arXiv subjects

Pierangelo Veltri

Publications and source records attributed to Pierangelo Veltri.

16 recordsLinked to original sources

arXiv2026

A Usable GAN-Based Tool for Synthetic ECG Generation in Cardiac Amyloidosis Research

Cardiac amyloidosis (CA) is a rare and underdiagnosed infiltrative cardiomyopathy, and available datasets for machine-learning models are typically small, imbalanced and heterogeneous. This paper presents a Generative Adversarial Network (GAN) and a graphical command-line interface for generating realistic synthetic electrocardiogram (ECG) beats to support early diagnosis and patient stratification in CA. The tool is designed for usability, allowing clinical researchers to train class-specific generators once and then interactively produce large volumes of labelled synthetic beats that preserve the distribution of minority classes.

cs.LG↗

arXiv2025

Context-Gated Cross-Modal Perception with Visual Mamba for PET-CT Lung Tumor Segmentation

Accurate lung tumor segmentation is vital for improving diagnosis and treatment planning, and effectively combining anatomical and functional information from PET and CT remains a major challenge. In this study, we propose vMambaX, a lightweight multimodal framework integrating PET and CT scan images through a Context-Gated Cross-Modal Perception Module (CGM). Built on the Visual Mamba architecture, vMambaX adaptively enhances inter-modality feature interaction, emphasizing informative regions while suppressing noise. Evaluated on the PCLT20K dataset, the model outperforms baseline models while maintaining lower computational complexity. These results highlight the effectiveness of adaptive cross-modal gating for multimodal tumor segmentation and demonstrate the potential of vMambaX as an efficient and scalable framework for advanced lung cancer analysis. The code is available at https://github.com/arco-group/vMambaX.

cs.CV↗

arXiv2025

Kolmogorov Arnold Network Autoencoder in Medicine

Deep learning neural networks architectures such Multi Layer Perceptrons (MLP) and Convolutional blocks still play a crucial role in nowadays research advancements. From a topological point of view, these architecture may be represented as graphs in which we learn the functions related to the nodes while fixed edges convey the information from the input to the output. A recent work introduced a new architecture called Kolmogorov Arnold Networks (KAN) that reports how putting learnable activation functions on the edges of the neural network leads to better performances in multiple scenarios. Multiple studies are focusing on optimizing the KAN architecture by adding important features such as dropout regularization, Autoencoders (AE), model benchmarking and last, but not least, the KAN Convolutional Network (KCN) that introduced matrix convolution with KANs learning. This study aims to benchmark multiple versions of vanilla AEs (such as Linear, Convolutional and Variational) against their Kolmogorov-Arnold counterparts that have same or less number of parameters. Using cardiological signals as model input, a total of five different classic AE tasks were studied: reconstruction, generation, denoising, inpainting and anomaly detection. The proposed experiments uses a medical dataset \textit{AbnormalHeartbeat} that contains audio signals obtained from the stethoscope.

cs.LG↗

arXiv2025

E-ABIN: an Explainable module for Anomaly detection in BIological Networks

The increasing availability of large-scale omics data calls for robust analytical frameworks capable of handling complex gene expression datasets while offering interpretable results. Recent advances in artificial intelligence have enabled the identification of aberrant molecular patterns distinguishing disease states from healthy controls. Coupled with improvements in model interpretability, these tools now support the identification of genes potentially driving disease phenotypes. However, current approaches to gene anomaly detection often remain limited to single datasets and lack accessible graphical interfaces. Here, we introduce E-ABIN, a general-purpose, explainable framework for Anomaly detection in Biological Networks. E-ABIN combines classical machine learning and graph-based deep learning techniques within a unified, user-friendly platform, enabling the detection and interpretation of anomalies from gene expression or methylation-derived networks. By integrating algorithms such as Support Vector Machines, Random Forests, Graph Autoencoders (GAEs), and Graph Adversarial Attributed Networks (GAANs), E-ABIN ensures a high predictive accuracy while maintaining interpretability. We demonstrate the utility of E-ABIN through case studies of bladder cancer and coeliac disease, where it effectively uncovers biologically relevant anomalies and offers insights into disease mechanisms.

cs.LG↗

arXiv2025

ExDiff: A Framework for Simulating Diffusion Processes on Complex Networks with Explainable AI Integration

