A5009406749- Osteoarthritis Treatment and Mechanisms
- Radiomics and Machine Learning in Medical Imaging
- Bone and Joint Diseases
- Medical Imaging and Analysis
- Hip disorders and treatments
- Knee injuries and reconstruction techniques
- Musculoskeletal synovial abnormalities and treatments
- Total Knee Arthroplasty Outcomes
- Lower Extremity Biomechanics and Pathologies
- Sarcoma Diagnosis and Treatment
- Advanced MRI Techniques and Applications
- Orthopedic Infections and Treatments
- Infectious Diseases and Tuberculosis
- Orthopaedic implants and arthroplasty
- Glioma Diagnosis and Treatment
- Advanced X-ray and CT Imaging
- Medical Imaging Techniques and Applications
- Cancer-related molecular mechanisms research
- Tumors and Oncological Cases
- Hematological disorders and diagnostics
- Cardiac Imaging and Diagnostics
- Artificial Intelligence in Healthcare and Education
- HIV-related health complications and treatments
- AI in cancer detection
- Spine and Intervertebral Disc Pathology
Klinikum rechts der Isar
2017-2025
Technical University of Munich
2016-2024
University of California, San Francisco
2018-2021
University of California System
2020-2021
Society of Interventional Radiology
2018
Background An artificial intelligence model that assesses primary bone tumors on radiographs may assist in the diagnostic workflow. Purpose To develop a multitask deep learning (DL) for simultaneous bounding box placement, segmentation, and classification of radiographs. Materials Methods This retrospective study analyzed acquired prior to treatment obtained from patient data January 2000 June 2020. Benign or malignant were diagnosed all patients by using histopathologic findings as...
Background A multitask deep learning model might be useful in large epidemiologic studies wherein detailed structural assessment of osteoarthritis still relies on expert radiologists' readings. The potential such a clinical routine should investigated. Purpose To develop for grading radiographic hip features radiographs and compare its performance to that attending-level radiologists. Materials Methods This retrospective study analyzed joints seen weight-bearing anterior-posterior pelvic...
To evaluate a compressed sensing artificial intelligence framework (CSAI) to accelerate MRI acquisition of the ankle.Thirty patients were scanned at 3T. Axial T2-w, coronal T1-w, and coronal/sagittal intermediate-w scans with fat saturation acquired using only (12:44 min, CS), CSAI an acceleration factor 4.6-5.3 (6:45 CSAI2x), 6.9-7.7 (4:46 CSAI3x). Moreover, high-resolution axial T2-w scan was obtained similar duration compared CS. Depiction presence abnormalities graded. Signal-to-noise...
Objective To identify joint structural risk factors, measured using quantitative compositional and semiquantitative magnetic resonance imaging (MRI) scoring, associated with the development of accelerated knee osteoarthritis (AKOA) compared a more normal rate (OA) development. Design From Osteoarthritis Initiative we selected knees no radiographic OA (Kellgren-Lawrence grade [KL] 0/1) that developed advanced-stage (KL 3/4; AKOA) within 4-year timeframe comparison group 0/1 to KL 2 in 4...
Background: In patients with soft-tissue sarcomas of the extremities, treatment decision is currently regularly based on tumor grading and size. The imaging-based analysis may pose an alternative way to stratify patients’ risk. this work, we compared value MRI-based radiomics expert-derived semantic imaging features for prediction overall survival (OS). Methods: Fat-saturated T2-weighted sequences (T2FS) contrast-enhanced T1-weighted fat-saturated (T1FSGd) were collected from two independent...
To develop and validate machine learning models to distinguish between benign malignant bone lesions compare the performance radiologists.In 880 patients (age 33.1 ± 19.4 years, 395 women) diagnosed with (n = 213, 24.2%) or 667, 75.8%) primary tumors, preoperative radiographs were obtained, diagnosis was established using histopathology. Data split 70%/15%/15% for training, validation, internal testing. Additionally, 96 from another institution obtained external Machine developed validated...
Background Differentiating between benign and malignant vertebral fractures poses diagnostic challenges. Purpose To investigate the reliability of CT-based deep learning models to differentiate fractures. Materials Methods CT scans acquired in patients with or from June 2005 December 2022 at two university hospitals were retrospectively identified based on a composite reference standard that included histopathologic radiologic information. An internal test set was randomly selected, an...
Abstract Background A deep learning (DL) model that automatically detects cardiac pathologies on MRI may help streamline the diagnostic workflow. To develop a DL to detect T1-mapping and late gadolinium phase sensitive inversion recovery (PSIR) sequences were used. Methods Subjects in this study either diagnosed with pathology ( n = 137) including acute chronic myocardial infarction, myocarditis, dilated cardiomyopathy, hypertrophic cardiomyopathy or classified as normal 63). Cardiac MR...
