Search

Coronary artery disease, caused by the narrowing of coronary vessels due to atherosclerosis, is the leading cause of death worldwide. The diagnostic gold standard, fractional flow reserve (FFR), measures the trans-stenotic pressure ratio during maximal vasodilation but is invasive and costly. This has driven the development of virtual FFR (vFFR) using computational fluid dynamics (CFD) to simulate coronary flow. Geometric deep learning algorithms have shown promise for learning features on meshes, including cardiovascular research applications. This study empirically analyzes various backends for predicting vFFR fields in coronary arteries as CFD surrogates, comparing six backends for learning hemodynamics on meshes using CFD solutions as ground truth. The study has two parts: i) Using 1,500 synthetic left coronary artery bifurcations, models were trained to predict pressure-related fields for vFFR reconstruction, comparing different learning variables. ii) Using 427 patient-specific CFD simulations, experiments were repeated focusing on the best-performing learning variable from the synthetic dataset. Most backends performed well on the synthetic dataset, especially when predicting pressure drop over the manifold. Transformer-based backends outperformed others when predicting pressure and vFFR fields and were the only models achieving strong performance on patient-specific data, excelling in both average per-point error and vFFR accuracy in stenotic lesions. These results suggest geometric deep learning backends can effectively replace CFD for simple geometries, while transformer-based networks are superior for complex, heterogeneous datasets. Pressure drop was identified as the optimal network output for learning pressure-related fields.

Cardiovascular hemodynamic fields provide valuable medical decision markers for coronary artery disease. Computational fluid dynamics (CFD) is the gold standard for accurate, non-invasive evaluation of these quantities in vivo. In this work, we propose a time-efficient surrogate model, powered by machine learning, for the estimation of pulsatile hemodynamics based on steady-state priors. We introduce deep vectorised operators, a modelling framework for discretisation independent learning on infinite-dimensional function spaces. The underlying neural architecture is a neural field conditioned on hemodynamic boundary conditions. Importantly, we show how relaxing the requirement of point-wise action to permutation-equivariance leads to a family of models that can be parametrised by message passing and self-attention layers. We evaluate our approach on a dataset of 74 stenotic coronary arteries extracted from coronary computed tomography angiography (CCTA) with patient-specific pulsatile CFD simulations as ground truth. We show that our model produces accurate estimates of the pulsatile velocity and pressure while being agnostic to re-sampling of the source domain (discretisation independence). This shows that deep vectorised operators are a powerful modelling tool for cardiovascular hemodynamics estimation in coronary arteries and beyond., Comment: Preprint. Under Review

Fractional flow reserve (FFR) is the gold standard for diagnosing coronary artery disease (CAD). FFRCT uses computational fluid dynamics (CFD) to evaluate FFR non-invasively by simulating coronary flow in geometries reconstructed from computed tomography (CT). However, it faces challenges related to the cost of computing and uncertainties in defining patient-specific boundary conditions (BCs). We investigated using time-averaged steady BCs instead of pulsatile ones to reduce computational time and deployed a self-adjusting method for tuning BCs to patient clinical data. 133 coronary arteries were reconstructed from CT images of CAD patients. For each vessel, invasive FFR was measured. Steady BCs for CFD were defined in two steps: i) rest BCs were extrapolated from clinical and image-derived data; ii) hyperemic BCs were computed from resting conditions. Flow rate was iteratively adjusted during the simulation until patient aortic pressure was matched. Pulsatile BCs were defined using the convergence values of steady BCs. Lesion-specific hemodynamic indexes were computed and compared between groups of patients indicated for surgery and those not. The whole pipeline was implemented as a straightforward, fully automated process. Steady and pulsatile FFRCT showed a strong correlation (r=0.988) and correlated with invasive FFR (r=0.797). The per-point difference between the pressure and FFRCT field predicted by the two methods was below 0.01 and 0.02, respectively. Both approaches exhibited good diagnostic performance: accuracy was 0.860 and 0.864, with AUCs of 0.923 and 0.912, for steady and pulsatile cases, respectively. Computational time for steady BCs CFD was approximately 30-fold lower than for the pulsatile case. This work demonstrates the feasibility of using steady BCs CFD for computing FFRCT in coronary arteries and its performance in a fully automated pipeline.

Low-lying states of $^{94}$Zr were investigated via low-energy multi-step Coulomb excitation. From the measured $\gamma$-ray yields, 13 reduced transition probabilities between low-spin states were determined, together with the spectroscopic quadrupole moments of the $2_{1,2}^+$ states. Based on this information, for the first time in the Zr isotopic chain, the shapes of the $0_{1,2}^+$ states including their deformation softness were inferred in a model-independent way using the quadrupole sum rules approach. The ground state of $^{94}$Zr possesses a rather diffuse shape associated with a spherical configuration, while the $0_2^+$ state is oblate and more strongly deformed. The observed features of shape coexistence in $^{94}$Zr are in agreement with Monte-Carlo shell-model predictions, and the present results are vital to refine the IBM-CM description of the Zr isotopes around $A\approx 100$ in terms of an intertwined quantum phase transition., Comment: 6 pages, 3 figures

Large Language Models (LLMs) have emerged as transformative forces in the realm of natural language processing, wielding the power to generate human-like text. However, despite their potential for content creation, they carry the risk of eroding our Semantic Capital (SC) - the collective knowledge within our digital ecosystem - thereby posing diverse social epistemic challenges. This paper explores the evolution, capabilities, and limitations of these models, while highlighting ethical concerns they raise. The study contribution is two-fold: first, it is acknowledged that, withstanding the challenges of tracking and controlling LLM impacts, it is necessary to reconsider our interaction with these AI technologies and the narratives that form public perception of them. It is argued that before achieving this goal, it is essential to confront a potential deontological tipping point in an increasing AI-driven infosphere. This goes beyond just adhering to AI ethical norms or regulations and requires understanding the spectrum of social epistemic risks LLMs might bring to our collective SC. Secondly, building on Luciano Floridi's taxonomy for SC risks, those are mapped within the functionality and constraints of LLMs. By this outlook, we aim to protect and enrich our SC while fostering a collaborative environment between humans and AI that augments human intelligence rather than replacing it.

