A5082545043- Radiomics and Machine Learning in Medical Imaging
- Cerebrovascular and Carotid Artery Diseases
- Colorectal Cancer Screening and Detection
- Acute Ischemic Stroke Management
- MRI in cancer diagnosis
- Colorectal Cancer Surgical Treatments
- Advanced MRI Techniques and Applications
- Pancreatic and Hepatic Oncology Research
- Vasculitis and related conditions
- Hepatocellular Carcinoma Treatment and Prognosis
- Advanced X-ray and CT Imaging
- Sarcoidosis and Beryllium Toxicity Research
- Cardiac Valve Diseases and Treatments
- Traumatic Brain Injury and Neurovascular Disturbances
- Medical Imaging Techniques and Applications
- Cardiac Imaging and Diagnostics
- IgG4-Related and Inflammatory Diseases
- Lymphoma Diagnosis and Treatment
- COVID-19 diagnosis using AI
- Colorectal and Anal Carcinomas
- Vascular Procedures and Complications
- COVID-19 Clinical Research Studies
- Infective Endocarditis Diagnosis and Management
- Cardiac tumors and thrombi
- Ultrasound in Clinical Applications
LMU Klinikum
2019-2025
Ludwig-Maximilians-Universität München
2016-2025
München Klinik
2020
Adenomatous colorectal polyps require endoscopic resection, as opposed to non-adenomatous hyperplastic polyps. This study aims evaluate the effect of artificial intelligence (AI)-assisted differentiation adenomatous and at CT colonography on radiologists' therapy management. Five board-certified radiologists evaluated images with all sizes morphologies retrospectively decided whether depicted required resection. After a primary unassisted reading based current guidelines, second access...
Background: Myocardial injury, defined by elevated troponin levels, is associated with adverse outcome in patients coronavirus disease 2019 (COVID-19). The frequency of cardiac injury remains highly uncertain and confounded current publications; myocarditis one several mechanisms that have been proposed. Methods: We prospectively assessed myocardial hospitalized for COVID-19 using transthoracic echocardiography, magnetic resonance imaging, endomyocardial biopsy. Results: Eighteen were...
Background CT colonography does not enable definite differentiation between benign and premalignant colorectal polyps. Purpose To perform machine learning–based of polyps detected with in an average-risk asymptomatic cancer screening sample external validation using radiomics. Materials Methods In this secondary analysis a prospective trial, all size categories morphologies were manually segmented on colonographic images classified as (hyperplastic polyp or regular mucosa) (adenoma)...
To investigate the differentiation of premalignant from benign colorectal polyps detected by CT colonography using deep learning.In this retrospective analysis an average risk cancer screening sample, all size categories and morphologies were manually segmented on supine prone images classified as (adenoma) or (hyperplastic polyp regular mucosa) according to histopathology. Two learning models SEG noSEG trained 3D image subvolumes predict class, model was additionally with segmentation...
Background and Purpose: Basilar artery occlusion is associated with high morbidity mortality. Optimal imaging treatment strategy are still controversial prognosis estimation challenging. We, therefore, aimed to determine the predictive value of computed tomography perfusion (CTP) parameters for functional outcome in patients basilar context endovascular treatment. Methods: Patients who underwent were selected from a prospectively acquired cohort. Ischemic changes assessed...
Large-bore arteriotomy for transcatheter aortic valve implantation (TAVI) requires percutaneous vascular closure devices, but real-world data comparing different strategies are limited.
The spleen is often involved in malignant lymphoma, which manifests on CT as either splenomegaly or focal, hypodense lymphoma lesions. This study aimed to investigate the diagnostic value of radiomics features classifying against non-lymphoma well determination subtypes case disease presence-in particular Hodgkin (HL), diffuse large B-cell (DLBCL), mantle-cell (MCL), and follicular (FL). Spleen segmentations 326 patients (139 female, median age 54.1 +/- 18.7 years) were generated 1317 per...
The goal of radiomics is to convert medical images into a minable data space by extraction quantitative imaging features for clinically relevant analyses, e.g. survival time prediction patient. One problem from computed tomography the impact technical variation such as reconstruction kernel within study. Additionally, what often neglected inter-patient variation, resulting patient characteristics, even when scan and parameters are constant. In our approach, measurements 3D...
