A5041779890- Medical Imaging Techniques and Applications
- Lung Cancer Diagnosis and Treatment
- Medical Imaging and Analysis
- Medical Image Segmentation Techniques
- Radiomics and Machine Learning in Medical Imaging
- Advanced Radiotherapy Techniques
- Image and Object Detection Techniques
- Dental Radiography and Imaging
- Advanced X-ray and CT Imaging
- Advanced Neural Network Applications
- Fetal and Pediatric Neurological Disorders
- Spinal Fractures and Fixation Techniques
- COVID-19 diagnosis using AI
- Advanced MRI Techniques and Applications
- Chronic Obstructive Pulmonary Disease (COPD) Research
- AI in cancer detection
- Domain Adaptation and Few-Shot Learning
- Lung Cancer Treatments and Mutations
- Radiation Dose and Imaging
- Retinal Imaging and Analysis
- Head and Neck Cancer Studies
- Prenatal Screening and Diagnostics
- Optical Coherence Tomography Applications
- Atomic and Subatomic Physics Research
- Non-Invasive Vital Sign Monitoring
Philips (Germany)
2015-2024
Philips (Finland)
2009-2015
Philips (United States)
2008-2012
IPS Research (United States)
2011
Philips (United Kingdom)
2011
Leibniz University Hannover
2008-2010
Institut für Informationsverarbeitung
2007-2010
A pulmonary ventilation imaging technique based on four-dimensional (4D) computed tomography (CT) has advantages over existing techniques. However, physiologically accurate 4D-CT not been achieved in patients. The purpose of this study was to evaluate by correlating with emphysema. Emphysematous lung regions are less ventilated and can be used as surrogates for low ventilation. We tested the hypothesis: emphysematous is significantly lower than non-emphysematous regions. Four-dimensional CT...
A novel pulmonary ventilation imaging technique based on four-dimensional (4D) CT has advantages over existing techniques and could be used for functional avoidance in radiotherapy. There are various deformable image registration (DIR) algorithms two classes of metric that can 4D-CT imaging, each yielding different images. The purpose this study was to quantify the variability DIR metrics.4D-CT images were created 12 patients using combinations algorithms, volumetric (DIR(vol)) surface-based...
Automatic detection of lung nodules from chest CT has been researched intensively over the last decades resulting also in several commercial products. However, solutions are adopted only slowly into daily clinical routine as many current CAD systems still potentially miss true while at same time generating too false positives (FP). While earlier approaches had to rely on rather few cases for development, larger databases become now available and can be used algorithmic development. In this...
Abstract Background In oncology, the correct determination of nodal metastatic disease is essential for patient management, as treatment and prognosis are closely linked to stage disease. The aim study was develop a tool automatic 3D detection segmentation lymph nodes (LNs) in computed tomography (CT) scans thorax using fully convolutional neural network based on foveal patches. Methods training dataset collected from Computed Tomography Lymph Nodes Collection Cancer Imaging Archive,...
Deep neural networks have emerged as the preferred method for semantic segmentation of CT images in recent years. However, understanding their limitations and generalization properties remains an active area research a relevant topic clinical applications. One crucial factor among many is X-ray radiation dose, which always kept low reasonably possible during acquisition. Therefore, potential dose reductions may pose challenge existing models. In this paper, we investigate robustness recently...
The concept of curvature and shape-based rendering is beneficial for medical visualization CT MRI image volumes. Color-coding local shape properties derived from the analysis Hessian can implicitly highlight tubular structures such as vessels airways, guide attention to potentially malignant nodular tumors, enlarged lymph nodes, or aneurysms. For some clinical applications, however, evaluation matrix does not yield satisfactory renderings, in particular hollow densely embedded low contrast...
Abstract Background In the management of cancer patients, determination TNM status is essential for treatment decision-making and therefore closely linked to clinical outcome survival. Here, we developed a tool automatic three-dimensional (3D) localization segmentation cervical lymph nodes (LNs) on contrast-enhanced computed tomography (CECT) examinations. Methods this IRB-approved retrospective single-center study, 187 CECT examinations head neck region from patients with various primary...
We have compared and validated image registration methods with respect to the clinically relevant use-case of lung CT max-inhale max-exhale registration. Four fundamentally different algorithms representing main approaches for were using clinical images. Each algorithm was assigned a person extensive working knowledge its usage. Quantitative qualitative evaluation is performed. Whereas achieve similar results in target error, characteristic differences come show by closer analysis...
Automatic instance segmentation of individual vertebrae from 3D CT is essential for various applications in orthopedics, neurology, and oncology. In case model-based (MBS) shall be used to generate a mesh-based representation the spine, good initialization MBS crucial avoid wrong vertebra labels due similar appearance adjacent vertebrae. Here, we propose use deep learning (DL) robustly guiding during 24 segmentations each every vertebra. We four-step approach: step 1, apply first...
Objective.In the context of primary in-hospital trauma management timely reading computed tomography (CT) images is critical. However, assessment spine time consuming, fractures can be very subtle, and potential for under-diagnosis or delayed diagnosis relevant. Artificial intelligence increasingly employed to assist radiologists with detection spinal prioritization cases. Currently, algorithms focusing on cervical are commercially available. A common approach vertebra-wise classification....
Respiration-induced organ motion can limit the accuracy required for many clinical applications working on thorax or upper abdomen. One approach to reduce uncertainty of location caused by respiration is use prior knowledge breathing motion. In this work, we deal with extraction and modeling lung fields based free-breathing 4D-CT data sets 36 patients. Since was acquired radiotherapy planning, images same patient were available over different weeks treatment. Motion field performed using an...
Ultrasound (US) is the modality of choice for fetal screening, which includes assessment a variety standardized growth measurements, like abdominal circumference (AC). Screening guidelines define criteria on scan plane, in measurement taken. As US increasingly becoming 3D modality, approaches automated determination optimal plane volumetric dataset would greatly improve workflow. In this work, novel framework deep hyperplane learning proposed and applied view estimation examinations. The...
Automatic segmentation of lung lobes from CT data is becoming clinically relevant as an enabler for, e.g., lobe-based quantitative analysis for diagnostics or more accurate interventional planning. The detection fissures thereby usually a first step in comprehensive framework. Although many approaches have been presented the past addressing fissure detection, there are still several limitations. In this paper, we review one most prominent algorithms which based on eigenvalue Hessian matrix...