A5082840545- Radiomics and Machine Learning in Medical Imaging
- MRI in cancer diagnosis
- Medical Imaging Techniques and Applications
- AI in cancer detection
- Advanced MRI Techniques and Applications
- Advanced NMR Techniques and Applications
- Ovarian cancer diagnosis and treatment
- Breast Lesions and Carcinomas
- Advanced Neuroimaging Techniques and Applications
- Fetal and Pediatric Neurological Disorders
- Digital Radiography and Breast Imaging
- Atomic and Subatomic Physics Research
- Ultrasound Imaging and Elastography
- Photoacoustic and Ultrasonic Imaging
- Advanced X-ray and CT Imaging
- Lanthanide and Transition Metal Complexes
- Medical Imaging and Analysis
- Glioma Diagnosis and Treatment
- CNS Lymphoma Diagnosis and Treatment
- Lymphoma Diagnosis and Treatment
- Breast Cancer Treatment Studies
- Cervical Cancer and HPV Research
- Cancer-related molecular mechanisms research
- Digital Imaging for Blood Diseases
- Optical Imaging and Spectroscopy Techniques
Danube Private University
2022-2025
Medical University of Vienna
2015-2025
University of Cambridge
2018-2025
Cancer Research UK Cambridge Center
2019-2025
Cambridge University Hospitals NHS Foundation Trust
2021-2025
Cancer Research UK
2019-2023
Cambridge School
2021-2022
Addenbrooke's Hospital
2021
Bridge University
2021
Vienna General Hospital
2010-2021
Our purpose is to investigate the feasibility of imaging tumor metabolism in breast cancer patients using 13 C magnetic resonance spectroscopic (MRSI) hyperpolarized label exchange between injected [1- C]pyruvate and endogenous lactate pool. Treatment-naïve were recruited: four triple-negative grade 3 cancers; two invasive ductal carcinomas that estrogen progesterone receptor-positive (ER/PR+) HER2/neu-negative (HER2−), one 2 3; ER/PR+ HER2− lobular carcinoma (ILC). Dynamic MRSI was...
Hyperpolarized 13C Magnetic Resonance Imaging (13C-MRI) provides a highly sensitive tool to probe tissue metabolism in vivo and has recently been translated into clinical studies. We report the cerebral of intravenously injected hyperpolarized [1–13C]pyruvate brain healthy human volunteers for first time. Dynamic acquisition images demonstrated 13C-labeling both lactate bicarbonate, catalyzed by cytosolic dehydrogenase mitochondrial pyruvate respectively. This demonstrates that enzymes can...
Abstract Objectives Multi-centre, multi-vendor validation of artificial intelligence (AI) software to detect clinically significant prostate cancer (PCa) using multiparametric magnetic resonance imaging (MRI) is lacking. We compared a new AI solution, validated on separate dataset from different UK hospitals, the original multidisciplinary team (MDT)-supported radiologist’s interpretations. Materials and methods A Conformité Européenne (CE)-marked deep-learning (DL) computer-aided detection...
To evaluate the prognostic relevance of temporal muscle thickness (TMT) in brain metastasis patients.We retrospectively analysed TMT on magnetic resonance (MR) images at diagnosis two independent cohorts 188 breast cancer (BC) and 247 non-small cell lung (NSCLC) patients (overall: 435 patients).Survival analysis using a Cox regression model showed reduced risk death by 19% with every additional millimetre baseline BC cohort 24% NSCLC cohort. Multivariate included diagnosis-specific graded...
Objectives The aim of this study was to assess the potential noncontrast magnetic resonance imaging (NC-MRI) with diffusion-weighted (DWI) in characterization breast lesions comparison dynamic contrast-enhanced MRI (DCE-MRI) at 3 T. Materials and Methods Consecutive patients conventional (mammography, ultrasound) BI-RADS 4/5 findings were included institutional review board–approved single-center study. All underwent T including readout-segmented DWI, DCE, T2-weighted sequences. Final...
This study aimed to assess the correlation of temporal muscle thickness (TMT), measured on routine cranial magnetic resonance (MR) images, with lumbar skeletal muscles obtained computed tomography (CT) images in brain metastasis patients establish a new parameter estimating mass MR images.We retrospectively analyzed cross-sectional area (CSA) at level third vertebra scans and correlated these values TMT two independent cohorts 93 lung cancer 61 melanoma (overall: 154 patients)...
Temporal muscle thickness (TMT) was investigated as a novel surrogate marker on MRI examinations of the brain, to detect patients who may be at risk for sarcopenia. TMT analyzed in retrospective, normal collective cohort (n = 624), establish standard reference values. These values were correlated with grip strength measurements and body mass index (BMI) 422 healthy volunteers validated prospective 130) various neurological disorders. Pearson correlation revealed strong association between...
