A5022112211- Radiomics and Machine Learning in Medical Imaging
- Advanced X-ray and CT Imaging
- COVID-19 diagnosis using AI
- Surgical Simulation and Training
- Anatomy and Medical Technology
- Lung Cancer Diagnosis and Treatment
- Augmented Reality Applications
- Hepatocellular Carcinoma Treatment and Prognosis
- Radiation Dose and Imaging
- Liver Disease and Transplantation
- Colorectal Cancer Treatments and Studies
- Medical Imaging Techniques and Applications
- Ultrasound in Clinical Applications
- Pancreatic and Hepatic Oncology Research
- Cardiac Arrest and Resuscitation
- Traumatic Brain Injury and Neurovascular Disturbances
- Colorectal Cancer Surgical Treatments
- Trauma Management and Diagnosis
- Organ Transplantation Techniques and Outcomes
- Liver Disease Diagnosis and Treatment
- Radiology practices and education
- Thermal Regulation in Medicine
- COVID-19 and healthcare impacts
- COVID-19 Clinical Research Studies
- Anorectal Disease Treatments and Outcomes
University of Milan
2019-2025
Ospedale Maggiore
2020-2024
Azienda Socio Sanitaria Territoriale Grande Ospedale Metropolitano Niguarda
2020-2024
Fondazione IRCCS Ca' Granda Ospedale Maggiore Policlinico
2022
Luigi Sacco Hospital
2020
The purpose of this paper is to develop and validate a delta-radiomics score predict the response individual colorectal cancer liver metastases (lmCRC) first-line FOLFOX chemotherapy. Three hundred one lmCRC were manually segmented on both CT performed at baseline after first cycle FOLFOX, 107 radiomics features computed by subtracting textural from those timepoint 1 (TP1). LmCRC classified as nonresponders (R−) if they showed progression disease (PD), according RECIST1.1, before 8 months,...
Abstract Objective The purpose of our study was to test the applicability and implications using O-RADS system, which is developed validated on adults, review MRI ovarian masses among pediatric patients. Materials methods We retrospectively reviewed consecutive examinations from patients referred imaging for suspected lesions, assessing them framework. Malignancy frequencies classes were reviewed, we appraised potential such approach split into low (O-RADS 1, 2, 3) high risk 4 5)....
Abstract Background Radiomics is expected to improve the management of metastatic colorectal cancer (CRC). We aimed at evaluating impact liver lesion contouring as a source variability on radiomic features (RFs). Methods After Ethics Committee approval, 70 metastases in 17 CRC patients were segmented contrast-enhanced computed tomography scans by two residents and checked experienced radiologists. RFs from grey level co-occurrence run length matrices extracted three-dimensional (3D) regions...
Abstract The aim of our study was to develop and validate a machine learning algorithm predict response individual HER2‐amplified colorectal cancer liver metastases (lmCRC) undergoing dual HER2‐targeted therapy. Twenty‐four radiomics features were extracted after 3D manual segmentation 141 lmCRC on pretreatment portal CT scans cohort including 38 patients; feature selection then performed using genetic algorithms. classified as nonresponders (R−), if their largest diameter increased more...
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...
Depressed skull fractures occur when broken bones displace inward, meaning that a portion of the outer table fracture line lies below normal anatomical position inner table. They typically result from force trauma, is struck by an object with moderately large amount kinetic energy but small surface area, or impacts only area skull. In present case, depressed frontal bone was detected at autopsy 52-year-old man who, according to belated confession assailant, kicked in head. The assailant...
With the availability of low-cost head-mounted displays (HMDs), virtual reality environments (VREs) are increasingly being used in medicine for teaching and clinical purposes. Our aim was to develop an interactive, user-friendly VRE tridimensional visualization patient-specific organs, establishing a workflow transfer 3-dimensional (3D) models from imaging datasets our immersive VRE.This original model built using open-source software mobile HMD, Samsung Gear VR. For its validation, we...
Abstract Background To develop a pipeline for automatic extraction of quantitative metrics and radiomic features from lung computed tomography (CT) artificial intelligence (AI) models supporting differential diagnosis between coronavirus disease 2019 (COVID-19) other viral pneumonia (non-COVID-19). Methods Chest CT 1,031 patients (811 model building; 220 as independent validation set (IVS) with positive swab severe acute respiratory syndrome coronavirus-2 (647 COVID-19) or viruses (384...
Neuroendocrine neoplasms (NENs) are a diverse group of tumors with varying clinical behaviors. Their incidence has risen due to increased awareness, improved diagnostics, and aging populations. The 2019 World Health Organization classification emphasizes integrating radiology histopathology characterize NENs create personalized treatment plans. Imaging methods like CT, MRI, PET/CT crucial for detection, staging, planning, monitoring, but each them poses different interpretative challenges...
