A5082859766- Dental Radiography and Imaging
- Advanced X-ray and CT Imaging
- Cardiac Imaging and Diagnostics
- Orthodontics and Dentofacial Orthopedics
- Aortic Disease and Treatment Approaches
- Radiomics and Machine Learning in Medical Imaging
- Cardiac Valve Diseases and Treatments
- Advanced MRI Techniques and Applications
- Artificial Intelligence in Healthcare and Education
- Aortic aneurysm repair treatments
- Cardiovascular Function and Risk Factors
- Cardiovascular Disease and Adiposity
- Craniofacial Disorders and Treatments
- Medical Imaging Techniques and Applications
- Congenital Heart Disease Studies
- Biomarkers in Disease Mechanisms
- Anatomy and Medical Technology
- Facial Rejuvenation and Surgery Techniques
- Cleft Lip and Palate Research
- Connective tissue disorders research
- Endodontics and Root Canal Treatments
- AI in cancer detection
- Facial Nerve Paralysis Treatment and Research
- Bone and Dental Protein Studies
- Cerebrovascular and Carotid Artery Diseases
Stanford University
2020-2025
IRCCS Policlinico San Donato
2017-2023
Palo Alto University
2021
Politecnico di Milano
2013-2021
University of Milan
2013-2020
KU Leuven
2016-2018
We report the results of a survey conducted among ESR members in November and December 2018, asking for expectations about artificial intelligence (AI) 5-10 years. Of 24,000 contacted, 675 (2.8%) completed survey, 454 males (67%), 555 (82%) working at academic/public hospitals. AI impact was mostly expected (≥ 30% responders) on breast, oncologic, thoracic, neuro imaging, mainly involving mammography, computed tomography, magnetic resonance. Responders foresee on: job opportunities (375/675,...
BACKGROUND: Risk stratification is highly desirable in patients with uncomplicated Stanford type B aortic dissection but inadequately supported by evidence. We sought to validate externally a published prediction model for late adverse events (LAEs), consisting of 1 clinical (connective tissue disease) and 4 imaging variables: maximum diameter, false lumen circumferential angle, outflow, number identifiable intercostal arteries. METHODS: assembled retrospective multicenter cohort (ROADMAP...
To objectively compare the influence of different cone-beam computed tomography (CBCT) devices, high-density materials and field views (FOVs) on metal artifact expression.For this in vitro study, three customized acrylic resin phantoms containing cylinders: titanium, copper-aluminum alloy amalgam were scanned CBCT devices using high-resolution protocols, same voxel size (0.2 mm) FOVs. After fully automatic segmentation image registration, region interest was defined for small medium The...
Abstract Machine learning (ML) and deep (DL) systems, currently employed in medical image analysis, are data-driven models often considered as black boxes . However, improved transparency is needed to translate automated decision-making clinical practice. To this aim, we propose a strategy open the box by presenting radiologist annotated cases (ACs) proximal current case (CC), making decision rationale uncertainty more explicit. The ACs, used for training, validation, testing supervised...
To assess whether three-dimensional morphometric parameters could be useful in nasal septal deviation (NSD) diagnosis and, secondarily, CBCT considered an adequate imaging technique for the proposed task.We analysed images of 46 subjects who underwent reasons not related to this study. Two experienced operators divided all into healthy and NSD subjects. Subsequently, were segmented using ITK Snap order obtain model airways compute four morphological parameters: angle (SDA), percentage volume...
Karate is a martial art that partly depends on subjective scoring of complex movements. Principal component analysis (PCA)-based methods can identify the fundamental synergies (principal movements) motor system, providing quantitative global technique. In this study, we aimed at describing multi-joint karate performance, under hypothesis latter are skilldependent; estimate karateka's experience level, expressed as years practice. A motion capture system recorded traditional techniques 10...
Pulmonary parenchymal and vascular damage are frequently reported in COVID-19 patients can be assessed with unenhanced chest computed tomography (CT), widely used as a triaging exam. Integrating clinical data, CT features, CT-derived metrics, we aimed to build predictive model of in-hospital mortality using univariate analysis (Mann–Whitney U test) machine learning models (support vectors machines (SVM) multilayer perceptrons (MLP)). Patients RT-PCR-confirmed SARS-CoV-2 infection performed...
Breast arterial calcifications (BAC) are a sex-specific cardiovascular disease biomarker that might improve risk stratification in women. We implemented deep convolutional neural network for automatic BAC detection and quantification.In this retrospective study, four readers labelled four-view mammograms as positive (BAC+) or negative (BAC-) at image level. Starting from pretrained VGG16 model, we trained to discriminate BAC+ BAC- mammograms. Accuracy, F1 score, area under the receiver...
Coronary CT angiography is increasingly used for cardiac diagnosis. Dose modulation techniques can reduce radiation dose, but resulting functional images are noisy and challenging analysis. This retrospective study describes evaluates a deep learning method denoising imaging, taking advantage of multiphase information in three-dimensional convolutional neural network. angiograms (