ObjectiveTo determine if presence of calcium-containing crystals (CaC) is associated with increased knee joint degeneration over 4 years and assess total number CaCs deposited a useful measure disease burden.DesignSeventy subjects in right knees at baseline were selected from the Osteoarthritis Initiative matched to 70 without evidence CaCs. T1-weighted gradient-echo sequences used confirm count numbers distinct circumscribed Morphological abnormalities assessed 4-year follow-up using...
The extent of medial meniscal extrusion (MME) that is associated with structural and symptomatic progression knee osteoarthritis has not been defined yet.
Though cognitive function is proven to be an independent predictor of survival in patients with intrinsic brain tumors, functions are still rarely considered. Aim this study was assess neurocognitive and identify risk factors for deficits. 103 primary neuroepithelial tumors who received tumor resections or biopsies were included prospective study. The following data acquired: mini-mental state examination, preoperative volume, WHO grade, entity location, the Karnofsky performance status...
The aim of this study was to develop and validate radiogenomic models predict the MDM2 gene amplification status differentiate between ALTs lipomas on preoperative MR images.MR images were obtained in 257 patients diagnosed with (n = 65) or 192) using histology analysis as a reference standard. protocols included T2-, T1-, fat-suppressed contrast-enhanced T1-weighted sequences. Additionally, 50 from different hospital for external testing. Radiomic features selected mRMR. Using repeated...
Metabolic disorders presenting in HIV-infected patients on antiretroviral therapy (ART) may increase the risk of osteoarthritis. However, structural changes knee HIV infected subjects are understudied. The aim this study is to investigate cartilage degeneration and over 8 years with without infection determined based use ART. We studied 10 participants from Osteoarthritis Initiative who received ART at baseline 20 controls ART, frequency matched for age, sex, race, body mass index (BMI)...
This study characterized the distribution of [18 F]-sodium fluoride (NaF) uptake and blood flow in femur acetabulum hip osteoarthritis (OA) patients to find associations between bone remodeling cartilage composition presence morphological abnormalities using simultaneous positron emission tomography magnetic resonance imaging (PET/MR), quantitative (MRI) shape modeling. Ten underwent a F]-NaF PET/MR dynamic scan simultaneously with: (i) fast spin-echo CUBE for morphology grading (ii) T1ρ /T2...
OBJECTIVE. The purpose of this study is to describe postoperative MRI findings after femoroacetabular impingement surgery in correlation with pain changes and surgical findings. SUBJECTS AND METHODS. We prospectively enrolled 42 patients (43 hips) who were scheduled for FAI surgery. Pre- MR images obtained using a 3-T system. Changes scores assessed the hip dysfunction osteoarthritis outcome score. evaluated presence acetabuloplasty or femoroplasty, chondral labral repair surgery, bone...
The assessment of fatty infiltration and edema in the musculature patients with neuromuscular diseases (NMDs) typically requires separate performance T1-weighted fat-suppressed T2-weighted sequences. Dixon turbo spin echo (TSE) enables generation fat- water-separated images, which can be used to assess both pathologies simultaneously. present study examines diagnostic TSE compared standard sequences 10 NMDs healthy subjects.Whole-body magnetic resonance imaging was performed including fast...
Abstract Purpose To assess the diagnostic performance of three-dimensional (3D) CT-based texture features (TFs) using a convolutional neural network (CNN)-based framework to differentiate benign (osteoporotic) and malignant vertebral fractures (VFs). Methods A total 409 patients who underwent routine thoracolumbar spine CT at two institutions were included. VFs categorized as or either biopsy imaging follow-up least three months standard reference. Automated detection, labelling,...
Cortical bone porosity is a major determinant of strength. Despite the biomechanical importance cortical porosity, biological drivers are unknown. The content pore space can indicate expansion mechanisms; both primary components space, vessels and adipocytes, have been implicated in expansion. Dynamic contrast-enhanced MRI (DCE-MRI) widely used vessel detection cardiovascular studies, but has not applied to visualize within bone. In this study, we developed multimodal DCE-MRI high resolution...
Objective To assess differences in biochemical composition of the deep cartilage layer subjects with type 2 diabetes mellitus (T2DM) and nondiabetic controls using UTE (ultra-short echo time) T2* mapping to investigate association vascular health measurements. Design Ten T2DM matched for age, sex, body mass index 10 controls. A 3D sequence 6 times was acquired 3T magnetic resonance imaging knee. For analysis, segmented analyzed 5 compartments (patella, medial, lateral femur tibia). The ankle...