Abstract High grade serous ovarian carcinoma (HGSOC) is a highly heterogeneous disease that typically presents at an advanced, metastatic state. The multi-scale complexity of HGSOC major obstacle to predicting response neoadjuvant chemotherapy (NACT) and understanding critical determinants response. Here we present framework predict the patients NACT integrating baseline clinical, blood-based, radiomic biomarkers extracted from all primary lesions. We use ensemble machine learning model...
Abstract In computational pathology, automatic nuclei instance segmentation plays an essential role in whole slide image analysis. While many computerized approaches have been proposed for this task, supervised deep learning (DL) methods shown superior performances compared to classical machine and processing techniques. However, these models need fully annotated datasets training which is challenging acquire, especially the medical domain. work, we release one of biggest manually...
Abstract Objectives To assess radiologists’ current use of, and opinions on, structured reporting (SR) in oncologic imaging, to provide recommendations for a report template. Materials methods An online survey with 28 questions was sent European Society of Oncologic Imaging (ESOI) members. The questionnaire had four main parts: (1) participant information, e.g., country, workplace, experience, SR use; (2) design, numbers sections fields, template (3) clinical impact SR, on quality length,...
The purpose of this study was to evaluate the prognostic relevance temporal muscle thickness (TMT) in melanoma patients with newly diagnosed brain metastases. TMT retrospectively assessed 146 metastases on cranial magnetic resonance images. Chart review used retrieve clinical parameters, including disease-specific graded assessment (DS-GPA) and survival times. Patients a > median showed statistically significant increase time (13 months) compared < (5 months; p 0.001; log rank test). A Cox...
To assess whether using the Tree flowchart obviates unnecessary magnetic resonance imaging (MRI)-guided biopsies in breast lesions only visible on MRI.This retrospective IRB-approved study evaluated consecutive suspicious (BI-RADS 4) MRI that were referred to our institution for MRI-guided biopsy. All according by experienced readers. The is a decision rule assigns levels of suspicion specific combinations diagnostic criteria. Receiver operating characteristic (ROC) curve analysis was used...
The aim of this study was to evaluate breast multiparametric ultrasound (mpUS) and its potential reduce unnecessary biopsies with 1, 2, or 3 additional quantitative parameters (Doppler, elastography, contrast-enhanced [CEUS]) B-mode investigate possible variations different reader experience.This prospective included 124 women (age range, 18-82 years; mean, 52 years), each 1 new lesion, scheduled for ultrasound-guided biopsy between October 2015 September 2016. Each lesion examined B-mode,...
To develop and validate a radiomic model, with features extracted from breast Dynamic Contrast-Enhanced Magnetic Resonance Imaging (DCE-MRI) 1.5T scanner, for predicting the malignancy of masses enhancement. Images were acquired using an 8-channel coil in axial plane. The rationale behind this study is to show feasibility radiomics-powered model that could be integrated into clinical practice by exploiting only standard-of-care DCE-MRI goal reducing required image pre-processing (ie,...
To assess whether a radiomics and machine learning (ML) model combining quantitative parameters features extracted from simultaneous multiparametric 18F-FDG PET/MRI can discriminate between benign malignant breast lesions.A population of 102 patients with 120 lesions (101 19 benign) detected on ultrasound and/or mammography was prospectively enrolled. All underwent hybrid for diagnostic purposes. Quantitative were DCE (MTT, VD, PF), DW (mean ADC contralateral parenchyma), PET (SUVmax,...
Differentiating aggressive clear cell renal carcinoma (ccRCC) from indolent lesions is challenging using conventional imaging. This work prospectively compared the metabolic imaging phenotype of tumors carbon-13 MRI following injection hyperpolarized [1-
Uncertainty quantification in automated image analysis is highly desired many applications. Typically, machine learning models classification or segmentation are only developed to provide binary answers; however, quantifying the uncertainty of can play a critical role for example active human interaction. especially difficult when using deep learning-based models, which state-of-the-art imaging The current approaches do not scale well high-dimensional real-world problems. Scalable solutions...
Activating signals generated by members of the tumour necrosis factor receptor superfamily upon interaction with their cognate ligands play important roles in T-cell responses. Members family namely 4-1BBL, OX40L, CD70, GITRL, LIGHT and CD30L have been described to function as costimulatory molecules binding such receptors on T cells. Using our recently system stimulator cells we performed first study where all these assessed compared regarding capacity costimulate proliferation cytokine...