About
63
Publications
6,483
Reads
How we measure 'reads'
A 'read' is counted each time someone views a publication summary (such as the title, abstract, and list of authors), clicks on a figure, or views or downloads the full-text. Learn more
1,088
Citations
Publications
Publications (63)
Radiomic datasets can be class-imbalanced, for instance, when the prevalence of diseases varies notably, meaning that the number of positive samples is much smaller than that of negative samples. In these cases, the majority class may dominate the model's training and thus negatively affect the model's predictive performance, leading to bias. There...
Class imbalance is often unavoidable for radiomic data collected from clinical routine. It can create problems during classifier training since the majority class could dominate the minority class. Consequently, resampling methods like oversampling or undersampling are applied to the data to class-balance the data. However, the resampling must not...
Abstract
Background
New machine learning methods and techniques are frequently introduced in radiomics, but they are often tested on a single dataset, which makes it challenging to assess their true benefit. Currently, there is a lack of a larger, publicly accessible dataset collection on which such assessments could be performed. In this study, a...
Radiomics aims to improve clinical decision making through the use of radiological imaging. How-ever, the field is challenged by reproducibility issues due to variability in imaging and subsequent statistical analysis, which particularly affects the interpretability of the model. In fact, radiomics extracts many highly correlated features that, com...
Objectives
In radiomics, different feature normalization methods, such as z-Score or Min–Max, are currently utilized, but their specific impact on the model is unclear. We aimed to measure their effect on the predictive performance and the feature selection.
Methods
We employed fifteen publicly available radiomics datasets to compare seven normali...
Purpose
We aimed to investigate the impact of post-thrombectomy isolated subarachnoid hemorrhage (i-SAH) and other types of intracranial hemorrhage (o-ICH) on patient’s neurological outcomes.
Methods
Stroke data from 2018 to 2022 in a tertiary care center were retrospectively analyzed. Patients with large vessel occlusion from ICA to M2 branch wer...
In this retrospective study, we aimed to assess the objective and subjective image quality of different reconstruction techniques and a deep learning-based software on non-contrast head computed tomography (CT) images. In total, 152 adult head CT scans (77 female, 75 male; mean age 69.4 ± 18.3 years) obtained from three different CT scanners using...
Background
Data on impact of COVID‐19 vaccination and outcomes of patients with COVID‐19 and acute ischemic stroke undergoing mechanical thrombectomy are scarce. Addressing this subject, we report our multicenter experience.
Methods and Results
This was a retrospective analysis of patients with COVID‐19 and known vaccination status treated with me...
Non-contrast computed tomography (CT) is commonly used for the evaluation of various pathologies including pulmonary infections or urolithiasis but, especially in low-dose protocols, image quality is reduced. To improve this, deep learning-based post-processing approaches are being developed. Therefore, we aimed to compare the objective and subject...
Purpose The aim of this study was to investigate the potential of multiparametric 18F-FDG PET/MR imaging as a platform for radiomics analysis and machine learning algorithms based on primary cervical cancers to predict N- and M-stage in patients.
Materials and Methods A total of 30 patients with histopathological confirmation of primary and untreat...
Purpose
To propose a new quality scoring tool, METhodological RadiomICs Score (METRICS), to assess and improve research quality of radiomics studies.
Methods
We conducted an online modified Delphi study with a group of international experts. It was performed in three consecutive stages: Stage#1, item preparation; Stage#2, panel discussion among Eu...
In this retrospective study, we aimed to predict the body height and weight of pediatric patients using CT localizers, which are overview scans performed before the acquisition of the CT. We trained three commonly used networks (EfficientNetV2-S, ResNet-18, and ResNet-34) on a cohort of 1009 and 1111 CT localizers of pediatric patients with recorde...
In radiomics, utilizing features extracted from pretrained deep networks could result in models with a higher predictive performance than those relying on hand-crafted features. This study compared the predictive performance of models trained with either deep features, hand-crafted features, or a combination of these features in terms of the area u...
Introduction
Subarachnoid hemorrhage is a common finding, ranging from 5.2% to 15.2% in ischemic stroke patients after mechanical thrombectomy.
Aim of Study
We aimed to evaluate neurological outcomes in patient groups without intracranial hemorrhage (non-ICH), with isolated subarachnoid hemorrhage (i-SAH) and with other types of intracranial hemor...
