Contacts
Intranet
SK
National projects
| MRCartilage – Automatic data evaluation tool from the longitudinal quantitative MRI studies of articular cartilage | |
| Automatický softvérový nástroj na výhodnocovanie kvantitatívnych MRI štúdií artikulárných chrupaviek v čase | |
| Program: | APVV |
| Duration: | 1.7.2022 – 30.6.2026 |
| Project leader: | Ing. Dr. Szomolányi Pavol, (PhD.) |
| Annotation: | The aim of the project is to design a comprehensive tool for automatic evaluation of human articular cartilage data from quantitative MRI. Data obtained from the Osteoarthritis Initiative database, and measured at Institute of Measurement Science and Medical University of Vienna will be segmented using an automated segmentation tool based on convolutional neural networks. The annotated data will then be registered on quantitative MRI data that will be available from the database (T2 and T1rho mapping, gagCEST, sodium MR) using automated or semiautomated tools developed within this project. The data obtained will be evaluated at multiple time points according to MR measurements that will be available. In addition to quantitative MR data, this will include volumetric data, cartilage thickness, and texture analysis of quantitative maps. Patient evaluation will be based on risk factor groups (transverse ligament rupture, meniscus rupture and menisectomy). The expected number of patients is approximately 4000 divided into individual groups in the ratio 40/30/30. The output of the project will be a compiled version of an automatic cartilage evaluation tool that will be available in a public source (such as website of Institute of Measurement). |
| FERINO – Advanced diagnostics of neurodegenerative disorders using magnetic resonance techniques and artificial intelligence | |
| Pokročilá diagnostika neurodegeneratívnych ochorení pomocou techník magnetickej rezonancie a umelej inteligencie | |
| Program: | APVV |
| Duration: | 1.7.2023 – 30.6.2027 |
| Project leader: | Ing. Gogola Daniel, PhD. |
| Annotation: | Neurodegenerative diseases (ND) are becoming a severe problem in developed countries. Since we currently haveno effective therapies available, early diagnosis is critical to ensure a good quality of life for ND patients. ND arecharacterized by iron accumulation and magnetite mineralization in brain tissue, with ferritin as a precursor. Due toits low relaxivity, physiological ferritin is at the edge of visibility using magnetic resonance imaging (MRI)techniques. On the contrary, "pathological" ferritin causes a significant shortening of MRI relaxation times. Thiscreates hypointense artifacts, which theoretically allow the distinguishability of both proteins. Since ironaccumulation precedes the clinical symptoms of the disease, MRI has the potential to become a non -invasivediagnostic method for the early stages of ND. At present, however, this is limited by the insufficient characterizationof the relaxation properties of biogenic iron and the uncertainty in the interpretation of clinical data. Therefore, ourbasic goal (application output) is the development of a comprehensive methodology (FERINO software tool) for theunequivocal diagnosis of the early stages of ND. To reach our goal, we will use a combination of several diagnostictechniques and artificial intelligence tools. The diagnostic techniques include in-vitro, in-silico, and in-vivocharacteristics of ferritin relaxation, structural MRI, magnetic resonance spectroscopy (MRS), neurological tests,and clinical biochemistry biomarkers. The cornerstone of the methodology will be the FerroQuant software tool,which was proposed by the principal investigator within the APVV 2012. It enables the analysis and quantificationof iron-related clinical MRI data but lacks new findings in iron MRI (false-positive artifacts, ferritin\’s mineral phases).FerroQuant also does not use artificial intelligence and does not combine different diagnostic data, whic h, however,will be an integral part of the FERINO tool. |
| QuantMR – Optimization and Standardization of Quantitative Magnetic Resonance Imaging Methods. Suppression of Metallic Artifacts on low-field MR Scanners | |
| Optimalizácia a štandardizácia kvantitatívnych metód zobrazovania magnetickou rezonanciou. Potlačenie kovových artefaktov na nízkopolových MR skeneroch | |
| Program: | Plán obnovy EÚ |
| Duration: | 1.9.2024 – 31.8.2026 |
| Project leader: | Ing. Gogola Daniel, PhD. |
| AgeFlex – Development and standardization of MR-based methods for detecting and evaluating metabolic and structural adaptations of aging muscles to exercise | |
| Vývoj a štandardizácia MR metód na detekciu a vyhodnocovanie metabolických a štrukturálnych adaptácií svalov na starnutie a cvičenie | |
| Program: | APVV |
| Duration: | 1.9.2025 – 31.8.2029 |
| Project leader: | Mgr. Klepochová Radka, PhD. |
| Annotation: | Aging is associated with a loss of muscle mass and the functional capacity of skeletal muscles; however, regular exercise can slow down these processes. The focus of this project is on examining the metabolic, functional, and structural parameters in the lower limb muscles, which we can non-invasively and repeatedly measure using innovative magnetic resonance methods (MR). This allows us to compare the trajectories of aging in skeletal muscles of sedentary individuals and those who are physically active. One of the key parameters that define a muscle\’s ability to efficiently mobilize and use energy for muscle work is called metabolic flexibility. The aim of the project is to develop innovative MR methods to study metabolic flexibility and structural changes in skeletal muscles during aging, and relate them to whole-body metabolic flexibility, as well as the metabolic phenotype and structural and molecular changes in the skeletal muscles of older adults. As part of the project, we will standardize the measurement of dynamic changes in metabolites