A5043671740- Hepatocellular Carcinoma Treatment and Prognosis
- Radiomics and Machine Learning in Medical Imaging
- Prostate Cancer Diagnosis and Treatment
- Prostate Cancer Treatment and Research
- MRI in cancer diagnosis
- Urologic and reproductive health conditions
- Renal cell carcinoma treatment
- Cancer, Hypoxia, and Metabolism
- Liver Disease Diagnosis and Treatment
- AI in cancer detection
- Cardiac Valve Diseases and Treatments
- Advanced X-ray and CT Imaging
- Cardiac Imaging and Diagnostics
- Aortic Disease and Treatment Approaches
- Rabies epidemiology and control
- Medical Imaging and Pathology Studies
- Metabolomics and Mass Spectrometry Studies
- Machine Learning in Healthcare
- Artificial Intelligence in Healthcare and Education
- Geological and Geochemical Analysis
- Turtle Biology and Conservation
- Medical Imaging Techniques and Applications
- ATP Synthase and ATPases Research
- Artificial Intelligence in Healthcare
- Face recognition and analysis
Charité - Universitätsmedizin Berlin
2019-2025
Berlin Institute of Health at Charité - Universitätsmedizin Berlin
2022-2025
Humboldt-Universität zu Berlin
2019-2025
Freie Universität Berlin
2019-2025
Yale University
2018-2022
Universitätsmedizin Greifswald
2020-2021
Kerckhoff Klinik
2013
Background Clinically significant prostate cancer (PCa) diagnosis at MRI requires accurate and efficient radiologic interpretation. Although artificial intelligence may assist in this task, lack of transparency has limited clinical translation. Purpose To develop an explainable (XAI) model for clinically PCa biparametric using Prostate Imaging Reporting Data System (PI-RADS) features classification justification. Materials Methods This retrospective study included consecutive patients with...
Abstract Objectives To develop and test zone-specific prostate-specific antigen density (sPSAD) combined with PI-RADS to guide prostate biopsy decision strategies (BDS). Methods This retrospective study included consecutive patients, who underwent MRI (01/2012–10/2018). The whole gland transition zone (TZ) were segmented at using a retrained deep learning system (DLS; nnU-Net) calculate PSAD sPSAD, respectively. Additionally, sPSAD in BDS, diagnostic performances detect Grade Group ≥ 2 (GG...
To establish magnetic resonance (MR)-based molecular imaging paradigms for the noninvasive monitoring of extracellular pH (pHe) as a functional surrogate biomarker metabolic changes induced by locoregional therapy liver cancer.Thirty-two VX2 tumor-bearing New Zealand white rabbits underwent longitudinal on clinical 3T-MRI and CT scanners before up to 2 weeks after complete conventional transarterial chemoembolization (cTACE) using ethiodized oil (lipiodol) doxorubicin. MR-spectroscopic...
Abstract The purpose of this study is to compare diagnostic performance Prostate Imaging Reporting and Data System (PI-RADS) version (v) 2.1 2.0 for detection Gleason Score (GS) ≥ 7 prostate cancer on MRI. Three experienced radiologists provided PI-RADS v2.0 scores at least 12 months later v2.1 lesions in 333 MRI examinations acquired between 2012 2015. Diagnostic was assessed retrospectively by using MRI/transrectal ultrasound fusion biopsy 10-core systematic as the reference. From a total...
The magnetic resonance imaging (MRI) pathway for diagnosing clinically significant prostate cancer (csPCa; defined as International Society of Urological Pathology grade group ≥2) uses multiparametric MRI (mpMRI) biopsy (PB) decision-making. However, the intermediate impact on patient outcomes in men with negative results avoiding PB and positive without PCa remains unknown.
Facial recognition technology in medical imaging, particularly with head scans, poses privacy risks due to identifiable facial features. This study evaluates the use of software identifying features from CT scans and explores a defacing pipeline using TotalSegmentator reduce re-identification while preserving data integrity for research.
Background/Objectives: The aim of this study was to investigate the prognostic value established response assessment tools for hepatocellular carcinoma (HCC) treated with high-dose-rate interstitial brachytherapy (iBT) alone or transarterial chemoembolization (cTACE). Methods: (Non-)responders were categorized using size-based RECIST 1.1 and WHO criteria, enhancement-based mRECIST EASL LI-RADS Treatment Response Algorithm (LR-TRA). outcomes overall survival (OS), progression-free (PFS), time...
