A5068880985- Radiomics and Machine Learning in Medical Imaging
- Hepatocellular Carcinoma Treatment and Prognosis
- Liver Disease Diagnosis and Treatment
- Liver Disease and Transplantation
- Advanced X-ray and CT Imaging
- Renal cell carcinoma treatment
- Radiation Dose and Imaging
- AI in cancer detection
- Breast Cancer Treatment Studies
- Musculoskeletal synovial abnormalities and treatments
- MRI in cancer diagnosis
- Metabolomics and Mass Spectrometry Studies
- Spectroscopy Techniques in Biomedical and Chemical Research
- COVID-19 diagnosis using AI
- Breast Lesions and Carcinomas
- Artificial Intelligence in Healthcare and Education
- Bone Tumor Diagnosis and Treatments
- Elasticity and Material Modeling
- Pancreatic and Hepatic Oncology Research
- Hepatitis C virus research
- Advanced MRI Techniques and Applications
- Cardiovascular Disease and Adiposity
- Medical Imaging and Pathology Studies
- Medical Imaging Techniques and Applications
- Sarcoma Diagnosis and Treatment
Semmelweis University
2020-2024
University Hospital Heidelberg
2024
Heidelberg University
2024
Weatherford College
2022
Abstract Background CT texture analysis (CTTA) has been successfully used to assess tissue heterogeneity in multiple diseases. The purpose of this work is demonstrate the value three-dimensional CTTA evaluation diffuse liver disease. We aimed develop based prediction models, which can be for staging fibrosis different anatomic segments irrespective variations scanning parameters. Methods retrospectively collected scans thirty-two chronic hepatitis patients with fibrosis. examinations were...
We aimed to assess the feasibility of ultrasound-based tissue attenuation imaging (TAI) and scatter distribution (TSI) for quantification liver steatosis in patients with nonalcoholic fatty disease (NAFLD). prospectively enrolled 101 participants suspected NAFLD. The TAI TSI measurements were performed a Samsung RS85 Prestige ultrasound system. Based on magnetic resonance proton density fat fraction (MRI-PDFF), divided into ≤5%, 5-10%, ≥10% MRI-PDFF groups. determined correlation between...
Background The nature of input data is an essential factor when training neural networks. Research concerning magnetic resonance imaging (MRI)-based diagnosis liver tumors using deep learning has been rapidly advancing. Still, evidence to support the utilization multi-dimensional and multi-parametric image lacking. Due higher information content, three-dimensional should presumably result in classification precision. Also, differentiation between focal lesions (FLLs) can only be plausible...
Background and Objectives: This study aims to evaluate artificial intelligence-calculated hepatorenal index (AI-HRI) as a diagnostic method for hepatic steatosis. Materials Methods: We prospectively enrolled 102 patients with clinically suspected non-alcoholic fatty liver disease (NAFLD). All had quantitative ultrasound (QUS), including AI-HRI, attenuation coefficient (AC,) backscatter-distribution (SC) measurements. The ultrasonographic indicator (US-FLI) score was also calculated. magnetic...
(1) Background: Open-source software tools are available to estimate proton density fat fraction (PDFF). (2) Methods: We compared four algorithms: complex-based with graph cut (GC), magnitude-based (MAG), magnitude-only estimation Rician noise modeling (MAG-R), and multi-scale quadratic pseudo-Boolean optimization (QPBO). The accuracy reliability of the methods were evaluated in phantoms known fat/water ratios a patient cohort various grades (S0-S3) steatosis. Image acquisitions performed at...
Liver tumors constitute a major part of the global disease burden, often making regular imaging follow-up necessary. Recently, deep learning (DL) has increasingly been applied in this research area. How these methods could facilitate report writing is still question, which our study aims to address by assessing multiple DL using Medical Open Network for Artificial Intelligence (MONAI) framework, may provide clinicians with preliminary information about given liver lesion. For purpose, we...
This study aimed to construct a radiomics-based machine learning (ML) model for differentiation between non-clear cell and clear renal carcinomas (ccRCC) that is robust against institutional imaging protocols scanners.Preoperative unenhanced (UN), corticomedullary (CM), excretory (EX) phase CT scans from 209 patients diagnosed with RCCs were retrospectively collected. After the three-dimensional segmentation, 107 radiomics features (RFs) extracted tumor volumes in each contrast phase. For ML...
