Roberto Casula

Exploiting multiple representations: 3D face biometrics fusion with application to surveillance

Simone Maurizio La Cava, Roberto Casula, Sara Concas, Giulia Orrù et autres

3D face reconstruction (3DFR) aims to recover a 3D face model from 2D images, providing richer representations that can enhance downstream face analytic tasks. Many 3DFR methods have been developed based on specific assumptions tailored to the limits and characteristics of the …

it, es, cz (code pays fourni par la source)

Surgical Versus Transcatheter Aortic Valve Replacement in Patients Aged >60 Years With Bicuspid Valve Stenosis: A Time‐to‐Event Data Meta‐Analysis

Marco Moscarelli, Patrizio Lancellotti, Thanos Athanasiou, Roberto Casula et autres

Background The role of transcatheter aortic valve implantation (TAVI) in bicuspid aortic valve stenosis requires further evaluation, particularly as its use has become comparable to surgical aortic valve replacement. We sought to compare midterm outcomes of TAVI and surgical aortic valve replacement …

it, gb, Ouganda, us (code pays fourni par la source)

FaceSpoofLDM: Language-Guided Synthesis of Face Presentation Attacks Based on Latent Diffusion

A. Dörsch, Marcel Grimmer, L. J. Gonzalez-Soler, Roberto Casula et autres

Presentation Attacks (PAs) pose a serious threat to face recognition (FR) systems. These attacks cover a broad range of scenarios, including images replayed on various devices, printed photographs, or more sophisticated approaches such as 3D masks used to impersonate another identity. Recent …

de, it (code pays fourni par la source)

Early post-TAVI thrombocytopenia recovery and subsequent subclinical leaflet thrombosis

Thanos Athanasiou, Roberto Casula, Mai‐Linh Nguyen Trung, Petitjean Hélène et autres

Abstract Objective Post-implant thrombocytopenia and subclinical leaflet thrombosis (SLT) are two common phenomena, yet their potential interplay remains unexplored. This study aimed to determine whether early platelet dynamics differed in patients diagnosed with SLT on multidetector computed tomography (MDCT) compared with those …

gb, it, fr, Ouganda (code pays fourni par la source)

Percutaneous left atrial appendage occlusion following failed surgical ligation for incessant left atrial appendage tachycardia: key role of multimodality imaging

Joseph Okafor, Balrik Kailey, Alfa Ali, Prapakaran Kanagaratnam et autres

We describe the case of a 31-year-old male with incessant left atrial appendage tachycardia and resultant severe left ventricular systolic dysfunction. Despite medical therapy, catheter ablation and surgical excision of the left atrial appendage with the AtriClip device, the tachycardia persistent. Following …

gb, us (code pays fourni par la source)

Combined Adversarial Attacks for Breaking Fingerprint Recognition and Presentation Attack Detection

Simone Zedda, Simone Maurizio La Cava, Roberto Casula, Gian Luca Marcialis

Recent advances in machine and deep learning played a crucial role in developing Fingerprint Presentation Attack Detection (FPAD) modules, aiming at mitigating attacks leveraging artificial fingerprint replicas against Automated Fingerprint Identification Systems (AFISs). However, these advances also introduce a new threat: adversarial …

it (code pays fourni par la source)

LivDet2025: Toward Robust and Generalizable Fingerprint Presentation Attack Detection

Giulia M. Orrù, Marco Micheletto, Roberto Casula, Simone Zedda et autres

The Fingerprint Liveness Detection Competition (LivDet) is a recurring benchmark series that evaluates the effectiveness of software-based Presentation Attack Detection (PAD) algorithms in fingerprint recognition. LivDet2025 presents three challenges: (1) "Liveness Detection in Action", requiring the integration of PAD with user-specific recognition; …

it, us, de (code pays fourni par la source)

Predicting subclinical leaflet thrombosis in self-expandable prosthesis: A multimodal machine learning analysis

Marco Moscarelli, Thanos Athanasiou, Roberto Casula, Vincenzo Pernice et autres

Objective: Subclinical leaflet thrombosis is a known finding after transcatheter aortic valve implantation, but its predictors remain poorly defined. Machine learning offers new opportunities for identifying complex, nonlinear relationships among clinical, anatomic, and hematological variables. Methods: We analyzed data from 118 patients …

it, gb, pl (code pays fourni par la source)

Interpretability of fingerprint presentation attack detection systems: a look at the “representativeness” of samples against never-seen-before attacks

Simone Carta, Roberto Casula, Giulia Orrù, Marco Micheletto et autres

Abstract Nowadays, fingerprint Presentation Attack Detection systems (PADs) are primarily based on deep learning architectures subjected to massive training. However, their performance decreases to never-seen-before attacks. With the goal of contributing to explaining this issue, we hypothesized that this limited ability to …

it (code pays fourni par la source)

Extraction of a bullet that migrated to the left ventricle: A case report

Riccardo Abbasciano, Maryam Alfa‐Wali, Marco Scarci, Andrés Díaz-Campos et autres

A continuous trend toward an increase in the number of gunshot wounds has been described in several countries, including the United Kindom.1 Bullet emboli is a rare occurrence wherein the foreign body enters the victim's circulatory system with a low velocity and …

gb (code pays fourni par la source)

Exploring 3D Face Reconstruction and Fusion Methods for Face Verification: A Case-Study in Video Surveillance

Simone Maurizio La Cava, Sara Concas, Rubén Tolosana, Roberto Casula et autres

it, es, cz (code pays fourni par la source)

Vulnerabilities in Machine Learning-Based Voice Disorder Detection Systems

Gianpaolo Perelli, Andrea Panzino, Roberto Casula, Marco Micheletto et autres

The impact of voice disorders is becoming more widely acknowledged as a public health issue. Several machine learning-based classifiers with the potential to identify disorders have been used in recent studies to differentiate between normal and pathological voices and sounds. In this …

it (code pays fourni par la source)