A5074124682- Advanced MRI Techniques and Applications
- MRI in cancer diagnosis
- Medical Imaging Techniques and Applications
- Atomic and Subatomic Physics Research
- Radiomics and Machine Learning in Medical Imaging
- Advanced X-ray and CT Imaging
- Medical Image Segmentation Techniques
- Renal and Vascular Pathologies
- Advanced Neuroimaging Techniques and Applications
- Pediatric Urology and Nephrology Studies
- History and Developments in Astronomy
- Lanthanide and Transition Metal Complexes
- Congenital Diaphragmatic Hernia Studies
- Ultrasound and Hyperthermia Applications
- Ultrasound Imaging and Elastography
- AI in cancer detection
- Advanced NMR Techniques and Applications
- Protein Structure and Dynamics
- Cell Image Analysis Techniques
- Cardiac Imaging and Diagnostics
- Prostate Cancer Diagnosis and Treatment
- Brain Tumor Detection and Classification
- Acute Kidney Injury Research
- History and Theory of Mathematics
- Colorectal Cancer Screening and Detection
University Medical Centre Mannheim
2016-2025
University Hospital Heidelberg
2016-2025
Heidelberg University
2016-2025
Heidelberg University
2014-2024
Universitätsklinikum Gießen und Marburg
2024
University of Mannheim
2009-2023
Medizinische Fakultät Mannheim
2009-2021
Haukeland University Hospital
2015
University of Bergen
2007-2012
Delft University of Technology
2006
Abstract Automatic recognition of different tissue types in histological images is an essential part the digital pathology toolbox. Texture analysis commonly used to address this problem; mainly context estimating tumour/stroma ratio on samples. However, although typically contain more than two types, only few studies have addressed multi-class problem. For colorectal cancer, one most prevalent tumour there are fact no published results multiclass texture separation. In paper we present a...
To develop a generic support vector machine (SVM) model by using magnetic resonance (MR) imaging-based blood volume distribution data for preoperative glioma survival associations and to prospectively evaluate the diagnostic effectiveness of this in autonomous patient data.Institutional regional medical ethics committees approved study, all patients signed consent form. Two hundred thirty-five adult from two institutions with subsequent histologically confirmed diagnosis after surgery were...
PurposeWe aim to enhance deep learning-based computed tomography (CT) image reconstructions. Conventional loss functions such as mean squared error (MSE) yield blurry images, and alternative methods may introduce artifacts. To address these limitations, we propose Eagle-Loss, designed improve sharpness edge definition without increasing computational complexity. Eagle-Loss leverages spectral analysis of localized gradient variations visual quality quantification in CT...
Myocardial T
Early detection of the autosomal dominant polycystic kidney disease (ADPKD) is crucial as it one most common causes end-stage renal (ESRD) and failure. The total volume (TKV) can be used a biomarker to quantify progression. TKV calculation requires accurate delineation volumes, which usually performed manually by an expert physician. However, this time-consuming automated segmentation warranted. Furthermore, scarcity large annotated datasets hinders development deep learning solutions. In...
We investigated the predictive power of feature reduction analysis approaches in support vector machine (SVM)-based classification glioma grade. In 101 untreated patients, three analytic were evaluated to derive an optimal features; (i) Pearson's correlation coefficients (PCC), (ii) principal component (PCA) and (iii) independent (ICA). Tumor grading was performed using a previously reported SVM approach including whole-tumor cerebral blood volume (CBV) histograms patient age. Best accuracy...
Blood vessels in solid tumors are not randomly distributed, but clustered angiogenic hotspots. Tumor microvessel density (MVD) within these hotspots correlates with patient survival and is widely used both diagnostic routine clinical trials. Still, usually subjectively defined. There no unbiased, continuous explicit representation of tumor vessel distribution histological whole slide images. This shortcoming distorts angiogenesis measurements may account for ambiguous results the literature....
To establish arterial spin labelling (ASL) for quantitative renal perfusion measurements in a rat model at 3 Tesla and to test the diagnostic significance of ASL dynamic contrast-enhanced magnetic resonance imaging (DCE-MRI) acute kidney injury (AKI).ASL DCE-MRI were consecutively employed on six Lewis rats, five which had unilateral ischaemic AKI. All this study performed MR scanner using FAIR True-FISP approach TWIST sequence DCE-MRI, respectively. Perfusion maps calculated both methods...
Magnetic resonance imaging has achieved an increasingly important role in the clinical work-up of renal diseases such chronic kidney disease (CKD). A large panel parameters have been proposed to diagnose CKD among them total volume (TKV) which recently qualified as biomarker. Volume estimation MRI is based on image segmentation and/or its compartments. Beyond supports also quantification other MR perfusion or filtration. The aim present article discuss recent existing literature techniques...
Abstract Objectives Achieving a consensus on definition for different aspects of radiomics workflows to support their translation into clinical usage. Furthermore, assess the perspective experts important challenges successful workflow implementation. Materials and methods The was achieved by multi-stage process. Stage 1 comprised screening, retrospective analysis with semantic mapping terms found in 22 definitions, compilation an initial baseline definition. Stages 2 3 consisted Delphi...
Purpose To quantitatively evaluate lung perfusion using Fourier decomposition MRI. The (FD) method is a noninvasive for assessing ventilation‐ and perfusion‐related information in the lungs, where maps particular have shown promise clinical use. However, are nonquantitative dimensionless, making follow‐ups direct comparisons between patients difficult. We present an approach to obtain physically meaningful quantifiable FD method. Methods standard images quantified by comparing partially...
Introduction Multiple sclerosis (MS) is a chronic neurological disorder characterized by the progressive loss of myelin and axonal structures in central nervous system. Accurate detection monitoring MS-related changes brain are crucial for disease management treatment evaluation. We propose deep learning algorithm creating Voxel-Guided Morphometry (VGM) maps from longitudinal MRI volumes analyzing MS activity. Our approach focuses on developing generalizable model that can effectively be...