A5006236000- Cardiac Imaging and Diagnostics
- Coronary Interventions and Diagnostics
- Cardiovascular Function and Risk Factors
- Cardiovascular Health and Disease Prevention
- Advanced MRI Techniques and Applications
- Cardiac Valve Diseases and Treatments
- Artificial Intelligence in Healthcare and Education
- ECG Monitoring and Analysis
- Lattice Boltzmann Simulation Studies
- Advanced Numerical Methods in Computational Mathematics
- Medical Image Segmentation Techniques
- Radiomics and Machine Learning in Medical Imaging
- Advanced X-ray and CT Imaging
- Congenital Heart Disease Studies
- Aortic Disease and Treatment Approaches
- Parallel Computing and Optimization Techniques
- Cardiac electrophysiology and arrhythmias
- Adversarial Robustness in Machine Learning
- Elasticity and Material Modeling
- Generative Adversarial Networks and Image Synthesis
- Cryptography and Data Security
- Privacy-Preserving Technologies in Data
- 3D Shape Modeling and Analysis
- Optical Coherence Tomography Applications
- Computational Fluid Dynamics and Aerodynamics
Transylvania University of Brașov
2015-2024
Siemens (Romania)
2015-2024
Airlangga University
2024
Clinical Emergency Hospital Bucharest
2023
Ovidius University
2023
Universitatea de Medicină, Farmacie, Științe și Tehnologie „George Emil Palade” din Târgu Mureș
2023
Siemens (Germany)
2012-2021
Siemens (United States)
2012-2019
Siemens Healthcare (United States)
2019
Onze Lieve Vrouwziekenhuis Hospital
2018
Fractional flow reserve (FFR) is a functional index quantifying the severity of coronary artery lesions and clinically obtained using an invasive, catheter-based measurement. Recently, physics-based models have shown great promise in being able to noninvasively estimate FFR from patient-specific anatomical information, e.g., computed tomography scans heart arteries. However, these high computational demand, limiting their clinical adoption. In this paper, we present machine-learning-based...
Purpose To compare two technical approaches for determination of coronary computed tomography (CT) angiography–derived fractional flow reserve (FFR)—FFR derived from CT angiography based on computational fluid dynamics (hereafter, FFRCFD) and FFR machine learning algorithm FFRML)—against quantitative (QCA). Materials Methods A total 85 patients (mean age, 62 years ± 11 [standard deviation]; 62% men) who had undergone followed by invasive were included in this single-center retrospective...
Abstract Background Artificial intelligence (AI) has the potential to transform our healthcare systems significantly. New AI technologies based on machine learning approaches should play a key role in clinical decision-making future. However, their implementation health care settings remains limited, mostly due lack of robust validation procedures. There is need develop reliable assessment frameworks for AI. We present here an approach assessing predicting treatment response triple-negative...
In recent years, powered by state-of-the-art achievements in a broad range of areas, machine learning has received considerable attention from the healthcare sector. Despite their ability to provide solutions within personalized medicine, strict regulations on confidentiality patient health information have many cases hindered adoption deep learning-based clinical workflows. To allow for processing sensitive without disclosing underlying data, we propose solution based fully homomorphic...
We introduce a patient-specific model for coronary circulation, by combining anatomical, hemodynamic and functional information from medical images other clinical observations. The main components of the coupled are: lumped heart model, reduced-order hemodynamics in arterial vessel tree (both healthy stenosed), physiological microvascular bed. anatomy is extracted Coronary Computed Tomography Angiography (CTA) images, followed an estimation impedance distal network. For blood flow...
We introduce a Computational Fluid Dynamics (CFD) based method for performing patient-specific coronary hemodynamic computations under two conditions: at rest and during drug-induced hyperemia. The proposed is on novel estimation procedure determining the boundary conditions from non-invasively acquired patient data rest. A multi-variable feedback control framework ensures that computed mean arterial pressure flow distribution matches estimated values an individual state. hyperemia are...
Data privacy is a major concern when accessing and processing sensitive medical data. A promising approach among privacy-preserving techniques homomorphic encryption (HE), which allows for computations to be performed on encrypted Currently, HE still faces practical limitations related high computational complexity, noise accumulation, sole applicability the at bit or small integer values level. We propose herein an encoding method that enables typical schemes operate real-valued numbers of...
Following the reports of breakthrough performances, machine learning based applications have become very popular in medical field. However, with recent increase concerns related to data privacy, and publication specific regulations (e.g. GDPR), development and, thus, exploitation deep clinical decision making processes, has been rendered impossible many cases. Herein, we describe evaluate an approach that employs Fully Homo-morphic Encryption for allowing computations be performed on...
Among all the sub-sections in a typical radiology report, Clinical Indications, Findings, and Impression often reflect important details about health status of patient. The information included is also covered Findings. While Findings can be deduced by inspecting image, Indications require additional context. cognitive task interpreting medical images remains most critical time-consuming step workflow. Instead generating an end-to-end this paper, we focus on from automated interpretation...
Abstract Computational fluid dynamics (CFD) can be used to analyze blood flow and predict hemodynamic outcomes after interventions for coarctation of the aorta other cardiovascular diseases. We report first use cardiac 3‐dimensional rotational angiography CFD show not only feasibility but also validation its computations with catheter‐based measurements in three patients.
Deep learning (DL)-based algorithms have demonstrated remarkable results in potentially improving the performance and efficiency of healthcare applications. Since data typically needs to leave facility for performing model training inference, e.g., a cloud based solution, privacy concerns been raised. As result, demand privacy-preserving techniques that enable DL inference on secured has significantly grown. We propose an image obfuscation algorithm combines variational autoencoder (VAE)...
Myocarditis, characterized by inflammation of the myocardial tissue, presents substantial risks to cardiovascular functionality, potentially precipitating critical outcomes including heart failure and arrhythmias. This investigation primarily aims identify optimal magnetic resonance imaging (CMRI) views for distinguishing between normal myocarditis cases, using deep learning (DL) methodologies. Analyzing CMRI data from a cohort 269 individuals, with 231 confirmed cases 38 as control...
We propose a numerical implementation based on Graphics Processing Unit (GPU) for the acceleration of execution time Lattice Boltzmann Method (LBM). The study focuses application LBM patient-specific blood flow computations, and hence, to obtain higher accuracy, double precision computations are employed. specific operations grouped into two kernels, whereas only one them uses information from neighboring nodes. Since regularly 1/5 or less nodes represent fluid nodes, an indirect addressing...
Purpose: Coarctation of the aorta (CoA) is a congenital heart disease characterized by an abnormal narrowing proximal descending aorta. Severity this pathology quantified blood pressure drop (△ P ) across stenotic coarctation lesion. In order to evaluate physiological significance preoperative and assess postoperative results, hemodynamic analysis routinely performed measuring △ site via invasive cardiac catheterization. The focus work present alternative, noninvasive measurement through...
Stencil based algorithms are used intensively in scientific computations. Graphics Processing Units (GPU) implementations of stencil computations speed-up the execution significantly compared to conventional CPU only systems. In this paper we focus on double precision computations, which required for meeting high accuracy requirements, inherent Starting from two baseline (using dimensional and three thread block structures respectively), employ different optimization techniques lead seven...
Abstract Although having been the subject of intense research over years, cardiac function quantification from MRI is still not a fully automatic process in clinical practice. This partly due to shortage training data covering all relevant cardiovascular disease phenotypes. We propose synthetically generate short axis CINE using generative adversarial model expand available sets that consist predominantly healthy subjects include more cases with reduced ejection fraction. introduce deep...