Public attention towards explainability of artificial intelligence (AI) systems has been rising in recent years to offer methodologies for human oversight. This has translated into the proliferation of research outputs, such as from Explainable AI, to enhance transparency and control for system debugging and monitoring, and intelligibility of system process and output for user services. Yet, such outputs are difficult to adopt on a practical level due to a lack of a common regulatory baseline, and the contextual nature of explanations. Governmental policies are now attempting to tackle such exigence, however it remains unclear to what extent published communications, regulations, and standards adopt an informed perspective to support research, industry, and civil interests. In this study, we perform the first thematic and gap analysis of this plethora of policies and standards on explainability in the EU, US, and UK. Through a rigorous survey of policy documents, we first contribute an overview of governmental regulatory trajectories within AI explainability and its sociotechnical impacts. We find that policies are often informed by coarse notions and requirements for explanations. This might be due to the willingness to conciliate explanations foremost as a risk management tool for AI oversight, but also due to the lack of a consensus on what constitutes a valid algorithmic explanation, and how feasible the implementation and deployment of such explanations are across stakeholders of an organization. Informed by AI explainability research, we conduct a gap analysis of existing policies, leading us to formulate a set of recommendations on how to address explainability in regulations for AI systems, especially discussing the definition, feasibility, and usability of explanations, as well as allocating accountability to explanation providers., Comment: Submission draft accepted for ACM FAccT 2023

The selenium isotopes lie at the heart of a tumultuous region of the nuclear chart where shape coexistence effects grapple with neutron-proton pairing correlations, triaxiality, and the impending proton dripline. In this work a study of $^{72}$Se by internal conversion electron and $\gamma$-ray spectroscopy was undertaken with the SPICE and TIGRESS arrays. New measurements of the branching ratio and lifetime of the $0_2^+$ state were performed yielding a determination of $\rho^2(E0;0_2^+{\rightarrow}0_1^+)=29(3)$ milliunits. two state mixing calculations were performed that highlighted the importance of interpretation of such $E0$ strength values in the context of shape-coexistence.

With increasing digitalization, Artificial Intelligence (AI) is becoming ubiquitous. AI-based systems to identify, optimize, automate, and scale solutions to complex economic and societal problems are being proposed and implemented. This has motivated regulation efforts, including the Proposal of an EU AI Act. This interdisciplinary position paper considers various concerns surrounding fairness and discrimination in AI, and discusses how AI regulations address them, focusing on (but not limited to) the Proposal. We first look at AI and fairness through the lenses of law, (AI) industry, sociotechnology, and (moral) philosophy, and present various perspectives. Then, we map these perspectives along three axes of interests: (i) Standardization vs. Localization, (ii) Utilitarianism vs. Egalitarianism, and (iii) Consequential vs. Deontological ethics which leads us to identify a pattern of common arguments and tensions between these axes. Positioning the discussion within the axes of interest and with a focus on reconciling the key tensions, we identify and propose the roles AI Regulation should take to make the endeavor of the AI Act a success in terms of AI fairness concerns., Comment: In proceedings of AAAI/ACM Conference AIES 2022 (https://doi.org/10.1145/3514094.3534158)

The structure of 106Pd, populated in the EC/beta+ decay of 106Ag, was investigated at the INFN Legnaro National Laboratories using the Spes Low-energy Internal Conversion Electron Spectrometer (SLICES). The K-internal conversion coefficients of some transitions have been measured and the electric monopole transition strengths, between low-lying 2+ and 0+ states, have been deduced. These experimental data combined with the results from internal conversion electron measurement on 104Pd previously performed by the Florence spectroscopy group were compared with the theoretical values calculated in the framework of the interacting proton-neutron boson model. Good agreement between experimental and theoretical values is found when interpreting the 0+3 level as an intruder state.

To implement a good Content Based Image Retrieval (CBIR) system, it is essential to adopt efficient search methods. One way to achieve this results is by exploiting approximate search techniques. In fact, when we deal with very large collections of data, using an exact search method makes the system very slow. In this project, we adopt the Locality Sensitive Hashing (LSH) index to implement a CBIR system that allows us to perform fast similarity search on deep features. Specifically, we exploit transfer learning techniques to extract deep features from images; this phase is done using two famous Convolutional Neural Networks (CNNs) as features extractors: Resnet50 and Resnet50v2, both pre-trained on ImageNet. Then we try out several fully connected deep neural networks, built on top of both of the previously mentioned CNNs in order to fine-tuned them on our dataset. In both of previous cases, we index the features within our LSH index implementation and within a sequential scan, to better understand how much the introduction of the index affects the results. Finally, we carry out a performance analysis: we evaluate the relevance of the result set, computing the mAP (mean Average Precision) value obtained during the different experiments with respect to the number of done comparison and varying the hyper-parameter values of the LSH index.