Publications by authors named "A Miladinovic"
Background: Ocular following responses (OFRs)-small-amplitude, short-latency reflexive eye movements-have been used to study visual motion processing, with potential diagnostic applications. However, they are difficult to record with commercial, video-based eye trackers, especially in children.
Objective: We aimed to design and develop a noninvasive eye tracker specialized for measuring OFRs, trading off lower temporal resolution and a smaller range for higher spatial resolution.
Article Synopsis
- Liquid-liquid phase separation in the cell nucleus plays a key role in gene regulation, chromatin organization, and DNA repair processes.
- The study utilized lipid-interacting RNA sequencing (LIPRNAseq) and confocal microscopy to explore the interaction of phosphatidylinositol 4,5 bisphosphate (PIP2) with specific RNA, identifying a PIP2-binding RNA motif and its colocalization with long non-coding RNA HANR in the perinucleolar compartment.
- The findings suggest a link between PIP2, lncHANR, and oncogenic super-enhancers, indicating their potential as prognostic markers for cancer and highlighting the importance of understanding lipid metabolism and RNA interactions for future cancer treatment strategies.
Article Synopsis
- The study explores how deep learning (DL) can enhance the classification of retinal diseases using OCT images, but faces challenges like variability in conditions and noise in the images.
- The research evaluated the performance of five DL architectures (ResNet18, ResNet34, ResNet50, VGG16, and InceptionV3) on a dataset of 5526 images, focusing on both data scarcity and label accuracy.
- Results showed that with 345 or more training images, DL models can accurately classify retinal pathologies, but labeling errors significantly impair performance, necessitating more training images to offset these errors.
Brain-computer interfaces (BCIs) are promising tools for motor neurorehabilitation. Achieving a balance between classification accuracy and system responsiveness is crucial for real-time applications. This study aimed to assess how the duration of time windows affects performance, specifically classification accuracy and the false positive rate, to optimize the temporal parameters of MI-BCI systems.
View Article and Find Full Text PDFArticle Synopsis
- The ability to merge retinal images for depth perception (stereopsis) is crucial for human vision and relies on good eye alignment and visual acuity during childhood.
- Early diagnosis of stereo deficiencies is important, but assessing these in infants and young children is challenging.
- Recent research indicates that ocular-following responses (OFRs) can effectively indicate stereo deficiencies, as they differ between children with normal and compromised stereopsis, suggesting their potential as a diagnostic tool for conditions like amblyopia.