A5080167379- Cardiac electrophysiology and arrhythmias
- ECG Monitoring and Analysis
- Atrial Fibrillation Management and Outcomes
- Radiomics and Machine Learning in Medical Imaging
- Heart Rate Variability and Autonomic Control
- Cardiac Arrhythmias and Treatments
- Advanced X-ray and CT Imaging
- EEG and Brain-Computer Interfaces
- Head and Neck Cancer Studies
- MRI in cancer diagnosis
- Non-Invasive Vital Sign Monitoring
- Sarcoma Diagnosis and Treatment
- Cardiac Imaging and Diagnostics
- Orthopaedic implants and arthroplasty
- Total Knee Arthroplasty Outcomes
- Cardiovascular Disease and Adiposity
- Head and Neck Surgical Oncology
- Phonocardiography and Auscultation Techniques
- Orthopedic Infections and Treatments
- Ion channel regulation and function
- Pancreatic and Hepatic Oncology Research
- Amyloidosis: Diagnosis, Treatment, Outcomes
- Cardiovascular Syncope and Autonomic Disorders
- Cardiovascular Function and Risk Factors
- Lung Cancer Diagnosis and Treatment
Politecnico di Milano
2016-2025
Centro Cardiologico Monzino
2022-2025
Bioengineering Technology and Systems (Italy)
2018-2024
Istituti di Ricovero e Cura a Carattere Scientifico
2024
University Hospital Leipzig
2008
University Hospital Magdeburg
2007
Polytechnic University
2006
Purpose To assess the feasibility of grading soft tissue sarcomas (STSs) using MRI features (radiomics). Materials and Methods (echo planar SE, 1.5T) from 19 patients with STSs a known histological grading, were retrospectively analyzed. The apparent diffusion coefficient (ADC) maps, obtained by diffusion‐weighted imaging acquisitions, analyzed through 65 radiomic features, intensity‐based (first order statistics, FOS) texture (gray level co‐occurrence matrix, GLCM; gray run length GLRLM)...
Undiagnosed atrial fibrillation (AF) patients are at high risk of cardioembolic stroke or other complications. The aim this study was to analyze the blood volume pulse (BVP) signals obtained from a wristband device and develop an algorithm for discriminating AF normal sinus rhythm (NSR) arrhythmias (ARR).Thirty with AF, 9 ARR 31 in NSR were included study. recordings rest Empatica E4 lasted 10 min. analysis, on 2 min segment, spectral, variability irregularity analysis performed...
To evaluate stability and machine learning-based classification performance of radiomic features spine bone tumors using diffusion- T2-weighted magnetic resonance imaging (MRI).This retrospective study included 101 patients with histology-proven tumor (22 benign; 38 primary malignant; 41 metastatic). All volumes were manually segmented on morphologic sequences. The same region interest (ROI) was used to perform analysis ADC map. A total 1702 considered. Feature assessed through small...
The purpose of the paper was to use a virtual phantom identify set radiomic features from T1-weighted and T2-weighted magnetic resonance imaging (MRI) brain which is stable variations in image acquisition parameters evaluate effect preprocessing on stability.Stability different sources variability (time repetition echo, voxel size, random noise intensity non-uniformity) evaluated for both MRI images. A 107 features, accounting shape first order statistics, textural used. Feature stability...
The objectives of the study are to develop a new way assess stability and discrimination capacity radiomic features without need test-retest or multiple delineations use information obtained perform preliminary feature selection. Apparent diffusion coefficient (ADC) maps were computed from diffusion-weighted magnetic resonance images (DW-MRI) two groups patients: 18 with soft tissue sarcomas (STS) oropharyngeal cancers (OPC). Sixty-nine computed, using three different histogram...
Background Impaired heart rate variability (HRV) is associated with increased mortality in sinus rhythm. However, HRV has not been systematically assessed patients atrial fibrillation (AF). We hypothesized that parameters of may be predictive cardiovascular death AF. Methods and Results From the multicenter prospective Swiss‐AF (Swiss Atrial Fibrillation) Cohort Study, we enrolled 1922 who were rhythm or Resting ECG recordings 5‐minute duration obtained at baseline. Standard (HRV triangular...
