| EDABSS - EEG data analysis by blind source separation methods |
| Analýza EEG signálu pomocou metód hľadania skrytých zdrojov |
| Program: | |
| Project ID: | 09I03-03-V04-00205 |
| Duration: | 1.9.2024 - 31.8.2026 |
| Project leader: | Mgr. Rošťáková Zuzana, PhD. |
| Annotation: |
Blind source separation (BSS) approaches are unsupervised machine learning methods focused on the detection of hidden, directly unobservable (latent) structure of real-world data. They play a crucial role in image processing, medical imaging, and music. The proposed project focuses mainly on human electroencephalogram (EEG), for which BSS is beneficial when detecting the narrowband brain oscillations representing brain processes either in health or disease. Two-dimensional BSS methods like principal or independent component analysis are easily applicable and understandable for a broader medical and neurophysiological community. However, the estimated latent component properties are usually incompatible with the real electrophysiological signal character. Consequently, they miss their neurophysiological interpretation. Tensor decomposition is a complex but more flexible mathematical procedure that allows adapting the model structure and constraints to the solution to mimic real-world signal characteristics. The proposed project focuses on tensor decomposition as a tool for i) EEG preprocessing, artefact detection and removal, ii) EEG latent structure analysis using a nonnegative tensor decomposition with block structure allowing to model various relationships between latent components, and iii) post-decomposition analysis of latent component dynamic properties. Obtaining comprehensive information about EEG latent structure and developing novel, user-friendly algorithms is crucial for better understanding brain processes and new methods for treating neurophysiological diseases and disorders. |
| 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: | |
| Project ID: | 09I03-03-V04-00544 |
| Duration: | 1.9.2024 - 31.8.2026 |
| Project leader: | Ing. Gogola Daniel, PhD. |
| cBCI-VR - Collaborative BCI post-stroke neurorehabilitation using a patient-therapist interactive VR environment |
| Pacient-terapeut kolaboratívna BCI-VR neurorehabilitácia po cievnej mozgovej príhode |
| Program: | |
| Project ID: | 09I03-03-V04-0043 |
| Duration: | 1.9.2024 - 31.8.2026 |
| Project leader: | Ing. Mgr. Rosipal Roman, DrSc. |
| Annotation: |
A growing body of evidence suggests that integrated brain-computer interface (BCI) technologies and virtual reality (VR) environments provide a flexible platform for a range of neurorehabilitation therapies, including significant motor recovery and cognitive-behavioral therapy following stroke. When a subject is immersed in such an environment, their perceptual level of social interaction is often impaired due to a suboptimal interface quality that lacks the social aspect of human interactions. The project proposes a user-friendly intelligent BCI system with a suitable VR environment in which both patient and therapist interact through their person-specific avatar representations. On the one hand, the patient voluntarily and at his/her own pace controls his/her activity in the environment and interacts with the therapist through a BCI-driven mental imagery process. On the other hand, the therapist\'s unrestricted motor and communication skills allow for full control of the environment. Thus, the VR environment can be flexibly modified by the therapist, allowing for the creation and selection of different occupational therapy scenarios according to the patient\'s recovery needs, mental states, and immediate reactions. |
| SQUIDiron - Determination of Iron in blood and tissues of laboratory animals using SQUID magnetometer. |
| Stanovenie množstva železa v krvi a tkanivách laboratórnych zvierat pomocou SQUID magnetometra |
| Program: | |
| Project ID: | 09I03-03-V04-00528 |
| Duration: | 1.9.2024 - 31.8.2026 |
| Project leader: | Mgr. Škrátek Martin, PhD. |
| Annotation: |
Iron is an essential chemical element that is part of many metabolic processes. However, the amount of iron in the body must be balanced, as its excess or deficiency can lead to serious health conditions. Iron is found in the body in ferritin, hemoglobin or transferrin proteins. Deoxyhemoglobin, methemoglobin, and myoglobin are known to exhibit paramagnetism, which originates from the Fe2+ Fe3+ ions embedded in their molecules. Ferritin, as an iron storage protein, contains Fe atoms mineralized in the form of oxyhydroxide nanoparticles, whose behavior is superparamagnetic. SQUID magnetometry offers the possibility of detecting and quantifying different forms of iron with high sensitivity and could be more useful than other established methods (colorimetric, spectrophotometric, histochemical or atomic absorption spectrometry) in determining the amount of iron in small samples. |
| - |
| Štipendiá pre excelentných PhD. študentov a študentky R1 |
| Program: | |
| 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. |
SAS
HRS4R