Magnetic resonance imaging (MRI) is used to detect the prostate index lesion before targeted biopsy. However, number of biopsy cores that should be obtained from unclear. The aim this study analyze how many MRI-targeted are needed establish most relevant histopathologic diagnosis and build a prediction model.We retrospectively included 451 patients who underwent 10-core systematic with sampling at least three lesion. A total 1587 were analyzed. core sequence was recorded, first detecting...
This study compared the efficacy and safety of conventional transarterial chemoembolization (cTACE) with drug-eluting beads (DEB)-TACE in patients unresectable hepatocellular carcinoma (HCC). retrospective analysis included 370 HCC treated cTACE (n = 248) or DEB-TACE 122) (January 2000–July 2014). Overall survival (OS) was assessed using uni- multivariate Cox proportional hazards models Kaplan-Meier analysis. Additionally, baseline imaging assessed, clinical laboratory toxicities were...
Abstract Traditional palaeontological techniques of disease characterisation are limited to the analysis osseous fossils, requiring several lines evidence support diagnoses. This study presents a novel stepwise concept for comprehensive diagnosis pathologies in fossils by computed tomography imaging morphological assessment combined with likelihood estimation based on systematic phylogenetic bracketing. approach was applied characterise left fibula and fused caudal vertebrae non-avian...
Abstract Dual-energy computed tomography (DECT) is an imaging technique that combines nondestructive morphological cross-sectional of objects and the quantification their chemical composition. However, its potential to assist investigations in paleontology has not yet been explored. This study investigates quantitative DECT for density- element-based material decomposition fossilized bones. Specifically, was developed validated imaging-based calcium fluorine bones five fossil vertebrates...
Our purpose was to identify baseline imaging features in patients with liver cancer that correlate <sup>90</sup>Y distribution on postprocedural SPECT and predict tumor response transarterial radioembolization (TARE). <b>Methods:</b> This retrospective study approved by the institutional review board included 38 hepatocellular carcinoma (HCC) (<i>n =</i> 23; 18/23 men; mean age, 62.39 ± 8.62 y; 34 dominant tumors) non-HCC hepatic malignancies 15; 9/15 61.13 11.51 24 who underwent 40...
Purpose: To identify disease-specific profiles comprising patient characteristics and imaging biomarkers on contrast-enhanced (CE)-computed tomography (CT) that enable the non-invasive prediction of hepatopulmonary shunt fraction (HPSF) in patients with hepatocellular carcinoma (HCC) before resin-based transarterial radioembolization (TARE). Patients Methods: This institutional review board-approved (EA2/071/19) retrospective study included 56 HCC recommended for TARE. All received...
To analyze possible differences in the inter-reader variability between PI-RADS version 2 (v2) and 2.1 (v2.1) for classification of prostate lesions using multiparametric MRI (mpMRI) prostate.In this retrospective randomized study, 239 annotated histopathologically correlated (104 positive 135 negative cancer) were rated twice by three experienced uroradiologists v2 v2.1 with an interval at least two months readings. Results tabulated across readers reading timepoints was determined Fleiss'...
Despite rapid advances in deep learning applications for radiological diagnosis and prognosis, the clinical adoption of such models is limited by their inability to explain or justify predictions. This work developed a probabilistic approach interpreting predictions convolutional neural network (CNN) trained classify liver lesions from multiphase magnetic resonance imaging (MRI). It determined presence 14 features, where each lesion image contained one four features only ten examples feature...
Given the extraordinary nature of tumor metabolism in hepatocellular carcinoma and its impact on oncologic treatment response, this study introduces a novel high‐throughput extracellular pH (pH e ) mapping platform using magnetic resonance spectroscopic imaging three‐dimensional (3D) vitro model liver cancer. was performed biosensor redundant deviation shifts (BIRDS) 9.4 T 11.7 MR scanners for validation purposes. 3D cultures four cancer (HepG2, Huh7, SNU475, VX2) one hepatocyte (THLE2) cell...
Histological microvascular invasion (MVI) is a risk factor for poor survival and early recurrence in hepatocellular carcinoma (HCC) after surgery. Its prognostic value the setting of locoregional therapies (LRT), where no tissue samples are obtained, remains unknown. This study aims to establish CT-derived indices indicative MVI on liver MRI with superior soft contrast evaluate their association patient ablation via interstitial brachytherapy (iBT) versus iBT combined prior conventional...