Finding prognostic biomarkers with high accuracy in patients pancreatic cancer (PC) remains a challenging problem. To improve the prediction of survival and to investigate relevance quantitative imaging (QIB) we combined QIB established clinical parameters. In this retrospective study total 75 metastatic PC liver metastases were analyzed. Segmentations whole tumor burden (WLTB) from baseline contrast-enhanced CT images used derive QIBs. The benefits QIBs multivariable Cox models analyzed...
Background We aimed to investigate the clinical value of a 3D-T1w turbo-spin-echo (TSE) sequence and [18F]fluorodeoxyglucose positron emission tomography/computed tomography ([18F]FDG-PET/CT) for diagnosis active large vessel vasculitis (LVV) single-organ (SOV) aorta. Methods Twenty-four patients with suspected who underwent MRI PET/CT were retrospectively evaluated. was analyzed concentric contrast enhancement wall thickening, flow artifact intensity (4-point-scales). analysis comprised...
To evaluate the performance of 1.5 T true fast imaging with steady state precession (TrueFISP) magnetic resonance (MRI) sequences for detection and characterization pulmonary abnormalities caused by coronavirus disease 2019 (COVID-19).In this retrospective single-center study, computed tomography (CT) MRI scans 20 patients COVID-19 pneumonia were evaluated regard to distribution, opacity, appearance lesions, as well bronchial changes, pleural effusion, thoracic lymphadenopathy. McNemar's...
Background: Neurologic symptom severity and deterioration at 24 hours (h) predict long-term outcomes in patients with acute large vessel occlusion (LVO) stroke of the anterior circulation. We aimed to examine association baseline multiparametric CT imaging clinical factors course neurologic first h after endovascular treatment (EVT). Methods: Patients LVO circulation were selected from a prospectively acquired consecutive cohort who underwent CT, including non-contrast angiography perfusion...
Background and Purpose: Acute ischemic stroke of the anterior circulation due to large vessel occlusion (LVO) is a multifactorial process, which causes neurologic symptoms different degree. Our aim was examine impact neuromorphologic vascular correlates as well clinical factors on acute symptom severity in LVO stroke. Methods: We selected patients with known onset time from consecutive cohort underwent multiparametric CT including non-contrast CT, angiography perfusion (CTP) before...
Purpose/Objectives: Advancements in transcatheter mitral and tricuspid valve repair have resulted growing demands preprocedural computed tomography (CT) imaging. Due to the introduction of multidetector CT (MDCT), shorter acquisition times as well high rates heart failure arrhythmias this specific patient population, optimal synchronization between passage contrast agent data is mandatory. There no consensus on which technique should be used population. We aimed optimize our protocol...
Background/Aim: Intraarterial Technetium-99m-Macroaggregated Albumin (<sup>99m</sup>Tc-MAA) administration is an established method to predict particle distribution prior radioembolization. This study aimed analyse the impact of intraarterial <sup>99m</sup>Tc-MAA on changes in liver-specific laboratory parameters and assess whether such are associated with post-radioembolization hepatotoxicity. Patients Methods: A total 202 patients treated radioembolization received mapping angiography...
The degree of metastatic progress is a crucial factor in cancer assessment and often estimated from few target lesions. However, features the overall configuration metastases, such as spread distance liver, offer further predictive information. Graphs can represent both local characteristics individual lesions their global spatial distribution. In this work, liver metastases stemming primary pancreatic tumor are transformed patient-wise into lesion graphs processed by geometric deep learning...
Splenomegalie tritt häufig bei Patienten mit Lymphomen auf. In der klinischen Routine wird eine meist durch die Längenmessung Milz in kraniokaudalen Ebene bestimmt. dieser Studie sollte untersucht werden ob Form-spezifische Features zusätzliche diagnostische Informationen zur Detektion und Klassifikation von liefern.
Zielsetzung Differenzierung von benignen und prämalignen/malignen Kolonläsionen in CT-Kolonografien aus einer asymptomatischen Darmkrebs-Screening-Kohorte mit Hilfe eines Radiomics-Ansatzes.