arXiv subjects

Luca Mariani

Publications and source records attributed to Luca Mariani.

7 recordsLinked to original sources

arXiv2026

OvAi Focus: AI-based Multi-class Segmentation of Functional Ovaries and Adnexal Masses in Gynecological Ultrasound

Ovarian cancer is the deadliest gynecological malignancy; accurate and objective segmentation of adnexal masses and functional ovaries in ultrasound (US) remains challenging due to operator variability and morphological complexity. We present OvAi Focus (SynDiag s.r.l., Italy), a stand-alone AI software medical device that performs multi-class semantic segmentation of functional ovaries and adnexal masses, distinguishing cystic from solid components. The system was trained and independently validated on a multicenter dataset of 1,081 adult women from 6 centers across Italy and Israel. Segmentation achieved DICE scores of 0.87 (complete lesion), 0.85 (cystic), 0.68 (solid), and 0.62 (functional ovary), in line with or superior to state-of-the-art approaches across heterogeneous acquisition settings.

eess.IV↗

arXiv2025

Assessing Projected Quantum Kernels for the Classification of IoT Data

The use of quantum computing for machine learning is among the most promising applications of quantum technologies. Quantum models inspired by classical algorithms are developed to explore some possible advantages over classical approaches. A primary challenge in the development and testing of Quantum Machine Learning (QML) algorithms is the scarcity of datasets designed specifically for a quantum approach. Existing datasets, often borrowed from classical machine learning, need modifications to be compatible with current quantum hardware. In this work, we utilize a dataset generated by Internet-of-Things (IoT) devices in a format directly compatible with the proposed quantum data process, eliminating the need for feature reduction. Among quantum-inspired machine learning algorithms, the Projected Quantum Kernel (PQK) stands out for its elegant solution of projecting the data encoded in the Hilbert space into a classical space. For a prediction task concerning office room occupancy, we compare PQK with the standard Quantum Kernel (QK) and their classical counterparts to investigate how different feature maps affect the encoding of IoT data. Our findings show that the PQK demonstrates comparable effectiveness to classical methods when the proposed shallow circuit is used for quantum encoding.

quant-ph↗

arXiv2025

Quantum Key Distribution over Complex Networks

There exist several initiatives worldwide to deploy quantum key distribution (QKD) over existing fibre networks and achieve quantum-safe security at large scales. To understand the overall QKD network performance, it is required to transition from the analysis of individual links, as done so far, to the characterization of the network as a whole. In this work, we undertake this study by embedding QKD protocols on complex networks, which correctly model the existing fiber networks. We focus on networks with trusted nodes and on continuous-variable (CV) schemes, which have much higher key rates than their discrete-variable (DV) counterparts. In the effective CV network, however, many of the unique properties of complex networks, such as small-worldness and the presence of hubs, are lost due to the fast decay of the key rate with physical distance for CV systems. These properties can be restored when considering a hybrid network consisting of both CV and DV protocols, achieving at the same time high average rate and inter-connectivity. Our work opens the path to the study of QKD complex networks in existing infrastructures.

quant-ph↗

arXiv2025

Pericoronary adipose tissue attenuation as a predictor of functional severity of coronary stenosis

Objective: This study aims to evaluate the functional significance of coronary stenosis by analyzing low-level radiomic features of the pericoronary adipose tissue (PCAT) surrounding the lesions, which are indicative of its inflammation status. Methods: A dataset of 72 patients who underwent coronary computed tomography angiography (CCTA) was analyzed, with 3D segmentation and computational fluid dynamics (CFD) simulations from a prior study. Centerlines of the main epicardial branches were automatically extracted, and lesions identified using Gaussian kernel regression to estimate healthy branch caliber. PCAT features were computed per vessel following guideline recommendations and per lesion within a region extending radially for two vessel radii. Features like fat volume and mean attenuation (FAI) were analyzed for their relationship with CFD-derived hemodynamic biomarkers, such as fractional flow reserve (FFR) and wall shear stress (WSS). These features also informed a machine learning (ML) model for classifying potentially ischemic lesions. Results: PCAT exhibited, on average, higher attenuation in the presence of hemodynamically significant lesions (i.e., FFR < 0.80), although this difference was of limited statistical significance. The ML classifier, trained on PCAT features, successfully distinguished potentially ischemic lesions, yielding average accuracy of 0.84. Conclusion: PCAT attenuation is correlated with the functional status of coronary stenosis and can be used to inform ML models for predicting potential ischemia. Significance: PCAT features, readily available from CCTA, can be used to predict the hemodynamic characteristics of a lesion without the need for an invasive FFR examination.

eess.IV↗

arXiv2025

Learning Hemodynamic Scalar Fields on Coronary Artery Meshes: A Benchmark of Geometric Deep Learning Models

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.

eess.IV↗

arXiv2024

An automated and time efficient framework for simulation of coronary blood flow under steady and pulsatile conditions

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.

physics.med-ph↗

arXiv2023

Information-theoretical analysis of the neural code for decoupled face representation

Processing faces accurately and efficiently is a key capability of humans and other animals that engage in sophisticated social tasks. Recent studies reported a decoupled coding for faces in the primate inferotemporal cortex, with two separate neural populations coding for the geometric position of (texture-free) facial landmarks and for the image texture at fixed landmark positions, respectively. Here, we formally assess the efficiency of this decoupled coding by appealing to the information-theoretic notion of description length, which quantifies the amount of information that is saved when encoding novel facial images, with a given precision. We show that despite decoupled coding describes the facial images in terms of two sets of principal components (of landmark shape and image texture), it is more efficient (i.e., yields more information compression) than the encoding in terms of the image principal components only, which corresponds to the widely used eigenface method. The advantage of decoupled coding over eigenface coding increases with image resolution and is especially prominent when coding variants of training set images that only differ in facial expressions. Moreover, we demonstrate that decoupled coding entails better performance in three different tasks: the representation of facial images, the (daydream) sampling of novel facial images, and the recognition of facial identities and gender. In summary, our study provides a first principle perspective on the efficiency and accuracy of the decoupled coding of facial stimuli reported in the primate inferotemporal cortex.

q-bio.NC↗