Understanding and controlling diffusion processes in complex networks is critical across domains ranging from epidemiology to information science. Here, we present ExDiff, an interactive and modular computational framework that integrates network simulation, graph neural networks (GNNs), and explainable artificial intelligence (XAI) to model and interpret diffusion dynamics. ExDiff combines classical compartmental models with deep learning techniques to capture both the structural and temporal characteristics of diffusion across diverse network topologies. The framework features dedicated modules for network analysis, neural modeling, simulation, and interpretability, all accessible via an intuitive interface built on Google Colab. Through a case study of the Susceptible Infectious Recovered Vaccinated Dead (SIRVD) model, we demonstrate the capacity to simulate disease spread, evaluate intervention strategies, classify node states, and reveal the structural determinants of contagion through XAI techniques. By unifying simulation and interpretability, ExDiff provides a powerful, flexible, and accessible platform for studying diffusion phenomena in networked systems, enabling both methodological innovation and practical insight.

cs.SI↗

arXiv2025

Towards medical AI misalignment: a preliminary study

Despite their staggering capabilities as assistant tools, often exceeding human performances, Large Language Models (LLMs) are still prone to jailbreak attempts from malevolent users. Although red teaming practices have already identified and helped to address several such jailbreak techniques, one particular sturdy approach involving role-playing (which we named `Goofy Game') seems effective against most of the current LLMs safeguards. This can result in the provision of unsafe content, which, although not harmful per se, might lead to dangerous consequences if delivered in a setting such as the medical domain. In this preliminary and exploratory study, we provide an initial analysis of how, even without technical knowledge of the internal architecture and parameters of generative AI models, a malicious user could construct a role-playing prompt capable of coercing an LLM into producing incorrect (and potentially harmful) clinical suggestions. We aim to illustrate a specific vulnerability scenario, providing insights that can support future advancements in the field.

cs.CY↗

arXiv2025

Decoding Rarity: Large Language Models in the Diagnosis of Rare Diseases

Recent advances in artificial intelligence, particularly large language models LLMs, have shown promising capabilities in transforming rare disease research. This survey paper explores the integration of LLMs in the analysis of rare diseases, highlighting significant strides and pivotal studies that leverage textual data to uncover insights and patterns critical for diagnosis, treatment, and patient care. While current research predominantly employs textual data, the potential for multimodal data integration combining genetic, imaging, and electronic health records stands as a promising frontier. We review foundational papers that demonstrate the application of LLMs in identifying and extracting relevant medical information, simulating intelligent conversational agents for patient interaction, and enabling the formulation of accurate and timely diagnoses. Furthermore, this paper discusses the challenges and ethical considerations inherent in deploying LLMs, including data privacy, model transparency, and the need for robust, inclusive data sets. As part of this exploration, we present a section on experimentation that utilizes multiple LLMs alongside structured questionnaires, specifically designed for diagnostic purposes in the context of different diseases. We conclude with future perspectives on the evolution of LLMs towards truly multimodal platforms, which would integrate diverse data types to provide a more comprehensive understanding of rare diseases, ultimately fostering better outcomes in clinical settings.

cs.CL↗

arXiv2024

DCAE-SR: Design of a Denoising Convolutional Autoencoder for reconstructing Electrocardiograms signals at Super Resolution

Electrocardiogram (ECG) signals play a pivotal role in cardiovascular diagnostics, providing essential information on the electrical activity of the heart. However, the inherent noise and limited resolution in ECG recordings can hinder accurate interpretation and diagnosis. In this paper, we propose a novel model for ECG super resolution (SR) that uses a DNAE to enhance temporal and frequency information inside ECG signals. Our approach addresses the limitations of traditional ECG signal processing techniques. Our model takes in input 5-second length ECG windows sampled at 50 Hz (very low resolution) and it is able to reconstruct a denoised super-resolution signal with an x10 upsampling rate (sampled at 500 Hz). We trained the proposed DCAE-SR on public available myocardial infraction ECG signals. Our method demonstrates superior performance in reconstructing high-resolution ECG signals from very low-resolution signals with a sampling rate of 50 Hz. We compared our results with the current deep-learning literature approaches for ECG super-resolution and some non-deep learning reproducible methods that can perform both super-resolution and denoising. We obtained current state-of-the-art performances in super-resolution of very low resolution ECG signals frequently corrupted by ECG artifacts. We were able to obtain a signal-to-noise ratio of 12.20 dB (outperforms previous 4.68 dB), mean squared error of 0.0044 (outperforms previous 0.0154) and root mean squared error of 4.86% (outperforms previous 12.40%). In conclusion, our DCAE-SR model offers a robust (to artefact presence), versatile and explainable solution to enhance the quality of ECG signals. This advancement holds promise in advancing the field of cardiovascular diagnostics, paving the way for improved patient care and high-quality clinical decisions