Advanced stage nasopharyngeal cancer (NPC) shows highly variable treatment outcomes, suggesting the need for independent prognostic factors. This study aims at developing a magnetic resonance imaging (MRI)-based radiomic signature as marker different clinical endpoints in NPC patients from non-endemic areas. A total 136 with advanced and available MRI (T1-weighted T2-weighted) were selected. For each patient, 2144 features extracted main tumor largest lymph node. multivariate Cox regression...
Objective: The present study addresses the problem of estimating respiratory rate from morphological ECG variations in presence atrial fibrillatory waves (f-waves). significance performing f-wave suppression before estimation is investigated. Methods: performance a novel approach to ECG-derived respiration, named “slope range” (SR) and designed particularly for operation fibrillation (AF), compared that two well-known methods based on either R-wave angle (RA) or QRS loop rotation (LA). A...
Introduction Coronary Artery Disease (CAD) is a leading cause of global mortality, accurate stenosis grading crucial for treatment planning, it currently requires time-consuming manual assessment and suffers from interobserver variability. Few deep learning methods have been proposed automated scoring, but none explored combining radiomic autoencoder (AE)-based features. This study develops machine approach AE-based features grade evaluation multiplanar reconstructed images (MPR) cardiac...
Coronavirus disease (COVID-19), caused by the severe acute respiratory syndrome coronavirus 2 (SARS-CoV-2), is rapidly spreading across globe. The clinical spectrum of SARS-CoV-2 pneumonia requires early detection and monitoring, within a environment for critical cases remotely mild cases, with large symptoms. fear contamination in environments has led to dramatic reduction on-site referrals routine care. There also been perceived need continuously monitor non-severe COVID-19 patients,...
Background: Total hip arthroplasty (THA) follow-up is conventionally conducted with serial X-ray imaging in order to ensure the early identification of implant failure. The purpose this study develop an automated radiographic failure detection system. Methods: 630 patients THA were included study, two thirds which needed total or partial revision for prosthetic loosening. analysis based on one antero-posterior and lateral view obtained from each patient during routine post-surgery follow-up....
. At present, the prognostic prediction in advanced oral cavity squamous cell carcinoma (OCSCC) is based on tumor-node-metastasis (TNM) staging system, and most used imaging modality these patients magnetic resonance image (MRI). With aim to improve prediction, we developed an MRI-based radiomic signature as a marker for overall survival (OS) OCSCC compared it with published gene expression signatures prognosis of OS head neck cancer patients, replicated herein our dataset.For each patient,...
Cardiac amyloidosis (CA) shares similar clinical and imaging characteristics (e.g., hypertrophic phenotype) with aortic stenosis (AS), but its prognosis is generally worse than severe AS alone. Recent studies suggest that the presence of CA frequent (1 out 8 patients) in patients AS. The coexistence two diseases complicates therapeutic management both conditions. Thus, there an urgent need to standardize optimize diagnostic process aim this study develop a robust reliable radiomics-based...
The extent of response to neoadjuvant chemotherapy predicts survival in Ewing sarcoma. This study focuses on MRI radiomics skeletal sarcoma and aims investigate feature reproducibility machine learning prediction chemotherapy.This retrospective included thirty patients with biopsy-proven sarcoma, who were treated before surgery at two tertiary centres. 7 poor responders 23 good based pathological assessment the surgical specimen. On pre-treatment T1-weighted T2-weighted MRI, 2D 3D tumour...
Abstract summary In this paper, several radiomics‐based predictive models of response to induction chemotherapy (IC) in sinonasal cancers (SNCs) are built and tested. Models were as a combination radiomic features extracted from three types MRI images: T1‐weighted images, T2‐weighted images apparent diffusion coefficient (ADC) maps. Fifty patients (aged 54 ± 12 years, 41 men) included study. Patients classified according their IC (25 responders 25 nonresponders). Not all acquired for the...
Revision hip arthroplasty has a less favorable outcome than primary total and an understanding of the timing failure may be helpful. The aim this study is to develop combined deep learning (DL) machine (ML) approach automatically detect prosthetic from conventional plain radiographs.Two cohorts patients (of 280 352 patients) were included in study, for model development validation, respectively. analysis was based on one antero-posterior lateral radiographic view obtained each patient during...