A5004460160- Digital Radiography and Breast Imaging
- Medical Imaging Techniques and Applications
- Radiomics and Machine Learning in Medical Imaging
- Advanced X-ray and CT Imaging
- AI in cancer detection
- Lung Cancer Diagnosis and Treatment
- Particle Detector Development and Performance
- Radiation Detection and Scintillator Technologies
- Advanced Semiconductor Detectors and Materials
- Radiation Dose and Imaging
- CCD and CMOS Imaging Sensors
- COVID-19 diagnosis using AI
- Nuclear Physics and Applications
- Infrared Thermography in Medicine
- Advanced Radiotherapy Techniques
- Advanced MRI Techniques and Applications
- Semiconductor Quantum Structures and Devices
- Medical Image Segmentation Techniques
- Colorectal Cancer Screening and Detection
- Global Cancer Incidence and Screening
- Distributed and Parallel Computing Systems
- Artificial Intelligence in Healthcare
- Functional Brain Connectivity Studies
- Sensor Technology and Measurement Systems
- Gene expression and cancer classification
University of Pisa
2016-2025
Azienda Usl Toscana Centro
2025
Istituto Nazionale di Fisica Nucleare
2008-2025
Azienda Ospedaliera Universitaria Pisana
2024
A. O. Ordine Mauriziano di Torino
2024
Istituto Nazionale di Fisica Nucleare, Sezione di Pisa
2011-2022
Istituto Nazionale di Fisica Nucleare, Sezione di Catania
2012
Istituto Nazionale di Fisica Nucleare, Sezione di Padova
2008
University of Padua
2008
University of Palermo
1995
M5L, a fully automated computer-aided detection (CAD) system for the and segmentation of lung nodules in thoracic computed tomography (CT), is presented validated on several image datasets.M5L combination two independent subsystems, based Channeler Ant Model as tool [lung channeler ant model (lungCAM)] voxel-based neural approach. The lungCAM was upgraded with scan equalization module new procedure to recover connected other structures; its classification module, which makes use feed-forward...
The mammography is the most effective procedure for an early diagnosis of breast cancer. In this paper, algorithm detecting masses in mammographic images will be presented. database consists 3762 digital acquired several hospitals belonging to MAGIC-5 collaboration (Medical Applications on a Grid Infrastructure Connection). A reduction whole image's area under investigation achieved through segmentation process, by means ROI Hunter algorithm, without loss meaningful information. following...
Mass localization plays a crucial role in computer-aided detection (CAD) systems for the classification of suspicious regions mammograms. In this article we present completely automated system masses digitized mammographic images. The tool discuss consists three processing levels: (a) Image segmentation interest (ROIs). This step relies on an iterative dynamical threshold algorithm able to select iso-intensity closed contours around gray level maxima mammogram. (b) ROI characterization by...
Multislice computed tomography (MSCT) is a valuable tool for lung cancer detection, thanks to its ability identify noncalcified nodules of small size (from about 3 mm). Due the large number images generated by MSCT, there much interest in developing computer-aided detection (CAD) systems that could assist radiologists nodule task. A complete multistage CAD system, including boundary segmentation, regions (ROIs) selection, feature extraction, and false positive reduction presented. The...
ABSTRACT Decision‐making systems trained on structural magnetic resonance imaging data of subjects affected by the Alzheimer's disease (AD) and healthy controls (CTRL) are becoming widespread prognostic tools for with mild cognitive impairment (MCI). This study compares performances three classification methods based support vector machines (SVMs), using as initial sets brain voxels (ie, features): (1) segmented grey matter (GM); (2) regions interest (ROIs) voxel‐wise t ‐test filtering; (3)...
Background: Thanks to the evolution of laboratory medicine, point-of-care testing (POCT) for troponin levels in blood (hs-cTn) has been greatly improved order quickly diagnose acute myocardial infarction (AMI) with an accuracy similar standard tests. The rationale HEART POCT study is propose application 0/1 h European Society Cardiology (ESC) algorithm pre-hospital setting using a device (Atellica VTLi). Methods: This prospective comparing patients who underwent VTLi) control group that...
Abstract Super-Resolution Microscopy (SRM) surpasses Abbe's diffraction limit, thus enabling nanoscale observation of cells. However, SRM techniques, such as Stochastic Optical Reconstruction (STORM), suffer from long acquisition times which can significantly impact imaging throughput. To address this issue, we adapted the Enhanced Generative Adversarial Network (ESRGAN) natural to microscopy images. Our goal is generate super-resolution images widefield in shorter times. We implemented for...
The purpose of this study is to develop a software for the extraction hippocampus and surrounding medial temporal lobe (MTL) regions from T1-weighted magnetic resonance (MR) images with no interactive input user, introduce novel statistical indicator, computed on intensities in automatically extracted MTL regions, which measures atrophy, evaluate accuracy newly developed intensity-based measure atrophy (a) distinguish between patients Alzheimer disease (AD), amnestic mild cognitive...
Morphological changes that may arise through a treatment course are probably one of the most significant sources range uncertainty in proton therapy. Non-invasive in-vivo monitoring is useful to increase quality. The INSIDE in-beam Positron Emission Tomography (PET) scanner performs and carbon therapy treatments at National Center Oncological Hadrontherapy (CNAO). It currently clinical trial (ID: NCT03662373) has acquired PET data during various patients. In this work we analyze (IB-PET)...
Abstract Background The role of computed tomography (CT) in the diagnosis and characterization coronavirus disease 2019 (COVID-19) pneumonia has been widely recognized. We evaluated performance a software for quantitative analysis chest CT, LungQuant system, by comparing its results with independent visual evaluations group 14 clinical experts. aim this work is to evaluate ability automated tool extract information from lung relevant design support model. Methods segments both lungs lesions...
This study aims at exploiting artificial intelligence (AI) for the identification, segmentation and quantification of COVID-19 pulmonary lesions. The limited data availability annotation quality are relevant factors in training AI-methods. We investigated effects using multiple datasets, heterogeneously populated annotated according to different criteria.We developed an automated analysis pipeline, LungQuant system, based on a cascade two U-nets. first one (U-net[Formula: see text]) is...
A 4096 pixel Photon Counting Chip (PCC) has been developed and tested. It is aimed primarily at medical imaging although it can be used for other applications involving particle counting. The readout chip consists of a matrix 64 by identical square pixels, whose side measures 170 micrometers bump-bonded to similar GaAs or Si diodes covering sensitive area 1.18 cm2. electronics in each cell comprises preamplifier, discriminator with variable threshold 3-bit tune as well 15-bit counter. Each...