A5030064827- Advanced X-ray and CT Imaging
- Radiomics and Machine Learning in Medical Imaging
- Radiation Dose and Imaging
- Medical Imaging Techniques and Applications
- Advanced MRI Techniques and Applications
- Lung Cancer Diagnosis and Treatment
- Orthopedic Surgery and Rehabilitation
- Photoacoustic and Ultrasonic Imaging
- Shoulder Injury and Treatment
- Acute Ischemic Stroke Management
- Artificial Intelligence in Healthcare and Education
- Cardiac Imaging and Diagnostics
- Elbow and Forearm Trauma Treatment
- Venous Thromboembolism Diagnosis and Management
- Radiology practices and education
- Foot and Ankle Surgery
- Bone fractures and treatments
- Head and Neck Cancer Studies
- COVID-19 and healthcare impacts
- Congenital Anomalies and Fetal Surgery
- Dental Radiography and Imaging
- Shoulder and Clavicle Injuries
- Atomic and Subatomic Physics Research
- Immune cells in cancer
- CAR-T cell therapy research
University of Cologne
2019-2025
University Hospital Cologne
2017-2025
Centrum für Integrierte Onkologie
2023
Published under a CC BY 4.0 license.
Background Errors in radiology reports may occur because of resident-to-attending discrepancies, speech recognition inaccuracies, and large workload. Large language models, such as GPT-4 (ChatGPT; OpenAI), assist generating reports. Purpose To assess effectiveness identifying common errors reports, focusing on performance, time, cost-efficiency. Materials Methods In this retrospective study, 200 (radiography cross-sectional imaging [CT MRI]) were compiled between June 2023 December at one...
PurposeTo investigate the potential of combining Compressed Sensing (CS) and a newly developed AI-based super resolution reconstruction prototype consisting series convolutional neural networks (CNN) for complete five-minute 2D knee MRI protocol.MethodsIn this prospective study, 20 volunteers were examined using 3T-MRI-scanner (Ingenia Elition X, Philips). Similar to clinical practice, protocol consists fat-saturated 2D-proton-density-sequence in coronal, sagittal transversal orientation as...
Compressed sensing accelerates magnetic resonance imaging (MRI) acquisition by undersampling of the k-space. Yet, excessive impairs image quality when using conventional reconstruction techniques. Deep-learning-based methods might allow for stronger and thus faster MRI scans without loss crucial quality. We compared approaches parallel (SENSE), a combination compressed (COMPRESSED SENSE, CS), CS deep-learning-based (CS AI) on raw k-space data acquired at different factors. 3D T2-weighted...
Background The latest advancement of artificial intelligence (AI) is generative pretrained transformer large language models (LLMs). They have been trained on massive amounts text, enabling humanlike and semantical responses to text-based inputs requests. Foreshadowing numerous possible applications in various fields, the potential such tools for medical data integration clinical decision-making not yet clear. Objective In this study, we investigate LLMs report-based example acute ischemic...
To evaluate the feasibility of combining compressed sense (CS) with a newly developed deep learning-based algorithm (CS-AI) using convolutional neural networks to accelerate 2D MRI knee.In this prospective study, 20 healthy volunteers were scanned 3T scanner. All subjects received fat-saturated sagittal proton density reference sequence without acceleration and four additional acquisitions different levels: 2, 3, 4 6. sequences reconstructed conventional CS new CS-AI algorithm. Two...
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,...
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...
Positron emission tomography (PET) is currently considered the non-invasive reference standard for lymph node (N-)staging in lung cancer. However, not all patients can undergo this diagnostic procedure due to high costs, limited availability, and additional radiation exposure. The purpose of study was predict PET result from traditional contrast-enhanced computed (CT) test different feature extraction strategies.
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...
The aims of this study were to evaluate spectral detector CT (SDCT)-derived iodine concentration (IC) lymph nodes diagnosed as metastatic and benign in prostate-specific membrane antigen (PSMA) PET/CT assess its potential use for node assessment prostate cancer.Thirty-four cancer patients retrospectively included: 16 with 18 without metastases determined by PSMA PET/CT. Patients underwent well portal venous phase abdominal SDCT clinical follow-up. Only scan pairs a stable nodal status...
To investigate if iodine density overlay maps (IDO) and virtual monoenergetic images at 40 keV (VMI40keV) acquired from spectral detector computed tomography (SDCT) can improve detection of incidental skeletal muscle metastases in whole-body CT staging examinations compared to conventional images. In total, consecutive cancer patients who underwent clinically-indicated, contrast-enhanced, oncologic SDCT were included this retrospective study: 16 with n = 108 confirmed by prior or follow-up...
We aimed to determine optimal window settings for conventional polyenergetic (PolyE) and virtual monoenergetic images (MonoE) derived from abdominal portal venous phase computed tomography (CT) examinations on a novel dual-layer spectral-detector CT (SDCT).From 50 patients, SDCT data sets MonoE at 40 kiloelectron volt as well PolyE were reconstructed best individual width level values manually assessed separately evaluation of arteries liver lesions. Via regression analysis, optimized...
The radiologic evaluation of the sagittal angulation distal humerus is commonly based on standard lateral radiographs. However, radiographs do not allow to examine capitulum and trochlea, separately. Although this problem could be approached via computed tomography, there are no data available describing difference between trochlea. Therefore, we aimed assess angles trochlea in relation humeral shaft 400 CT-scans elbow healthy adults. Angles were measured planes at center three anatomically...
The assessment of lymph nodes in CT examinations cancer patients is essential for staging with direct impact on therapeutic decisions. Automated detection and segmentation challenging, especially, due to significant variability size, shape location coupled weak variable image contrast. In this paper, we propose a joint approach using fully convolutional neural network based 3D foveal patches. To enable training, 89 publicly available data sets were carefully re-annotated yielding an...
Purpose Due to the increasing number of COVID-19 infections since spring 2020 patient care workflow underwent changes in Germany. To minimize face-to-face exposure and reduce infection risk, non-time-critical elective medical procedures were postponed. Since ultrasound examinations include often can be substituted by other imaging modalities not requiring direct contact, has declined significantly. The aim this study is quantify baseline years before, during, early post-pandemic period...
To determine if anemia can be predicted on enhanced computed tomography (CT) examinations of the thorax using virtual non-contrast (VNC) images, in order to support clinicians especially diagnosing primary asymptomatic patients daily routine.In this monocentric study, 100 consecutive (50 with proven anemia), who underwent a contrast-enhanced CT examination due various indications were included. Attenuation was measured descending thoracic aorta, intraventricular septum, and left ventricle...
The aim of this study was to determine optimal window settings for conventional polyenergetic and virtual monoenergetic images derived from computed tomography pulmonary angiogram (CTPA) examinations a novel dual-layer spectral detector system (DLCT).Monoenergetic (40 keV) 50 CTPA were calculated the best individual width level (W/L) values manually assessed. Optimized obtained afterwards based on regression analysis. Diameters standardized artery segments subjective image quality parameters...