Projects

Iveta Pajanová

Project selection:

National projects

–
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.
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: SRDA
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).