Objectives:
Cardiac computed tomography (CT) is essential in diagnosing coronary heart disease. However, a disadvantage is the associated radiation exposure to the patient which depends in part on the scan range. This study aimed to develop a deep neural network to optimize the delimitation of scan ranges in CT localizers to reduce the radiation d...
Background:
Application of radiomics proceeds by extracting and analysing imaging features based on generic morphological, textural, and statistical features defined by formulas. Recently, deep learning methods were applied. It is unclear whether deep models (DMs) can outperform generic models (GMs).
Methods:
We identified publications on PubMed...
Age assessment is regularly used in clinical routine by pediatric endocrinologists to determine the physical development or maturity of children and adolescents. Our study investigates whether age assessment can be performed using CT scout views from thoracic and abdominal CT scans using a deep neural network. Hence, we retrospectively collected 19...
Purpose:
We aimed to evaluate predictors of symptomatic intracranial hemorrhage (sICH) in acute ischemic stroke (AIS) patients following thrombectomy due to anterior large vessel occlusion (LVO).
Methods:
Data on stroke patients from January 2018 to December 2020 in a tertiary care centre were retrospectively analysed. sICH was defined as intrac...
Objectives
In radiomics, generic texture and morphological features are often used for modeling. Recently, features extracted from pretrained deep networks have been used as an alternative. However, extracting deep features involves several decisions, and it is unclear how these affect the resulting models. Therefore, in this study, we considered t...
Background
In radiomic studies, several models are often trained with different combinations of feature selection methods and classifiers. The features of the best model are usually considered relevant to the problem, and they represent potential biomarkers. Features selected from statistically similarly performing models are generally not studied....
In cirrhotic patients with hepatocellular carcinoma (HCC), right-sided radioembolization (RE) with Yttrium-90-loaded microspheres is an established palliative therapy and can be considered a “curative intention” treatment when aiming for sequential tumor resection. To become surgical candidate, hypertrophy of the left liver lobe to > 40% (future li...
Rationale: Limited treatment options in patients suffering from intrahepatic cholangiocarinoma (iCCA) demand the introduction of new, catheter-based treatment options. Especially 90Y radioembolization could expand therapeutic abilities beyond surgery or chemotherapy. Therefore, the purpose of this study was to identify factors associated with an im...
Background
Radiomics is a noninvasive method using machine learning to support personalised medicine. Preprocessing filters such as wavelet and Laplacian-of-Gaussian filters are commonly used being thought to increase predictive performance. However, the use of preprocessing filters increases the number of features by up to an order of magnitude an...
Objectives:
A critical problem in radiomic studies is the high dimensionality of the datasets, which stems from small sample sizes and many generic features extracted from the volume of interest. Therefore, feature selection methods are used, which aim to remove redundant as well as irrelevant features. Because there are many feature selection alg...
An important quality criterion for radiographs is the correct anatomical side marking. A deep neural network is evaluated to predict the correct anatomical side in radiographs of the knee acquired in anterior–posterior direction. In this retrospective study, a ResNet-34 network was trained on 2892 radiographs from 2540 patients to predict the anato...
Purpose
We aimed to investigate treatment effect of endovascular thrombectomy (EVT) on the change of National Institutes of Health Stroke Scale (NIHSS) scores in acute ischemic stroke (AIS) patients with anterior large vessel occlusion (LVO). Predictors of early neurological improvement (ENI) were assessed in those with successful reperfusion.
Met...
Objectives
Age estimation, especially in pediatric patients, is regularly used in different contexts ranging from forensic over medicolegal to clinical applications. A deep neural network has been developed to automatically estimate chronological age from knee radiographs in pediatric patients.
Methods
In this retrospective study, 3816 radiographs...
Background
Many studies in radiomics are using feature selection methods to identify the most predictive features. At the same time, they employ cross-validation to estimate the performance of the developed models. However, if the feature selection is performed before the cross-validation, data leakage can occur, and the results can be biased. To m...
Short tau inversion recovery (STIR) sequences are frequently used in magnetic resonance imaging (MRI) of the spine. However, STIR sequences require a significant amount of scanning time. The purpose of the present study was to generate virtual STIR (vSTIR) images from non-contrast, non-fat-suppressed T1- and T2-weighted images using a conditional g...
Objectives:
To improve organ protection with the frozen elephant trunk (FET) procedure, a so-called four-sites perfusion in combination with proximalization for the distal aortic anastomosis was performed. The impact of these techniques on patient outcome is reported.
