A5089210413- Radiomics and Machine Learning in Medical Imaging
- Hepatocellular Carcinoma Treatment and Prognosis
- MRI in cancer diagnosis
- Brain Tumor Detection and Classification
- Prostate Cancer Diagnosis and Treatment
- Advanced X-ray and CT Imaging
- Liver Disease Diagnosis and Treatment
- Intracerebral and Subarachnoid Hemorrhage Research
- Urological Disorders and Treatments
- Acute Ischemic Stroke Management
- Lung Cancer Diagnosis and Treatment
- Cancer Immunotherapy and Biomarkers
- Medical Imaging Techniques and Applications
- Lung Cancer Research Studies
- Colorectal Cancer Screening and Detection
- Urologic and reproductive health conditions
- Migration, Racism, and Human Rights
- Renal cell carcinoma treatment
- Pancreatic and Hepatic Oncology Research
- Esophageal Cancer Research and Treatment
- Liver Disease and Transplantation
- AI in cancer detection
- Cancer, Stress, Anesthesia, and Immune Response
- Endoplasmic Reticulum Stress and Disease
- Cancer, Hypoxia, and Metabolism
Charité - Universitätsmedizin Berlin
2021-2025
Humboldt-Universität zu Berlin
2022-2025
Freie Universität Berlin
2022-2025
Yale University
2021-2025
Berlin Institute of Health at Charité - Universitätsmedizin Berlin
2024
Barmherzige Schwestern Krankenhaus Wien
2024
Abstract Objectives To develop and evaluate a deep convolutional neural network (DCNN) for automated liver segmentation, volumetry, radiomic feature extraction on contrast-enhanced portal venous phase magnetic resonance imaging (MRI). Materials methods This retrospective study included hepatocellular carcinoma patients from an institutional database with MRI. After manual the data was randomly split into independent training, validation, internal testing sets. From collaborating institution,...
To devise and validate radiomic signatures of impending hematoma expansion (HE) based on admission non-contrast head computed tomography (CT) patients with intracerebral hemorrhage (ICH).Utilizing a large multicentric clinical trial dataset hypertensive spontaneous supratentorial ICH, we developed predictive HE in discovery cohort (n = 449) confirmed their performance an independent validation 448). In addition to n 1,130 features, 6 variables associated HE, 8 previously defined visual...
Posttreatment recurrence is an unpredictable complication after liver transplant for hepatocellular carcinoma (HCC) that associated with poor survival. Biomarkers are needed to estimate risk before organ allocation.
Abstract Background and purpose Radiomics provides a framework for automated extraction of high‐dimensional feature sets from medical images. We aimed to determine radiomics signature correlates admission clinical severity medium‐term outcome intracerebral hemorrhage (ICH) lesions on baseline head computed tomography (CT). Methods used the ATACH‐2 (Antihypertensive Treatment Acute Cerebral Hemorrhage II) trial dataset. Patients included in this analysis ( n = 895) were randomly allocated...
Accurate segmentation of liver and tumor regions in medical imaging is crucial for the diagnosis, treatment, monitoring hepatocellular carcinoma (HCC) patients. However, manual time-consuming subject to inter- intra-rater variability. Therefore, automated methods are necessary but require rigorous validation high-quality segmentations based on a consensus raters. To address need reliable comprehensive data this domain, we present LiverHccSeg, dataset that provides multiphasic...
We aimed to investigate the effects of <sup>18</sup>F-FDG PET voxel intensity normalization on radiomic features oropharyngeal squamous cell carcinoma (OPSCC) and machine learning–generated biomarkers. <b>Methods:</b> extracted 1,037 quantifying shape, intensity, texture 430 OPSCC primary tumors. The reproducibility individual across 3 intensity-normalized images (body-weight SUV, reference tissue activity ratio lentiform nucleus brain cerebellum) raw data was assessed using an intraclass...
Abstract Background Accurate mortality risk quantification is crucial for the management of hepatocellular carcinoma (HCC); however, most scoring systems are subjective. Purpose To develop and independently validate a machine learning method HCC patients using standard-of-care clinical data liver radiomics on baseline magnetic resonance imaging (MRI). Methods This retrospective study included all with multiphasic contrast-enhanced MRI at time diagnosis treated our institution. Patients were...
Abstract Background Numerous studies have shown that magnetic resonance imaging (MRI)-targeted biopsy approaches are superior to traditional systematic transrectal ultrasound guided (TRUS-Bx). The optimal number of cores be obtained per lesion identified on multiparametric MRI (mpMRI) images, however, remains a matter debate. aim this study was evaluate the incremental value additional in an MRI-targeted “in-bore”-biopsy (MRI-Bx) setting. Patients and methods Two hundred forty-five patients,...
Purpose Accurate liver segmentation is key for volumetry assessment to guide treatment decisions. Moreover, it an important pre-processing step cancer detection algorithms. Liver can be especially challenging in patients with cancer-related tissue changes and shape deformation. The aim of this study was assess the ability state-of-the-art deep learning 3D algorithms generalize across all different Barcelona Clinic Cancer (BCLC) stages. Methods This retrospective study, included from...