The aim of this multicentric study is an inter-center benchmarking, to assess how different set tools applied the same radiomics workflow affected features (RFs) values. This topic key importance start collaboration between centers and bring radiomic studies from benchmark bedside. A per-lesion analysis was performed on 56 metastases (mts) selected 14 patients. single radiologist segmentation all mts, RFs were extracted each using two software file formats. Potential sources discrepancies...
The definition of oligometastatic colorectal cancer (CRC) identifies a peculiar subpopulation patients characterized by limited metastatic spread disease.1 Oligometastatic disease is defined as the involvement up to two or occasionally three sites with five sometimes more metastases that for their anatomic localization amenable local ablative therapies, thus rendering patient free disease.1-3 Thus, this subgroup wide and has significant cohort CRC. Among CRC, those liver-limited represent...
Introduction: Endoscopic procedures are performed more frequently in children due to technological advances that can be safely an adequate setting with a support of multidisciplinary team. Pediatric indications for ERCP (endoscopic retrograde cholangiopancreatography) and EUS ultrasound) occur mainly congenital malformations. In pediatric case series, we report the application combined duodenoscopy, eventually associated minimally invasive surgery, highlighting importance defining tailored...
From 30 to 70% of patients with Crohn's disease (CD) may develop perianal fistulas during their lifetime. The medical and surgical management this complication is challenging, its treatment still gives unsatisfactory results. However, recent studies on adipose-derived mesenchymal stem cells have proven anti-inflammatory immuno-modulatory potential, representing a new promising tool in the such stubborn disease. We report our initial experience three who had recurrent CD treated local...
Pneumothorax (PTX) is a common clinical urgency, its diagnosis usually performed on chest radiography (CXR), and it presents setting where artificial intelligence (AI) methods could find terrain in aiding radiologists facing increasing workloads. Hence, the purpose of our study was to test an AI system for detection PTX CXR examinations, review diagnostic performance such alongside that reading radiologists.
To assess the impact of lung segmentation accuracy in an automatic pipeline for quantitative analysis CT images.Four different platforms based on convolutional neural network (CNN), region-growing technique and atlas-based algorithm were considered. The tested using images 55 COVID-19 patients with severe impairment. Four radiologists assessed segmentations a 5-point qualitative score (QS). For each series, manually revised reference (RS) was obtained. Histogram-based metrics (QM) calculated...
<ns4:p>This article was migrated. The not marked as recommended. IntroductionThe course of Anatomy in Vialba Medical School - University Milan, integrates systemic, topographic and development anatomy, dissection laboratory, peer-teaching, flipped classroom, clinical correlation to radiology surgery.MethodsAn anonymous questionnaire based on a five-point Likert scale submitted 162 students who had passed the exam Anatomy. Students evaluated importance given during study morphology, relations...
Due to the complexity of liver surgery, interest in 3D printing is constantly increasing among hepatobiliary surgeons. The aim this study was produce a patient-specific transparent life-sized model with tissue-like haptic properties by combining additive manufacturing and moulding. A multistep pipeline adopted obtain accurate printable models. Semiautomatic segmentation registration routine medical imaging using Slicer software allowed digital objects representing structures (liver...
Video assisted thoracoscopic surgery (VATS) has been adopted in pediatric age for the treatment of congenital lung malformations (CLM). The success VATS pediatrics largely depends on surgeon's skill ability to understand airways, vascular system and parenchyma anatomy CLM. In last years, virtual reality (VR) 3-dimensional (3D) printing organ models VR head mounted display (HMD) technologies have introduced completion preoperative planning adult patients. To date no reports about use HMD a...
The impact of spontaneous portosystemic shunts (SPSSs) on natural history cirrhotic patients was recently evaluated through the measurement total shunt area (TSA), a novel tool that allows comprehensive assessment SPSSs extension, identifying direct correlation higher TSA with lower patient survival. role in liver transplant (LT) is still debated: we sought to investigate clinical development early allograft dysfunction (EAD), acute kidney injury (AKI), postoperative complications, and graft...
Colorectal cancer (CRC) has the second-highest tumor incidence and is a leading cause of death by cancer. Nearly 20% patients with CRC will have metastases (mts) at time diagnosis, more than 50% develop during their disease. Unfortunately, only 45% after chemotherapy respond to treatment. The aim this study validate machine learning algorithm predict response individual liver mts, using CT scans. Understanding which mts or not help clinicians in providing efficient per-lesion treatment based...