A5091804792- Radiomics and Machine Learning in Medical Imaging
- COVID-19 diagnosis using AI
- Advanced X-ray and CT Imaging
- COVID-19 and healthcare impacts
- COVID-19 Clinical Research Studies
- MRI in cancer diagnosis
- Hepatocellular Carcinoma Treatment and Prognosis
- Breast Lesions and Carcinomas
- Digital Radiography and Breast Imaging
- Cardiac Valve Diseases and Treatments
- Breast Cancer Treatment Studies
- Radiology practices and education
- Radiation Dose and Imaging
- Artificial Intelligence in Healthcare and Education
- AI in cancer detection
- Non-Invasive Vital Sign Monitoring
- Liver Disease and Transplantation
- Renal cell carcinoma treatment
- Global Cancer Incidence and Screening
- Venous Thromboembolism Diagnosis and Management
- Vascular Procedures and Complications
- Advanced MRI Techniques and Applications
- Medical Imaging Techniques and Applications
- Abdominal vascular conditions and treatments
- Anatomy and Medical Technology
Fondazione IRCCS Ca' Granda Ospedale Maggiore Policlinico
2022-2025
Ospedale Maggiore
2024-2025
University of Cambridge
2025
Istituti di Ricovero e Cura a Carattere Scientifico
2025
University of Milan
2020-2024
Fondazione Poliambulanza Istituto Ospedaliero
2022
IRCCS Policlinico San Donato
2022
Chest x-ray (CXR) can play a role in diagnosing patients with suspected severe acute respiratory syndrome coronavirus 2 (SARS-CoV-2) infection, but only few small-scale studies are available. We assessed the diagnostic performance of CXR consecutive presenting at emergency room Policlinico San Donato, Milan, Italy from February 24 to April 8, 2020 for SARS-CoV-2 infection. The results were classified as positive or negative according original prospective radiologic reports. To overcome...
Background Lower muscle mass is a known predictor of unfavorable outcomes, but its prognostic impact on patients with COVID-19 unknown. Purpose To investigate the contribution CT-derived status in predicting clinical outcomes COVID-19. Materials and Methods Clinical or laboratory data (intensive care unit [ICU] admission death) were retrospectively retrieved for reverse transcriptase polymerase chain reaction-confirmed SARS-CoV-2 infection, who underwent chest CT four hospitals Northern...
Abstract Background Integration of imaging and clinical parameters could improve the stratification COVID-19 patients on emergency department (ED) admission. We aimed to assess extent pulmonary abnormalities chest x-ray (CXR) using a semiquantitative severity score, correlating it with data testing its interobserver agreement. Methods From February 22 April 8, 2020, 926 consecutive referring ED two institutions in Northern Italy for suspected SARS-CoV-2 infection were reviewed. Patients...
Mammographic breast density (BD) is commonly visually assessed using the Breast Imaging Reporting and Data System (BI-RADS) four-category scale. To overcome inter- intraobserver variability of visual assessment, authors retrospectively developed externally validated a software for BD classification based on convolutional neural networks from mammograms obtained between 2017 2020. The tool was trained majority category determined by seven board-certified radiologists who independently 760...
Purpose To report the results of our preliminary experience in treating patients with papillary thyroid microcarcinoma (PTMC) image-guided thermal ablation, particular estimating feasibility, safety and short-term efficacy Materials Methods From 2018 cytologically proven PTMC < 10 mm were discussed a multidisciplinary team evaluated for feasibility ablation. In case technical three possible alternatives (i.e., surgery, active surveillance) patients. Patients who agreed to be treated...
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...
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...
Abstract Objectives To estimate tumour volume doubling time (TVDT) of interval cancers (ICs). Methods Two radiologists retrospectively reviewed prior screening and diagnostic mammograms measured mean diameter on “visible” ICs. Univariate analyses clinicopathological variables (ER, HER2, grade, age at diagnosis, breast density) were undertaken, those with p < 0.1 included in a generalised linear model to TVDT, cancer size screening, visibility for “non-visible” tumours. Results From 2011...
Background/Objectives: Vacuum-assisted excision (VAE) is a minimally invasive technique for breast tumor treatment, offering precision, comfort, and quick recovery. It widely used benign lesions playing an increasingly important role in the therapeutic management of non-surgical patients or who refuse surgery. Optimal outcomes require understanding device features to tailor treatment each lesion. The Mammotome® Elite 10G operates fixed mode, while Revolve EX 8G offers multiple aspiration...
Spontaneous abdominal muscle bleeding is an uncommon condition that usually arises in elderly and fragile patients. Commonly affected areas include body wall muscles, particularly the rectus sheath iliopsoas, with clinical manifestations such as pain, groin anemia, severe cases, hemorrhagic shock. A computed tomography multiphase scan preferred modality of examination, it allows characterization hematomas assessment active bleeding. Conservative management coagulopathy standard care for...
This study evaluates the capabilities of large language models, specifically GPT-4, in interpreting mammographic images. The analysis involved 120 images equally divided between cases with and without mammography's findings. Without additional context, LLM was tasked to generate reports based solely on these GPT-4 correctly identified projections 53.3% showed varying degrees accuracy identifying microcalcifications masses. highlighted GPT-4's embryonic interpretative abilities a sensitivity...
Background/Objectives: the aim of this study was to evaluate safety and efficacy percutaneous transhepatic lithotripsy using SpyGlassDSTM cholangioscopy system for treatment difficult stones. Methods: Retrospectively, all patients treated with were analyzed. As primary outcome measures, following data assessed: presence a previous history hepatobiliary disease, location stones, reasons choice procedure, balloon bilioplasty, type pre-procedural imaging, procedural time, technical success,...
Abstract The aim of the article is to introduce a new term in post-procedural events related procedure itself. All Societies and Councils report these as complications they are divided mild, moderate severe or immediate delayed. On other hand error known application wrong plan, strategy achieve goal. For first time, we trying “consequence”; assuming that only available best fit clinical indication, consequence should be seen an expected unavoidable occurrence “adverse event” despite correct...