A5080977311- Advanced MRI Techniques and Applications
- Advanced Neuroimaging Techniques and Applications
- MRI in cancer diagnosis
- Photoacoustic and Ultrasonic Imaging
- Advanced X-ray Imaging Techniques
- Lung Cancer Diagnosis and Treatment
- Medical Imaging Techniques and Applications
- Advanced X-ray and CT Imaging
- Radiomics and Machine Learning in Medical Imaging
- X-ray Spectroscopy and Fluorescence Analysis
- Cardiac Imaging and Diagnostics
- Aortic aneurysm repair treatments
- Sparse and Compressive Sensing Techniques
- Aortic Disease and Treatment Approaches
- Radiation Dose and Imaging
- Laser-Plasma Interactions and Diagnostics
- Chronic Obstructive Pulmonary Disease (COPD) Research
- Optical Coherence Tomography Applications
- Lung Cancer Treatments and Mutations
- Optical Imaging and Spectroscopy Techniques
- Acute Ischemic Stroke Management
- Advanced NMR Techniques and Applications
- Electron Spin Resonance Studies
- Coronary Artery Anomalies
- Venous Thromboembolism Diagnosis and Management
Siemens Healthcare (Germany)
2020-2025
Siemens Healthcare (United States)
2021-2025
Siemens (United States)
2021
gec-co Global Engineering & Consulting (Germany)
2011-2017
GE Global Research (United States)
2016
General Electric (United States)
2007-2014
This note summarizes the characterization of acoustic properties four materials intended for development tissue, and especially breast phantoms use in photoacoustic ultrasound imaging. The are agar, silicone, polyvinyl alcohol gel (PVA) polyacrylamide (PAA). acoustical properties, i.e., speed sound, impedance attenuation, determined by transmission measurements sound waves at room temperature under controlled conditions. Although tested application such as phantoms, we focus here on while...
Numerous scientific fields rely on elaborate but partly suboptimal data processing pipelines. An example is diffusion magnetic resonance imaging (diffusion MRI), a non-invasive microstructure assessment method with prominent application in neuroimaging. Advanced models providing accurate microstructural characterization so far have required long acquisition times and thus been inapplicable for children adults who are uncooperative, uncomfortable, or unwell. We show that the scan time...
Abstract We developed a novel method to accelerate diffusion spectrum imaging using compressed sensing. The can be applied either reduce acquisition time of without losing critical information or improve the resolution in space increasing scan time. Unlike parallel imaging, sensing reconstruct sub‐Nyquist sampled dataset domains other than spatial one. Simulations fiber crossings 2D and 3D were performed systematically evaluate effect reconstruction with different types undersampling...
Abstract Background Artificial intelligence (AI) in diagnostic radiology is undergoing rapid development. Its potential utility to improve performance for cardiopulmonary events widely recognized, but the accuracy and precision have yet be demonstrated context of current screening modalities. Here, we present findings on an AI convolutional neural network (CNN) prototype (AI-RAD Companion, Siemens Healthineers) that automatically detects pulmonary nodules quantifies coronary artery calcium...
Abstract Within the last decade hyperpolarized [1‐ 13 C] pyruvate chemical‐shift imaging has demonstrated impressive potential for metabolic MR a wide range of applications in oncology, cardiology, and neurology. In this work, highly efficient pulse sequence is described time‐resolved, multislice chemical shift injected substrate obtained downstream metabolites. Using spectral‐spatial excitation combination with single‐shot spiral data acquisition, overall encoding evenly distributed between...
Objectives: The objective of this study was to evaluate an artificial intelligence (AI)-based prototype algorithm for the fully automated per lobe segmentation and emphysema quantification (EQ) on chest-computed tomography as it compares Global Initiative Chronic Obstructive Lung Disease (GOLD) severity classification chronic obstructive pulmonary disease (COPD) patients. Methods: Patients (n=137) who underwent acquisition spirometry within 6 months were retrospectively included in...
Please see the Editorial Comment by Edwin F. Donnelly discussing this article.
Abstract Background The growing demand for follow-up imaging highlights the need tools supporting assessment of pulmonary nodules over time. We evaluated performance an artificial intelligence (AI)-based system automated nodule matching. Methods In this single-center study, patients with and ≤ 2 chest computed tomography (CT) examinations were retrospectively selected. An AI-based algorithm was used detection matching rate causes incorrect ten largest lesions (5–30 mm in diameter) registered...
Comparison of Artificial Intelligence–Based Fully Automatic Chest CT Emphysema Quantification to Pulmonary Function TestingAndreas M. Fischer1,2, Akos Varga-Szemes1, Marly van Assen1,3, L. Parkwood Griffith1, Pooyan Sahbaee4, Jonathan I. Sperl5, John W. Nance6 and U. Joseph Schoepf1Audio Available | Share Claim CREDIT
Objectives: The aim of the study is to investigate performance artificial intelligence (AI) convolutional neural networks (CNN) in detecting lung nodules on chest computed tomography patients with complex disease, and demonstrate its noninferiority when compared against an experienced radiologist through clinically relevant assessments. Methods: A CNN prototype was used retrospectively evaluate 103 disease cases 40 control without reported nodules. Computed scans were blindly evaluated by...
