A5084093500- Radiomics and Machine Learning in Medical Imaging
- MRI in cancer diagnosis
- AI in cancer detection
- Hernia repair and management
- Digital Radiography and Breast Imaging
- Advanced MRI Techniques and Applications
- Advanced Neuroimaging Techniques and Applications
- Pelvic and Acetabular Injuries
- Medical Imaging Techniques and Applications
- Hepatocellular Carcinoma Treatment and Prognosis
- Abdominal Surgery and Complications
- Global Cancer Incidence and Screening
- Liver Disease Diagnosis and Treatment
- Artificial Intelligence in Healthcare and Education
- Pelvic floor disorders treatments
- Intestinal and Peritoneal Adhesions
- Cervical Cancer and HPV Research
- Body Contouring and Surgery
- Anatomy and Medical Technology
- Infrared Thermography in Medicine
- Colorectal Cancer Screening and Detection
- Hepatitis B Virus Studies
- Breast Lesions and Carcinomas
- Musculoskeletal pain and rehabilitation
- Appendicitis Diagnosis and Management
University Hospital of Zurich
2017-2025
University of Zurich
2018-2022
Weatherford College
2020
RWTH Aachen University
2014-2018
Universitätsklinikum Aachen
2014-2018
Committee on Publication Ethics
2015
Ministry of Economics
2015
High breast density is a risk factor for cancer. The aim of this study was to develop deep convolutional neural network (dCNN) the automatic classification based on mammographic appearance tissue according American College Radiology Breast Imaging Reporting and Data System (ACR BI-RADS) Atlas.In study, 20,578 mammography single views from 5221 different patients (58.3 ± 11.5 years) were downloaded picture archiving communications system our institution automatically sorted ACR (a-d) provided...
Abstract Purpose The aim of this study was to develop and test a post-processing technique for detection classification lesions according the BI-RADS atlas in automated breast ultrasound (ABUS) based on deep convolutional neural networks (dCNNs). Methods materials In retrospective study, 645 ABUS datasets from 113 patients were included; 55 had classified as high malignancy probability. Lesions categorized 2 (no suspicion malignancy), 3 (probability < 3%), 4/5 > 3%). A network trained...
Objectives Patients with hepatic metastases who are candidates for Y90-radioembolization (Y90-RE) usually have advanced tumor stages involvement of both liver lobes. Per current guidelines, these patients undergone several cycles potentially hepatotoxic systemic chemotherapy before Y90-RE is at all considered, requiring split (lobar) treatment sessions to reduce toxicity. Assessing response early, that is, already after the first lobar session, would be helpful avoid an ineffective and...
Marked enhancement of the fibroglandular tissue on contrast-enhanced breast magnetic resonance imaging (MRI) may affect lesion detection and classification is suggested to be associated with higher risk developing cancer. The background parenchymal (BPE) qualitatively classified according BI-RADS atlas into categories "minimal," "mild," "moderate," "marked." purpose this study was train a deep convolutional neural network (dCNN) for standardized automatic BPE categories.This IRB-approved...
Objectives Until today, there have been no conventional imaging methods available to visualize surgical mesh implants and related complications. In a new approach, we incorporated iron particles into polymer-based visualized them by magnetic resonance (MRI). After clinical approval of such implants, the purposes this study were evaluate MRI conspicuity iron-loaded in patients treated for inguinal hernias assess immediate postsurgical configuration. Materials Methods Approved ethics...
Shrinkage and deformation of mesh implants used for hernia treatment can be the cause long-term complications. The purpose this study was to quantify noninvasively time-dependent shrinkage, migration, configuration changes in patients who were surgically treated inguinal using magnetic resonance imaging (MRI)-visible implants.In an agarose phantom, meshes different shrinkage folding conditions validate quantification process. Seven (3 bilaterally) iron-loaded prospectively examined MRI....
Purpose The goal of this retrospective cohort study was to investigate the potential a deep convolutional neural network (dCNN) accurately classify microcalcifications in mammograms with aim obtaining standardized observer-independent microcalcification classification system based on Breast Imaging Reporting and Data System (BI-RADS) catalog. Materials Methods Over 56,000 images 268 from 94 patients were labeled 3 classes according BI-RADS standard: “no microcalcifications” (BI-RADS 1),...
The diffusion‐weighted (DW) MR signal sampled over a wide range of b ‐values potentially allows for tissue differentiation in terms cellularity, microstructure, perfusion, and T 2 relaxivity. This study aimed to implement machine learning algorithm automatic brain segmentation from DW‐MRI datasets, determine the optimal sub‐set features accurate segmentation. DWI was performed at 3 eight healthy volunteers using 15 20 diffusion‐encoding directions. pixel‐wise attenuation, as well trace...
The aim of this study was to systematically evaluate the accuracy quantitative intravoxel incoherent motion (IVIM) analysis upper abdomen applying simultaneous multislice (SMS) diffusion-weighted imaging (DWI) reduce acquisition time.Diffusion-weighted parenchymal abdominal organs performed in 8 healthy volunteers at 3 T using a standard DWI sequence (acceleration factor 1 [AF1]) and an SMS-accelerated echo planar with acceleration factors 2 (AF2/AF3). Intravoxel multistep algorithm for true...
