvolve the bremsstrahlung effect. STIX records imaging data computing visibilities in the spatial frequency domain. Our RIS is a sequential scheme in which part of the information coded in the image reconstructed at a specific energy channel is transferred to the reconstruction process at a contiguous channel via visibility interpolation based on Variably Scaled Kernels. In the case of STIX visibilities recorded during the November 11, 2022 flaring event, we show that RIS is able to generate hard X-ray maps whose morphology smoothly evolves from one energy channel to the contiguous one, and that from these maps it is possible to infer spatially-resolved count spectra characterized by notable numerical stability. We also show that the performances of this approach are robust with respect to both the image reconstruction method and the count energy channel utilized to trigger the sequential process. RIS is appropriate to construct image cubes from STIX visibilities that are characterized by a smooth behavior across count energies, thus allowing the generation of numerically stable (and, thus, physically reliable) local count spectra.

astro-ph.SR↗

arXiv2024

Localized FDG loss in lung cancer lesions

Purpose: Analysis of [18F]-Fluorodeoxyglucose (FDG) kinetics in cancer has been most often limited to the evaluation of the average uptake over relatively large volumes. Nevertheless, tumor lesion almost contains inflammatory infiltrates whose cells are characterized by a significant radioactivity washout due to the hydrolysis of FDG-6P catalyzed by glucose-6P phosphatase. The present study aimed to verify whether voxel-wise compartmental analysis of dynamic imaging can identify tumor regions characterized by tracer washout. Materials & Methods: The study included 11 patients with lung cancer submitted to PET/CT imaging for staging purposes. Tumor was defined by drawing a volume of interest loosely surrounding the lesion and considering all inside voxels with standardized uptake value (SUV) >40% of the maximum. After 20 minutes dynamic imaging centered on the heart, eight whole body scans were repeated. Six parametric maps were progressively generated by computing six regression lines that considered all eight frames, the last seven ones, and so on, up to the last three. Results: Progressively delaying the starting point of regression line computation identified a progressive increase in the prevalence of voxels with a negative slope. Conclusions: The voxel-wise parametric maps provided by compartmental analysis permits to identify a measurable volume characterized by radioactivity washout. The spatial localization of this pattern is compatible with the recognized preferential site of inflammatory infiltrates populating the tumor stroma and might improve the power of FDG imaging in monitoring the effectiveness of treatments aimed to empower the host immune response against the cancer.

q-bio.TO↗

arXiv2024

Forecasting Geoffective Events from Solar Wind Data and Evaluating the Most Predictive Features through Machine Learning Approaches

This study addresses the prediction of geomagnetic disturbances by exploiting machine learning techniques. Specifically, the Long-Short Term Memory recurrent neural network, which is particularly suited for application over long time series, is employed in the analysis of in-situ measurements of solar wind plasma and magnetic field acquired over more than one solar cycle, from $2005$ to $2019$, at the Lagrangian point L$1$. The problem is approached as a binary classification aiming to predict one hour in advance a decrease in the SYM-H geomagnetic activity index below the threshold of $-50$ nT, which is generally regarded as indicative of magnetospheric perturbations. The strong class imbalance issue is tackled by using an appropriate loss function tailored to optimize appropriate skill scores in the training phase of the neural network. Beside classical skill scores, value-weighted skill scores are then employed to evaluate predictions, suitable in the study of problems, such as the one faced here, characterized by strong temporal variability. For the first time, the content of magnetic helicity and energy carried by solar transients, associated with their detection and likelihood of geo-effectiveness, were considered as input features of the network architecture. Their predictive capabilities are demonstrated through a correlation-driven feature selection method to rank the most relevant characteristics involved in the neural network prediction model. The optimal performance of the adopted neural network in properly forecasting the onset of geomagnetic storms, which is a crucial point for giving real warnings in an operational setting, is finally showed.

physics.space-ph↗