Search the repository

Keywords: kognitivne alternative, podnebna akcija, kolektivna akcija, socialna identiteta, modeliranje strukturnih enačb, magistrske naloge
Published in RUP: 12.10.2025; Views: 484; Downloads: 13
Full text (653,91 KB)

Abstract: Brain MRI segmentation plays a crucial role in neuroimaging studies and clinical trials by enabling the precise localization and quantification of brain tissues and structures. The advent of deep learning has transformed the field, offering accurate and fast tools for MRI segmentation. Nevertheless, several challenges limit the widespread applicability of these methods in practice. In this systematic review, we provide a comprehensive analysis of developments in deep learning-based segmentation of brain MRI in adults, segmenting the brain into tissues, structures, and regions of interest. We explore the key model factors influencing segmentation performance, including architectural design, choice of input size and model dimensionality, and generalization strategies. Furthermore, we address validation practices, which are particularly important given the scarcity of manual annotations, and identify the limitations of current methodologies. We present an extensive compilation of existing segmentation works and highlight the emerging trends and key results. Finally, we discuss the challenges and potential future directions in the field.
Keywords: magnetic resonance imaging, brain, image segmentation, deep learning
Published in RUP: 10.10.2025; Views: 675; Downloads: 9
Full text (956,69 KB)
This document has more files! More...

Keywords: Asteroidea, vedenje morskih zvezd, lokomotorni vzorci, slovensko morje, vpliv vrste in velikosti, diplomske naloge
Published in RUP: 07.10.2025; Views: 488; Downloads: 26
Full text (1,64 MB)

Keywords: dark patterns, UX design, psychological reactions, eyetracking, facial emotion analysis, stress level, final project paper
Published in RUP: 07.10.2025; Views: 475; Downloads: 5
Full text (6,06 MB)

Abstract: Phlebotomine sand flies (Diptera: Phlebotominae) are the principal vectors of Leishmania spp. (Kinetoplastida: Trypanosomatidae). In Central Europe, Phlebotomus mascittii is the predominant species, but largely understudied. To better understand factors driving its current distribution, we infer patterns of genetic diversity by testing for signals of population expansion based on two mitochondrial genes and model current and past climate and habitat suitability for seven post-glacial maximum periods, taking 19 climatic variables into account. Consequently, we elucidate their connections by environmental-geographical network analysis. Most analyzed populations share a main haplotype tracing back to a single glacial maximum refuge area on the Mediterranean coasts of South France, which is supported by network analysis. The rapid range expansion of Ph. mascittii likely started in the early mid-Holocene epoch until today and its spread possibly followed two routes. The first one was through northern France to Germany and then Belgium, and the second across the Ligurian coast through present-day Slovenia to Austria, toward the northern Balkans. Here we present a combined approach to reveal glacial refugia and post-glacial spread of Ph. mascittii and observed discrepancies between the modelled and the current known distribution might reveal yet overlooked populations and potential further spread.
Keywords: Phlebotomus mascittii, modeling, Europe
Published in RUP: 06.10.2025; Views: 351; Downloads: 5
Full text (2,55 MB)
This document has more files! More...