Methods:
Between February 2005 and April 2020, a total of 357 patients underwe...
Background:
To evaluate the potential of simultaneously acquired 18F-FDG PET- and MR-derived quantitative imaging data sets of primary soft-tissue sarcomas for the prediction of neoadjuvant treatment response, the metastatic status and tumor grade.
Methods:
A total of 52 patients with a high-risk soft-tissue sarcoma underwent a 18F-FDG PET/MR ex...
For CT pulmonary angiograms, a scout view obtained in anterior–posterior projection is usually used for planning. For bolus tracking the radiographer manually locates a position in the CT scout view where the pulmonary trunk will be visible in an axial CT pre-scan. We automate the task of localizing the pulmonary trunk in CT scout views by deep lea...
Purpose:
To develop and evaluate fully automatic scan range delimitation for chest CT by using deep learning.
Materials and methods:
For this retrospective study, scan ranges were annotated by two expert radiologists in consensus in 1149 (mean age, 65 years ± 16 [standard deviation]; 595 male patients) chest CT topograms acquired between March 2...
Background:
To investigate and compare the diagnostic performance of 18F-Fluorodeoxyglucose (18F-FDG) PET/MR and MR alone in whole-body primary staging and restaging of patients with rectal cancer.
Methods:
A retrospective analysis was performed to evaluate diagnostic accuracies of combined reading of PET/MR and MR alone in T, N and M staging ag...
Background: To investigate the diagnostic performance of simultaneous 18F-fluoro-deoxyglucose ([18F]-FDG) PET/MR enterography in assessing and grading endoscopically active inflammation in patients with ulcerative colitis. Methods: 50 patients underwent PET/MR 24 h before ileocolonoscopy. Inflammatory activities of bowel segments were evaluated wit...
Purpose: To evaluate and compare the clinical utility of simultaneously obtained quantitative 18F-fluorodeoxyglucose positron-emission-tomography (18F-FDG PET) and diffusion-weighted imaging (DWI) datasets for the prediction of histopathological therapy response of soft tissue sarcomas (STS) under neoadjuvant isolated limb perfusion (ILP). Methods:...
Background
Recently, radiomics has emerged as a non-invasive, imaging-based tissue characterization method in multiple cancer types. One limitation for robust and reproducible analysis lies in the inter-reader variability of the tumor annotations, which can potentially cause differences in the extracted feature sets and results. In this study, the...
Objective
To compare the diagnostic performance of fecal biomarkers and ¹⁸ F-fludeoxyglucose ( ¹⁸ F-FDG) positron emmision tomography-MR (PET-MR) in the assessment of disease activity in patients with ulcerative colitis.
Methods
This study was conducted under the framework of a single-center clinical trial (clinicaltrials.gov [NCT03781284]). N = 5...
Objectives
The introduction of the 2016 WHO classification of CNS tumors has made the combined molecular and histopathological characterization of tumors a pivotal part of glioma patient management. Recent publications on radiogenomics-based prediction of the mutational status have demonstrated the predictive potential of imaging-based, non-invasiv...
Zielsetzung Ziel dieser Studie war die Evaluierung des prädiktiven Potenzials der Radiomics-Analyse zur Bestimmung des N- und M-Stadiums des primären Zervixkarzinoms anhand multiparametrischer 18F-FDG-PET/MRT-Bildgebung.
Material und Methoden 30 Patientinnen mit einem histologisch gesicherten, primären und therapienaiven Zervixkarzinom unterzogen s...
Purpose
To evaluate the diagnostic performance of PET-MR enterography in detecting histological active inflammation in patients with ulcerative colitis and the impact of bowel purgation on diagnostic accuracies of PET-MR parameters.
Methods
Fifty patients were enrolled in this randomized controlled trial (clinicaltrials.gov [NCT03781284]). Forty p...
Objectives
The aim of this study was to compare PET/MR enterography with ileocolonoscopy regarding patients' acceptance and their future preference.
Methods
Between October 2014 and February 2018 one-hundred-eleven patients underwent PET/MR enterography and ileocolonoscopy within 2 weeks. Overall acceptance of each modality was rated using a 10-po...
Purpose: To investigate differences between positron emission tomography/magnetic resonance imaging (PET/MRI) and PET/computed tomography (PET/CT) in lesion detection and classification in oncological whole-body examinations and to investigate radiation exposure differences between both modalities. Material and Methods: In this prospective, single-...