eess.SP↗

arXiv2024

Leveraging graph neural networks for supporting Automatic Triage of Patients

Patient triage plays a crucial role in emergency departments, ensuring timely and appropriate care based on correctly evaluating the emergency grade of patient conditions. Triage methods are generally performed by human operator based on her own experience and information that are gathered from the patient management process. Thus, it is a process that can generate errors in emergency level associations. Recently, Traditional triage methods heavily rely on human decisions, which can be subjective and prone to errors. Recently, a growing interest has been focused on leveraging artificial intelligence (AI) to develop algorithms able to maximize information gathering and minimize errors in patient triage processing. We define and implement an AI based module to manage patients emergency code assignments in emergency departments. It uses emergency department historical data to train the medical decision process. Data containing relevant patient information, such as vital signs, symptoms, and medical history, are used to accurately classify patients into triage categories. Experimental results demonstrate that the proposed algorithm achieved high accuracy outperforming traditional triage methods. By using the proposed method we claim that healthcare professionals can predict severity index to guide patient management processing and resource allocation.

cs.LG↗

arXiv2023

A novel Network Science Algorithm for Improving Triage of Patients

Patient triage plays a crucial role in healthcare, ensuring timely and appropriate care based on the urgency of patient conditions. Traditional triage methods heavily rely on human judgment, which can be subjective and prone to errors. Recently, a growing interest has been in leveraging artificial intelligence (AI) to develop algorithms for triaging patients. This paper presents the development of a novel algorithm for triaging patients. It is based on the analysis of patient data to produce decisions regarding their prioritization. The algorithm was trained on a comprehensive data set containing relevant patient information, such as vital signs, symptoms, and medical history. The algorithm was designed to accurately classify patients into triage categories through rigorous preprocessing and feature engineering. Experimental results demonstrate that our algorithm achieved high accuracy and performance, outperforming traditional triage methods. By incorporating computer science into the triage process, healthcare professionals can benefit from improved efficiency, accuracy, and consistency, prioritizing patients effectively and optimizing resource allocation. Although further research is needed to address challenges such as biases in training data and model interpretability, the development of AI-based algorithms for triaging patients shows great promise in enhancing healthcare delivery and patient outcomes.

cs.LG↗

arXiv2022

Design and Development of PCN-Miner: A tool for the Analysis of Protein Contact Networks

Protein Contact Network (PCN) is a powerful tool for analysing the structure and function of proteins. In particular, PCN has been used for disclosing the molecular features of allosteric regulation through PCN clustering. Such analysis is relevant in many applications, such as the recent study of SARS-CoV-2 Spike Protein. Despite its relevance, methods for the analysis of PCN are spread into a set of different libraries and tools. Therefore, the introduction of a tool that incorporates all the function may help researchers. We present PCN-Miner a software tool implemented in the Python programming language able to import protein in the Protein Data Bank format and generate the corresponding protein contact network. Then it offers a set of algorithms for the analysis of PCS that cover a large set of applications: from clustering to embedding and subsequent analysis. Software is available at \url{https://github.com/hguzzi/ProteinContactNetworks}

q-bio.QM↗

arXiv2021

Using Dual-Network Analyser for extracting communities from Dual Networks

The representation of data and its relationships using networks is prevalent in many research fields such as computational biology, medical informatics and social networks. Recently, complex networks models have been introduced to better capture the insights of the modelled scenarios. Among others, dual networks -based models have been introduced, which consist in mapping information as pair of networks containing the same nodes but different edges. We focus on the use of a novel approach to visualise and analyse dual networks. The method uses two algorithms for community discovery, and it is provided as a Python-based tool with a graphical user interface. The tool is able to load dual networks and to extract both the densest connected subgraph as well as the common modular communities. The latter is obtained by using an adapted implementation of the Louvain algorithm. The proposed algorithm and graphical tool have been tested by using social, biological, and co-authorship networks. Results demonstrate that the proposed approach is efficient and is able to extract meaningful information from dual networks. Finally, as contribution, the proposed graphical user interface can be considered a valuable innovation to the context.

