A5031002175- Advanced X-ray and CT Imaging
- Radiation Dose and Imaging
- Radiomics and Machine Learning in Medical Imaging
- Lung Cancer Diagnosis and Treatment
- Medical Imaging Techniques and Applications
- Cardiac Imaging and Diagnostics
- Cardiac Valve Diseases and Treatments
- Pleural and Pulmonary Diseases
- MRI in cancer diagnosis
- Occupational and environmental lung diseases
- Medical Imaging and Pathology Studies
- Interstitial Lung Diseases and Idiopathic Pulmonary Fibrosis
- Aortic aneurysm repair treatments
- Systemic Sclerosis and Related Diseases
- Infective Endocarditis Diagnosis and Management
- Aortic Disease and Treatment Approaches
- Advanced MRI Techniques and Applications
- Lung Cancer Treatments and Mutations
- Digital Radiography and Breast Imaging
- Venous Thromboembolism Diagnosis and Management
- Pulmonary Hypertension Research and Treatments
- Ultrasound Imaging and Elastography
- COVID-19 diagnosis using AI
- Atomic and Subatomic Physics Research
- Radiology practices and education
University Hospital of Zurich
2016-2025
University of Zurich
2016-2025
Memorial Sloan Kettering Cancer Center
2024
Anna Needs Neuroblastoma Answers
2024
Weatherford College
2021-2023
University Hospital of Bern
2023
University Medical Center Groningen
2023
Society of Interventional Radiology
2013-2022
Dentsply Sirona (Sweden)
2021
St. Petersburg State Medical Academy "City Polyclinic №44"
2016
The aim of this study was to assess the diagnostic accuracy dual-source computed tomography (DSCT) for evaluation coronary artery disease (CAD) in a population with extensive calcifications without heart rate control. Thirty patients (24 male, 6 female, mean age 63.1+/-11.3 years) high pre-test probability CAD underwent DSCT angiography and invasive (ICA) within 14+/-9 days. No beta-blockers were administered prior scan. Two readers independently assessed image quality all segments diameter...
Objectives The aim of this study was to evaluate the diagnostic accuracy a multipurpose image analysis software based on deep learning with artificial neural networks for detection breast cancer in an independent, dual-center mammography data set. Materials and Methods In retrospective, Health Insurance Portability Accountability Act-compliant study, all patients undergoing 2012 at our institution were reviewed (n = 3228). All their prior follow-up mammographies from time span 7 years...
The purpose of this study was to evaluate the image quality and sensitivity ultralow radiation dose single-energy computed tomography (CT) with tin filtration for spectral shaping iterative reconstructions detection pulmonary nodules in a phantom setting.Single-energy CT performed using third-generation dual-source (SOMATOM Force; 2 × 192 slices) at 70 kVp, 100 kVp (100Sn kVp), 150Sn kV tube current-time product adjustments resulting standard (CT volume index, 3.1 mGy/effective dose, 1.3 mSv...
Objective Validated methods for the screening and early diagnosis of systemic sclerosis (SSc; scleroderma)–related interstitial lung disease (ILD) are needed. The aim this study was to evaluate performance pulmonary function tests (PFTs) compared with that high‐resolution computed tomography (HRCT) chest detection SSc‐related ILD in clinical practice, identify predictors involvement is functionally occult but significant on HRCT. Methods Prospectively enrolled patients SSc were assessed...
Background: Radiomics is a promising methodology for quantitative analysis and description of radiological images using advanced mathematics statistics. Tumor delineation, which still often done manually, an essential step in radiomics, however, inter-observer variability well-known uncertainty radiation oncology. This study investigated the impact (IOV) manual tumor delineation on reliability radiomic features (RF).Methods: Three different types (head neck squamous cell carcinoma (HNSCC),...
Abstract Objectives Incidentally detected pulmonary nodules present a challenge in clinical routine with demand for reliable support systems risk classification. We aimed to evaluate the performance of lung-cancer-prediction-convolutional-neural-network (LCP-CNN), deep learning-based approach, comparison multiparametric statistical methods (Brock model and Lung-RADS®) classification cohorts different profiles underlying diseases. Materials Retrospective analysis was conducted on non-contrast...
The widespread use of chest X-rays (CXRs), coupled with a shortage radiologists, has driven growing interest in automated CXR analysis and AI-assisted reporting. While existing vision-language models (VLMs) show promise specific tasks such as report generation or abnormality detection, they often lack support for interactive diagnostic capabilities. In this work we present RadVLM, compact, multitask conversational foundation model designed interpretation. To end, curate large-scale...
Purpose: To assess the diagnostic performance of dual-energy dual-source computed tomography (CT) in detection endoleaks after endovascular abdominal aortic aneurysm (AAA) repair. Materials and Methods: This study was local ethics board approved, written informed consent obtained from all patients. One hundred eighteen patients (21 women, 97 men; mean age, 74 years ± 8 [standard deviation]) underwent follow-up CT during nonenhanced, arterial, delayed phases AAA Delayed phase images were...