Radiomics beschäftigt sich mit der statistischen Analyse von radiologischen Bilddaten. Dieser Beitrag führt in Radiomics ein und zeigt einige ihrer Anwendungsbeispiele auf. Insbesondere wurde an einem Beispiel demonstriert, dass Pathologie und Radiologie in Zusammenarbeit zu besseren Diagnosen kommen können. Es ist nicht zu bestreiten, dass die kün...
Despite the great media attention for artificial intelligence (AI), for many health care professionals the term and the functioning of AI remain a "black box," leading to exaggerated expectations on the one hand and unfounded fears on the other. In this review, we provide a conceptual classification and a brief summary of the technical fundamentals...
Zusammenfassung
Radiomics ist eine Methode der medizinischen Bildanalyse, bei der quantitative Merkmale aus Bilddaten extrahiert und mittels Machine Learning zu prädiktiven Modellen weiterverarbeitet werden. Ziel dieser Arbeit ist es, die technischen Grundlagen von Radiomics und mögliche klinische Anwendungen unter besonderer Berücksichtigung nukle...
Our purpose was to assess the diagnostic potential of simultaneously acquired 18F-FDG PET and MRI data sets for therapy response assessment of isolated limb perfusion (ILP) in patients with soft-tissue sarcomas (STS). Methods: In total, 45 patients with histopathologically verified STS were prospectively enrolled for an integrated 18F-FDG PET/MRI e...
Objectives: We aimed to compare the in vitro flow dynamics of the Perimount Magna Ease™ (PME) and the Trifecta™ (TF) bioprostheses.
Material and methods: A new flow chamber was designed to compare the flow patterns of the PME (Edwards Lifesciences, Irvine, CA, USA) and the TF (SJM, St. Paul, MN, USA) aortic valve prostheses. This new channel offere...
Background
Detection of ossification areas of hand bones in X-ray images is an important task, e.g. as a preprocessing step in automated bone age estimation. Deep neural networks have emerged recently as de facto standard detection methods, but their drawback is the need of large annotated datasets. Finetuning pre-trained networks is a viable alter...
Rationale: To define an [18F]-FDG PET/MR enterography index as a hybrid surrogate marker for active ileocolonic inflammation in Crohn's disease (CD) and assess its diagnostic performance in comparison to validated MR indices (MaRIA, Clermont score). Methods: 52 CD patients with recurrent symptoms underwent ileocolonoscopy and [18F]-FDG PET/MR enter...
Background:
Transit-time flow measurement (TTFM) should be routinely used in CABG surgery to verify graft function. Most recently, a 2D high-frequency-ultrasound (HF-US) epi-cardiac imaging probe has been released (MiraQTM, Medistim, Oslo, Norway), which allows to evaluate the cannulation/clamping site of the aorta morphologically and to evaluate...
The aim of the present in vitro study was the evaluation of the fluid dynamical performance of the Carpentier-Edwards PERIMOUNT Magna Ease depending on the prosthetic size (21, 23, and 25 mm) and the cardiac output (3.6-6.4 L/min). A self-constructed flow channel in combination with particle image velocimetry (PIV) enabled precise results with high...
Kernelized support vector machines (SVMs) belong to the most widely used classification methods. However, in contrast to linear SVMs, the computation time required to train such a machine becomes a bottleneck when facing large data sets. In order to mitigate this shortcoming of kernel SVMs, many approximate training algorithms were developed. While...
Kernelized Support Vector Machines (SVMs) are among the best performing supervised learning methods. But for optimal predictive performance, time-consuming parameter tuning is crucial, which impedes application. To tackle this problem, the classic model selection procedure based on grid-search and cross-validation was refined, e.g. by data subsampl...
Obesity in adults and children is increasing worldwide at alarming rates. Obese children and adolescents are likely to become obese adults with increased risk of a number of comorbidities. In addition to preventing the development of obesity at young age, it is necessary to individualize the therapy of already obese children and adolescents in orde...
In der vorliegenden Arbeit verallgemeinern wir im Wesentlichen zwei Theoreme von Mackaay-Picken und Picken (2002, 2004). Im ihrem Artikel zeigen Mackaay und Picken,dass es eine bijektive Korrespodenz zwischen Deligne 2-Klassen $\xi \in \check{H}^2(M, \mathcal{D}^2)$ und Holonomie Abbildungen von der zweiten dünnen Homotopiegruppe $\pi_2^2(M)$ in di...