cs.SI↗

arXiv2020

Extracting Dense and Connected Subgraphs in Dual Networks by Network Alignment

The use of network based approaches to model and analyse large datasets is currently a growing research field. For instance in biology and medicine, networks are used to model interactions among biological molecules as well as relations among patients. Similarly, data coming from social networks can be trivially modelled by using graphs. More recently, the use of dual networks gained the attention of researchers. A dual network model uses a pair of graphs to model a scenario in which one of the two graphs is usually unweighted (a network representing physical associations among nodes) while the other one is edge-weighted (a network representing conceptual associations among nodes). In this paper we focus on the problem of finding the Densest Connected sub-graph (DCS) having the largest density in the conceptual network which is also connected in the physical network. The problem is relevant but also computationally hard, therefore the need for introducing of novel algorithms arises. We formalise the problem and then we map DCS into a graph alignment problem. Then we propose a possible solution. A set of experiments is also presented to support our approach.

cs.DS↗

arXiv2018

HetNetAligner: Design and Implementation of an algorithm for heterogeneous network alignment on Apache Spark

The importance of the use of networks to model and analyse biological data and the interplay of bio-molecules is widely recognised. Consequently, many algorithms for the analysis and the comparison of networks (such as alignment algorithms) have been developed in the past. Recently, many different approaches tried to integrate into a single model the interplay of different molecules, such as genes, transcription factors and microRNAs. A possible formalism to model such scenario comes from node coloured networks (or heterogeneous networks) implemented as node/ edge-coloured graphs. Consequently, the need for the introduction of alignment algorithms able to analyse heterogeneous networks arises. To the best of our knowledge, all the existing algorithms are not able to mine heterogeneous networks. We propose a two-step alignment strategy that receives as input two heterogeneous networks (node-coloured graphs) and a similarity function among nodes of two networks extending the previous formulations. We first build a single alignment graph. Then we mine this graph extracting relevant subgraphs. Despite this simple approach, the analysis of such networks relies on graph and subgraph isomorphism and the size of the data is still growing. Therefore the use of high-performance data analytics framework is needed. We here present HetNetAligner a framework built on top of Apache Spark. We also implemented our algorithm, and we tested it on some selected heterogeneous biological networks. Preliminary results confirm that our method may extract relevant knowledge from biological data reducing the computational time.

cs.DC↗

arXiv2014

A web-based tool to Analyze Semantic Similarity Networks

In computational biology, biological entities such as genes or proteins are usually annotated with terms extracted from Gene Ontology (GO). The functional similarity among terms of an ontology is evaluated by using Semantic Similarity Measures (SSM). More recently, the extensive application of SSMs yielded to the Semantic Similarity Networks (SSNs). SSNs are edge-weighted graphs where the nodes are concepts (e.g. proteins) and each edge has an associated weight that represents the semantic similarity among related pairs of nodes. The analysis of SSNs may reveal biologically meaningful knowledge. For these aims, the need for the introduction of tool able to manage and analyze SSN arises. Consequently we developed SSN-Analyzer a web based tool able to build and preprocess SSN. As proof of concept we demonstrate that community detection algorithms applied to filtered (thresholded) networks, have better performances in terms of biological relevance of the results, with respect to the use of raw unfiltered networks.

cs.CE↗

arXiv2013

Thresholding of Semantic Similarity Networks using a Spectral Graph Based Technique

Semantic similarity measures (SSMs) refer to a set of algorithms used to quantify the similarity of two or more terms belonging to the same ontology. Ontology terms may be associated to concepts, for instance in computational biology gene and proteins are associated with terms of biological ontologies. Thus, SSMs may be used to quantify the similarity of genes and proteins starting from the comparison of the associated annotations. SSMs have been recently used to compare genes and proteins even on a system level scale. More recently some works have focused on the building and analysis of Semantic Similarity Networks (SSNs) i.e. weighted networks in which nodes represents genes or proteins while weighted edges represent the semantic similarity score among them. SSNs are quasi-complete networks, thus their analysis presents different challenges that should be addressed. For instance, the need for the introduction of reliable thresholds for the elimination of meaningless edges arises. Nevertheless, the use of global thresholding methods may produce the elimination of meaningful nodes, while the use of local thresholds may introduce biases. For these aims, we introduce a novel technique, based on spectral graph considerations and on a mixed global-local focus. The effectiveness of our technique is demonstrated by using markov clustering for the extraction of biological modules. We applied clustering to simplified networks demonstrating a considerable improvements with respect to the original ones.

q-bio.MN↗