Microvascular flow imaging (MVFI) is an advanced Doppler ultrasound technique designed to detect slow-velocity blood in small-caliber microvessels. This capable of realtime, highly detailed visualization tumor vessels without using a contrast agent. MVFI has been recently applied for the characterization focal liver lesions and revealed typical vascularity distributions multiple types thereof. Focal nodular hyperplasia (FNH) constitutes important differential diagnosis malignant tumors. In...
We aimed to develop a non-linear regression model that could predict the fat fraction of liver (USFF), similar magnetic resonance imaging proton density (MRI-PDFF), based on quantitative ultrasound (QUS) parameters. measured and retrospectively collected attenuation coefficient (AC), backscatter-distribution (BSC-D), stiffness (LS) using shear wave elastography (SWE) in 90 patients with clinically suspected non-alcoholic fatty disease (NAFLD) 51 metabolic-associated (MAFLD). The MRI-PDFF was...
We aimed to develop a non-linear regression model that could predict the fat fraction of liver (UEFF), similar magnetic resonance imaging proton density (MRI-PDFF), based on quantitative ultrasound (QUS) parameters. measured and retrospectively collected attenuation coefficient (AC), backscatter-distribution (BSC-D), stiffness (LS) using shear wave elastography (SWE) in 90 patients with clinically suspected non-alcoholic fatty disease (NAFLD), 51 metabolic-associated (MAFLD). The MRI-PDFF...
Abstract The area of Artificial Intelligence is developing at a high rate. In the medical field, an extreme amount data created every day. As images and reports are quantifiable, field radiology aspires to deliver better, more efficient clinical care. intelligence (AI) means simulation human by system or machine. It has been developed enable machines “think”, which be able learn, reason, predict, categorize, solve problems concerning amounts make decisions in effective manner than before....
Abstract During the coronavirus disease 2019 (COVID-19) pandemic, artificial intelligence (AI) based software on chest computed tomography (CT) imaging has proven to have a valuable role in accelerating diagnosis and screening. The proposed AI-based tools proved be rapid reproducible techniques guide patient management treatment protocols. Although no specific guidelines exist, CT-imaging clinical features are used for staging. To shed light of AI that been developed fighting COVID-19, this...
A komputertomográfia (CT) a hasnyálmirigy képalkotásában az egyik legszélesebb körben alkalmazott képalkotó diagnosztikai eljárás. klinikumban elterjedten használt hagyományos energiaintegráló detektoros CT-készülékek (EID-CT-k) detektorainak jól ismert korlátozó tényezője, hogy azok beérkező röntgenfotonokat két lépésben alakítják át elektronikus jellé. Ebből adódóan EID-CT-technológia számos klinikailag is jelentős limitációval bír, melyek leküzdése érdekében 2021-ben megjelent első,...
Abstract It has been proven in a few early studies that radiomic analysis offers promising opportunity to detect or differentiate between organ lesions based on their unique texture parameters. Recently, the utilization of CT (CTTA) receiving significant attention, especially for response evaluation and prognostication different oncological diagnoses. In this review article, we discuss ability radiomics its subfield CTTA diagnose pancreas kidney. We which was used classification histology...
Abstract Artificial Intelligence and the use of radiomics analysis have been great interest in last decade field imaging. CT texture (CTTA) is a new emerging radiomics, which seems promising assessment diagnosis both focal diffuse liver lesions. The utilization CTTA has only receiving attention recently, especially for response evaluation prognostication different oncological diagnoses. Radiomics, combined with machine learning techniques, offers opportunity to accurately detect or...
This study aimed to observe the effect of direct-acting antiviral (DAA) therapy on liver stiffness (LS) and serum biomarkers. We prospectively observed 35 patients with chronic hepatitis C infection attained a sustained virological response (SVR) after therapy. Shear wave elastography (SWE) measurement was performed at beginning DAA treatment 48 weeks end (EOT48w). The METAVIR score for varices needing (VNT) were determined based LS values; fibrosis-4 (FIB4) calculated from laboratory tests....