Purpose To compare the effectiveness of prospective, retrospective, and combined (prospective + retrospective) EPI distortion correction methods in bilateral breast diffusion‐weighted imaging (DWI) scans. Methods Five healthy female subjects underwent an axial DWI exam with without prospective B 0 inhomogeneity using slice‐by‐slice linear shimming. In each case, additional b=0 scan was performed polarity phase‐encoding gradient reversed, to generate estimated map; this map or a separately...
The fractal design of the bronchial tree, as described by Hess–Murray law, facilitates energy-efficient lung ventilation, yet its developmental origins remain unclear. Here, we quantify rearrangement embryonic tree into architecture, using SkelePlex, a new neural network-based image processing pipeline, and elucidate biophysical principles governing formation. We find that branch shapes are such pressure drop, shear, axial hoop stress equal across all branches. seemingly random diameter...
X-ray computed tomography is a powerful medical imaging device. It allows high-resolution 3-D visualization of the human body. However, one drawback health risk associated with ionizing radiation. Simply downscaling radiation intensities over entire scan results in increased quantum noise. This paper proposes concept computer-assisted protocol and reconstruction. More specifically, we propose method to compute patient task-specific intensity profiles that achieve an optimal tradeoff between...
Radiology reporting of emergency whole-body computed tomography (CT) scans is time-critical and therefore involves a significant risk pathology under-detection. We hypothesize relevant number initially missed secondary thoracic findings that would have been detected by an artificial intelligence (AI) software platform including several pathology-specific AI algorithms.This retrospective proof-of-concept-study consecutively included 105 shock-room CT scans. Image data was analyzed...
Phase retrieval in differential X-ray phase contrast imaging involves a one dimensional integration step. In the presence of noise, standard methods result image blurring and streak artifacts. This work proposes regularized method which takes availability two data as well integration-specific frequency-dependent noise amplification into account. more detail, Fourier-domain algorithm is developed comprising minimization total variation orthogonal to direction integration. For both simulated...
Purpose: The purpose of this study was to validate the accuracy an artificial intelligence (AI) prototype application in determining bone mineral density (BMD) from chest computed tomography (CT), as compared with dual-energy x-ray absorptiometry (DEXA). Materials and Methods: In Institutional Review Board–approved study, we analyzed data 65 patients (57 female, mean age: 67.4 y) who underwent both DEXA CT (mean time between scans: 1.31 y). From studies, T -scores for L1-L4 (lumbar vertebrae...
Manually performed diameter measurements on ECG-gated CT-angiography (CTA) represent the gold standard for diagnosis of thoracic aortic dilatation. However, they are time-consuming and show high inter-reader variability. Therefore, we aimed to evaluate accuracy a deep learning-(DL)-algorithm in comparison those radiologists evaluated measurement times (MT).We retrospectively analyzed 405 CTA exams 371 consecutive patients with suspected dilatation between May 2010 June 2019. The DL-algorithm...
Hyperpolarized 13 C imaging allows real-time in vivo measurements of metabolite levels. Quantification conversion between [1- C]pyruvate and downstream metabolites C]alanine, C]lactate, [ C]bicarbonate can be achieved through kinetic modeling. Since pyruvate interacts dynamically simultaneously with its metabolites, the purpose this work is determination parameter values a multisite, dynamic model involving possible biochemical pathways present MR spectroscopy. Kinetic modeling parameters...
Purpose Diffusion MRI often suffers from low signal‐to‐noise ratio, especially for high b‐values. This work proposes a model‐based denoising technique to address this limitation. Methods A generalization of the multi‐shell spherical deconvolution model using Richardson‐Lucy algorithm is applied noisy data. The reconstructed coefficients are then used in forward compute denoised diffusion‐weighted images (DWIs). proposed method operates diffusion space and thus complementary image‐based...
Differential phase-contrast X-ray imaging using a Talbot-Lau interferometer has recently shown promising results for applications in medical imaging. However, reducing the applied radiation dose remains major challenge. In this study, we consider realization of high Talbot order to increase signal-to-noise ratio low-dose applications. The quantitative performance π and π/2 systems at orders is analyzed through simulations, design energy spectrum are optimized mammography. It found that...
Many scientific research areas rely on accurate electron density characterization of various materials. For instance in X-ray optics and radiation therapy, there is a need for fast reliable technique to quantitatively characterize samples density. We present how precise measurement can be performed using an phase-contrast grating interferometer radiographic mode homogenous sample controlled geometry. A batch plastic materials was characterized compared with calculated results. found that the...
X-ray grating interferometry requires gratings with periods in the micrometer range and allows acquisition of dark-field contrast. The analyzer is designed to match period interference pattern order translate it into a measurable intensity modulation. In this study, we explore influence sample-induced mismatch between on We propose formula for calculation signal due present estimations varying detector pixel size. Furthermore, numerical simulations wave-front demonstrate that curvature,...