in muscle during exercise using proton (1H) MR spectroscopy, create standard procedures for quality control of acquired MR spectroscopy data, and a key aspect of the project will also be the development of an automated segmentation method based on a convolutional neural network, which will enable more efficient and reliable evaluation of MR images of skeletal muscles. These innovative methods will be validated using data from ongoing longitudinal studies at the Biomedical Center of the Slovak Academy of Sciences, and their results will be directly compared with parallel changes in metabolic health, functional capacity, histological structure, and molecular mediators of metabolic flexibility in skeletal muscles. The results may not only improve our understanding of the processes that define metabolic flexibility during aging but may also offer relevant strategies to support metabolically healthy aging. |
| OrgPipeSK2025 – Research of the metal organ pipe collections of historical pipe organs in Slovakia | |
| Výskum kovového píšťalového fondu historických organov na Slovensku | |
| Program: | APVV |
| Duration: | 1.9.2025 – 31.8.2028 |
| Project leader: | RNDr. Krafčík Andrej, PhD. |
| Annotation: | The sound-stylistic quality of historical organs is determined by various factors, including the material used for the organ pipes and the scaling (mensuration) of individual pipes and entire stops. The proposed project will examine organ metal as a key sound-stylistic determinant of historical organs, with consideration of the constructional evolution of organs in Slovakia from the 17th to the 20th century. The project will be conducted in four phases. The first phase will focus on the chemical composition analysis of organ pipe metal from selected instruments. These pipes and entire stops will undergo mensuration analysis, leading to the development of a mathematical model. The next phase will involve the visual recording (collection) of signings—etched or stamped markings indicating the specific tone for which a pipe is constructed. The signings of pipes from instruments with known builders will be documented to create a standard that will enable the use of neural networks (AI) to identify the authorship of organs whose builders are currently unknown. The research will also address the technical condition of organ metal, particularly corrosion, which affects not only the sound properties but also the preservation of the metal components of these historical instruments. The project\’s outcomes will include an online map of organ metal composition, corrosion, mensurations, an atlas of various types of corrosion and defects in organ pipes, as well as a comprehensive mapping of the metal and mensurations of studied stops. Furthermore, we will establish a method for gradually authorizing organs whose builders remain unidentified. All findings will be contextualized within the sound-stylistic development of historical organ building on Slovak territory. |
| – | |
| Štipendiá pre excelentných PhD. študentov a študentky R1 | |
| Program: | Plán obnovy EÚ |
| Duration: | 1.9.2023 – 31.8.2026 |
| Project leader: | Ing. Pajanová Iveta |
| Annotation: | PhD Topic: Application of deep-learning algorithms on automated MRI data processing. Annotation: Automated identification and segmentation of clinical data, obtained primary by MRI, is very desirable. The reason is typically large size of data and therefore enormous time, which radiologist has to invest into the manual segmentation. Availability of powerful hardware open new capabilities to automate this processes and speedup via deep learning techniques using convolutional neural networks (CNN). Therefore, student will learn the fundamental functionality principles of MRI device (theoretically and practically), try manual segmentation of volumetric MRI data, and theoretically and practically learn principles of CNN. Student will design own architecture of CNN for automated segmentation of volumetric data, further train, validate and implement on testing data.The output of this dissertation should be a CNN capable of deployment in clinical practice, in the diagnosis and quantitative analysis of selected tissues (cartilage, ligaments, tendons, menisci, subcutaneous fat, etc.). It is theoretical work, in which programming basics and knowledge of some programming language are necessary. As the programming environment, for design and implementation of CNN, will be used Python with module TensorFlow. |
| Research of properties of magnetic nanoparticles for imaging purposes in biomedical diagnostics based on magnetic resonance methods | |
| Výskum vlastností magnetických nanočastíc pre účely zobrazovania v biomedicínskej diagnostike na báze metód magnetickej rezonancie | |
| Program: | VEGA |
| Duration: | 1.1.2023 – 31.12.2025 |
| Project leader: | Dr. Ing. Přibil Jiří, (PhD.) |
| Annotation: | The project focuses on experimental and theoretical research in the field of magnetic resonance imaging (MRI)methods. The following issues will be addressed in the project: 1. Research of properties of magneticnanoparticles in external magnetic fields regarding creation of a theoretical model and its subsequentexperimental verification. 2. Analysis of MRI scanning effect on cardiovascular system of a tested person in orderto find appropriate methods of detection, quantification, and design of measures to minimize them. 3. Analysis ofmetabolic processes in order to map the rate of energy production in the human heart and muscles in order todiagnose the slowing down of energy production in the heart. 4. Automated processing of MR images of thehuman knee in order to obtain quantitative characteristics and morphological quantities of individual tissues. 5.Calibration of gradient fields to ensure undistorted morphology in measured MR images. Mapping ofinhomogeneities into magn. fields using MRI methods |