Abstract Background Our aims were to determine if features derived from texture analysis (TA) can distinguish normal, benign, and malignant tissue on automated breast ultrasound (ABUS); evaluate whether machine learning (ML) applied TA categorise ABUS findings; compare ML the of single for lesion classification. Methods This ethically approved retrospective pilot study included 54 women with benign ( n = 38) 32) solid lesions who underwent ABUS. After manual region interest placement along...
To evaluate the feasibility of accelerated simultaneous multislice diffusion weighted sequences (SMS-DWI) for lymph node detection in abdominopelvic region. Sequences were evaluated regarding number and depiction nodes detected with SMS-DWI compared conventional sequences, most suitable SMS- acceleration factor, signal-to-noise ratio (SNR), overall acquisition time (TA). Eight healthy volunteers (4 men, 4 women; age range 21–39 years; median 25 years) examined pelvic region at 3T using a DWI...
Diffusion tensor imaging (DTI) adds functional information to morphological magnetic resonance neurography (MRN) in the assessment of brachial nerve plexus. To determine most appropriate pulse sequence scan times suited for diagnostic clinical routine, we compared image quality between simultaneous multi-slice readout-segmented (rs-DTI) and conventional single-shot (ss-DTI) echo-planar techniques.Institutional Review Board (IRB) approved study including 10 healthy volunteers. The...
Abstract Objectives Development of automated segmentation models enabling standardized volumetric quantification fibroglandular tissue (FGT) from native volumes and background parenchymal enhancement (BPE) subtraction dynamic contrast-enhanced breast MRI. Subsequent assessment the developed in context FGT BPE Breast Imaging Reporting Data System (BI-RADS)-compliant classification. Methods For training validation attention U-Net models, data coming a single 3.0-T scanner was used. testing,...
In DCE-MRI, the degree of contrast uptake in normal fibroglandular tissue, i.e., background parenchymal enhancement (BPE), is a crucial biomarker linked to breast cancer risk and treatment outcome. accordance with Breast Imaging Reporting & Data System (BI-RADS), it should be visually classified into four classes. The susceptibility such an assessment inter-reader variability highlights urgent need for standardized classification algorithm. this retrospective study, first post-contrast...
Abstract Purpose In vivo , a loss of mesh porosity triggers scar tissue formation and restricts functionality. The purpose this study was to evaluate the properties configuration changes as deformation shrinkage soft implant compared with conventional stiff in vitro porcine model. Material Methods Tensile tests digital image correlation were used determine textile for both types . A group three pigs each treated magnetic resonance imaging (MRI) visible polyvinylidene fluoride meshes (PVDF)...
The aim of this study was to investigate the potential a machine learning algorithm classify breast cancer solely by presence soft tissue opacities in mammograms, independent other morphological features, using deep convolutional neural network (dCNN). Soft were classified based on their radiological appearance ACR BI-RADS atlas. We included 1744 mammograms from 438 patients create 7242 icons manual labeling. sorted into three categories: "no opacities" (BI-RADS 1), "probably benign 2/3) and...
Abstract Background We investigated whether features derived from texture analysis (TA) can distinguish breast density (BD) in spiral photon-counting computed tomography (PC-BCT). Methods In this retrospective single-centre study, we analysed 10,000 images 400 PC-BCT examinations of 200 patients. Images were categorised into four-level scale ( a – d ) using Breast Imaging Reporting and Data System (BI-RADS)-like criteria. After manual definition representative regions interest, 19 (TFs)...
From a surgeon's point of view, meshes implanted for inguinal hernia repair should overlap the defect by 3 cm or more during implantation to avoid recurrence secondary mesh shrinkage. The use magnetic resonance imaging (MRI)-visible now offers opportunity noninvasively monitor whether is still covered sufficiently in living patient. purpose this study was therefore evaluate efficacy after based on MRI findings (mesh coverage, visibility structures) and patient's postoperative symptoms.In...
Abstract Background: Application of a mesh in presence pneumoperitoneum may cause deformation or wave formation when gas is released. Moreover, shrinkage during subsequent wound healing cannot be detected vivo without invasive diagnostics. Using MRI‐visible polyvinylidene fluoride (PVDF) mesh, the extend and could objectified by MRI for first time. Materials Methods: Laparoscopic intraperitoneal onlay (IPOM) implantation was performed 10 female rabbits using ferro‐oxide loaded PVDF meshes....
The aim of this study was to investigate the potential a machine learning algorithm accurately classify parenchymal density in spiral breast-CT (BCT), using deep convolutional neural network (dCNN). In retrospectively designed study, 634 examinations 317 patients were included. After image selection and preparation, 5589 images from different BCT sorted by four-level scale, ranging A D, ACR BI-RADS-like criteria. Subsequently four dCNN models (differences optimizer spatial resolution)...
Monitoring the tissue sodium content (TSC) in intervertebral disk geometry noninvasively by MRI is a sensitive measure to estimate changes proteoglycan of disk, which biomarker degenerative disease (DDD) and lumbar back pain (LBP). However, application quantitative concentration measurements 23 Na‐MRI highly challenging due lower vivo concentrations smaller gyromagnetic ratio, ultimately yielding much signal relative 1 H‐MRI. Moreover, imaging imposes higher demands, mainly because necessary...