A5101414319- Remote Sensing and LiDAR Applications
- Medical Image Segmentation Techniques
- Medical Imaging Techniques and Applications
- Radiomics and Machine Learning in Medical Imaging
- Advanced X-ray and CT Imaging
- Forest ecology and management
- Forest Ecology and Biodiversity Studies
- AI in cancer detection
- Radiation Dose and Imaging
- Neonatal and Maternal Infections
- Advanced MRI Techniques and Applications
- Streptococcal Infections and Treatments
- Image Retrieval and Classification Techniques
- Lung Cancer Diagnosis and Treatment
- Sepsis Diagnosis and Treatment
- Image and Object Detection Techniques
- Kawasaki Disease and Coronary Complications
- Service-Oriented Architecture and Web Services
- Medical Imaging and Analysis
- 3D Surveying and Cultural Heritage
- Cardiac Fibrosis and Remodeling
- 3D Shape Modeling and Analysis
- Cardiovascular Function and Risk Factors
- Cerebrovascular and Carotid Artery Diseases
- Heart Failure Treatment and Management
Joanneum Research
2000-2022
Siemens Healthcare (Germany)
2014-2021
Innsbruck Medical University
2018
Siemens Healthcare (United States)
2015
Siemens (Germany)
2008-2014
Klinik für Frauenheilkunde
2013
Friedrich-Alexander-Universität Erlangen-Nürnberg
2006-2011
Universität Ulm
2011
Semmelweis University
2010
Medical Solutions
2008
<para xmlns:mml="http://www.w3.org/1998/Math/MathML" xmlns:xlink="http://www.w3.org/1999/xlink"> This paper presents a comparison study between 10 automatic and six interactive methods for liver segmentation from contrast-enhanced CT images. It is based on results the "MICCAI 2007 Grand Challenge" workshop, where 16 teams evaluated their algorithms common database. A collection of 20 clinical images with reference segmentations was provided to train tune in advance. Participants were also...
The aim of this study was to evaluate the accuracy a 3-dimensional (3D) camera algorithm for automatic and individualized patient positioning based on body surface detection compare results 3D with manual performed by technologists in routinely obtained chest abdomen computed tomography (CT) examinations.This included data 120 patients undergoing clinically indicated (n = 68) 52) CT. Fifty-two were scanned CT using table height manually selected technologists; 68 automatically positioned...
To delineate image data curation needs and describe a locally designed graphical user interface (GUI) to aid radiologists in annotation for artificial intelligence (AI) applications medical imaging.GUI components support analysis toolboxes, picture archiving communication system integration, third-party applications, processing of scripting languages, integration deep learning libraries. For clinical AI GUI included two-dimensional segmentation classification; three-dimensional...
Abstract Objective To assess the accuracy of a 3D camera for body contour detection in pediatric patient positioning CT compared with routine manual by radiographers. Methods and materials One hundred ninety-one patients, without fixation aid, which underwent head, thorax, and/or abdomen on scanner table height selection suggestion were retrospectively included. The ideal was defined as position at isocenter coincides patient’s isocenter. Table heights suggested selected radiographer height....
The automatic extraction and labeling of the rib centerlines is a useful yet challenging task in many clinical applications. In this paper, we propose new approach integrating seed point detection template matching to detect identify each chest CT scans. bottom-up learning based exploits local image cues top-down deformable imposes global shape constraints. To adapt deformation different cages whereas maintain high computational efficiency, employ Markov Random Field (MRF) articulated rigid...
Background Mutations in the LMNA gene are a common cause (6–8%) of dilated cardiomyopathy (DCM) leading to heart failure, growing health care problem worldwide. The premature aging disease Hutchinson-Gilford syndrome (HGPS) is also caused by defined mutations resulting activation cryptic splice donor site defective truncated prelamin A protein called progerin. Low levels progerin expressed healthy individuals associated with ageing. Here, we aimed address role cardiomyopathy. Methods and...
In this paper we present an efficient algorithm for the segmentation of inner and outer boundary thoratic abdominal aortic aneurysms (TAA & AAA) in computed tomography angiography (CTA) acquisitions. The aneurysm includes two steps: first, is segmented based on a grey level model with thresholds; then, adapted active contour approach applied to more complicated segmentation, its initialization available segmentation. An opacity image, which aims at enhancing important features while reducing...
Fluoroscopic overlay images rendered from preoperative volumetric data can provide additional anatomical details to guide physicians during catheter ablation procedures for treatment of atrial fibrillation (AFib). As these are often compromised by cardiac and respiratory motion, motion compensation methods needed keep the in sync with fluoroscopic images. So far, approaches have either required simultaneous biplane imaging 3-D compensation, or case monoplane X-ray imaging, provided only a...
The increasing availability of dense time series earth observation data has incited a growing interest in analysis for vegetation monitoring and change detection. Vegetation algorithms need to deal with several characteristics such as seasonality, irregular sampling intervals, signal artefacts. While common based on deterministic harmonic regression models account intra-annual inter-annual variations the seasonal pattern related shifts phenology due different temperature rainfall are usually...
In this study laser scanner canopy height metrics data from the Toposys-1 were investigated to derive forest attributes such as timber volume, tree height, and crown area coverage for use in inventories. Investigations based both on single information segmentation stand-wise assessments. while statistical approach only utilizes mean values stand areas, classification makes of full potential high resolution data. Forest inventory parameters classified base trees or small groups using digital...
Activation of the CXCL12/CXCR4/ACKR3 axis is known to aid myocardial repair through ischemia-triggered hypoxia-inducible factor-1α (HIF-1α). To enhance upregulation HIF-1α, we administered roxadustat, a novel prolyl hydroxylase inhibitor (PHI) clinically approved by European Medicines Agency 2021 for treatment renal anemia, with purpose improving LV function and attenuating ischemic cardiomyopathy.
Excessive neurohumoral activity remains a major burden to the circulation of patients with advanced heart failure. Prostaglandin El (PGE1), balanced i.v. vasodilator, was shown elicit favorable hemodynamic and clinical effects in this cohort. A prospective randomized parallel group trial performed evaluate acute, intermediate chronic changes hemodynamic, renal variables response PGE1, dobutamine placebo. Thirty class III IV failure low cardiac index (mean 1.9 l/min/m2) two hours after oral...
We present an algorithm for the segmentation of liver in 2-D computed tomography slice images. The basis our is implicit active shape model. In order to detect boundary and guide model deformation, a classifier has been integrated into framework novel manner. accuracy evaluated 20 test cases including both normal abnormal livers.
To assess the influence of breathing state on accuracy a 3D camera for body contour detection and patient positioning in thoracic CT.Patients who underwent CT thorax with both an inspiratory expiratory scan were prospectively included analysis differences ideal table height at different states. For subgroup, suggestion based images states was available to their accuracy. Ideal defined as which scanner isocenter coincides patient's isocenter.The mean (SD) difference between among 64 patients...
This paper focuses on an adaptive multi-resolutional algorithm for generating forest floor digital elevation models by processing the three dimensional data acquired laser scanner. The adaptivity of our ensures that it can be used successfully in flat, hilly, and mountainous terrain deliver accurate results. A large set GPS ground reference points are to verify along with others commonly used. First results show average error is between 0,5 1m Alpine region Austria which very close scanner...