This study had institutional review board approval; written informed consent was obtained. The purpose to prospectively determine the heart rate (HR) dependency of three-dimensional (3D) coronary artery motion by incorporating into analysis durations systole and diastole. Thirty patients (seven women, 23 men; mean age, 56.6 years +/- 12.7 [standard deviation]; HR: 45-100 beats per minute) underwent electrocardiographically gated 64-section computed tomographic (CT) angiography velocities at...
To introduce a novel algorithm of automated attenuation-based tube potential selection and to assess its impact on image quality radiation dose body computed tomography angiography (CTA).In all, 40 patients (mean age 71±11.8 years, mass index (BMI) 25.7±3.8 kg/m², range 18.8-33.8 kg/m²) underwent 64-slice thoracoabdominal CTA (contrast material: 80 mL, 5 mL/s) using an (CAREkV), which optimizes tube-potential (70-140 kV) tube-current (138.8±18.6 effective mAs, 106-177 mAs) based the...
Purpose To evaluate prospectively the performance of noncalcium images reconstructed from dual-energy (DE) computed tomography (CT) for diagnosis bone marrow lesions in patients with acute ankle joint trauma comparison magnetic resonance (MR) images. Materials and Methods The study had local ethics board approval, written informed consent was obtained. Thirty consecutive (15 women; mean age, 34 years ± 11.8 [standard deviation]) underwent dual-source DE CT (80 kVp 140 tin filter) MR imaging...
The objective of this study was to prospectively compare the detection rate, location, and size pulmonary nodules in low-dose computed tomography (CT) magnetic resonance (MR) imaging with a 3-dimensional (3D) dual-echo gradient-echo (GRE) pulse sequence using trimodality positron emission (PET)/CT-MR setup.Forty consecutive patients (25 men 15 women; mean [SD] age 64 [12] years) referred for staging malignancy were included single-center, Institutional Review Board-approved study. Imaging...
Inspired by Curriculum Learning, we propose a consecutive (i.e., image-to-text-to-text) generation framework where divide the problem of radiology report into two steps. Contrary to generating full from image at once, model generates global concepts in first step and then reforms them finer coherent texts using transformer-based architecture. We follow sequence-to-sequence paradigm each step. improve upon state-of-the-art on benchmark datasets.
Background Radiomic features calculated from routine medical images show great potential for personalised medicine in cancer. Patients with systemic sclerosis (SSc), a rare, multiorgan autoimmune disorder, have similarly poor prognosis due to interstitial lung disease (ILD). Here, our objectives were explore computed tomography (CT)-based high-dimensional image analysis (“radiomics”) characterisation, risk stratification and relaying information on pathophysiology SSc-ILD. Methods We...
Objective The aim of this study was to evaluate the image quality (IQ) and performance an artificial intelligence (AI)-based computer-aided detection (CAD) system in photon-counting detector computed tomography (PCD-CT) for pulmonary nodule evaluation at different low-dose levels. Materials Methods An anthropomorphic chest-phantom containing 14 nodules sizes (range, 3–12 mm) imaged on a PCD-CT conventional energy-integrating CT (EID-CT). Scans were performed with each 3 vendor-specific...
The aim of this study was to characterize image quality and determine the optimal strength levels a novel iterative reconstruction algorithm (quantum reconstruction, QIR) for low-dose, ultra-high-resolution (UHR) photon-counting detector CT (PCD-CT) lung. Images were acquired on clinical dual-source PCD-CT in UHR mode reconstructed with sharp lung kernel at different QIR (QIR-1 QIR-4) without (QIR-off). Noise power spectrum (NPS) target transfer function (TTF) analyzed cylindrical phantom....
Abstract This document from the European Society of Thoracic Imaging (ESTI) and Radiology (ESR) discusses role imaging in long-term follow-up COVID-19 patients, to define which patients may benefit imaging, what modalities protocols should be used. Insights into features encountered on computed tomography (CT) scans potential pitfalls are discussed possible areas for future review research also included. Key Points • Post-COVID-19 pneumonia changes mainly consistent with prior organizing...
The aim of this study was to determine the potential photon-counting detector computed tomography (PCD-CT) for radiation dose reduction compared with conventional energy-integrated CT (EID-CT) in assessment interstitial lung disease (ILD) systemic sclerosis (SSc) patients.In retrospective study, SSc patients receiving a follow-up noncontrast chest examination on PCD-CT were included between May 2021 and December 2021. Baseline scans generated dual-source EID-CT by selecting tube current-time...
Objectives: To assess the value of dual-energy contrast-enhanced computed tomography (CT) imaging for detection urinary stone disease using dual-source CT. Materials and Methods: Forty consecutive patients (mean age 46.6 ± 16.2 years, range 27–85 years) suspected having underwent CT tract. A 3-phasic scan protocol consisting a standard unenhanced scan, nephrographic, an excretory phase contrast enhancement was performed. The nephrographic acquired in mode (80 kV/400 mA 140 kV/95 mA) allowing...