Contribution to a book

This study investigates how to improve the reliability of probability estimates produced by deep learning models for the detection of Alzheimer’s disease using MRI data. Although convolutional neural networks (CNNs) can accurately classify neurodegenerative diseases, their softmax outputs often misrepresent true classification probabilities. [...]

Ictal single-photon emission computed tomography (SPECT) is an imaging technique used to identify the seizure-onset zone (SOZ) in epilepsy patients. It visualizes increased cerebral blood flow near the SOZ through radiopharmaceuticals injected shortly after seizure onset. [...]

Accurately predicting age at symptom onset in genetic frontotemporal dementia (FTD) remains challenging due to substantial inter-individual variability, even among carriers of distinct pathogenic variants within the same gene. Time-to-event models provide a natural framework to address this problem while accounting for right censoring in presymptomatic individuals. [...]

Growing interest in perivascular spaces (PVS) quantification has highlighted the need for accurate and robust methods, particularly in magnetic resonance imaging (MRI). The Frangi filter is widely used to enhance tubular structures, including PVS, however its performance is highly dependent on scale selection. [...]

This case highlights a diagnostic challenge in a 63-year-old female with mild cognitive impairment (MCI) and an arteriovenous malformation (AVM) in the right parieto-occipital brain region. While the patient exhibited minor memory deficits with preserved daily function, a tau-PET scan using [18F]PI-2620 was performed to evaluate possible underlying tauopathy. [...]

This case study reports a diagnostically complex scenario involving a 77-year-old female who initially presented with mild memory complaints. Over the course of one year, she exhibited significant cognitive decline, with MMSE scores dropping from 27/30 to 20/30. [...]

In many biomedical segmentation tasks, the preservation of elongated structure continuity and length is more important than voxel-wise accuracy. We propose two novel loss functions, Negative Centerline Loss and Simplified Topology Loss, that, applied to Convolutional Neural Networks (CNNs), help preserve connectivity of output instances. [...]

Global societies face unprecedented challenges as populations age. The ability to navigate is central to nearly all meaningful activities in which older adults participate, promoting both independence and health. [...]

Alzheimer's disease (AD), a progressive neurodegenerative disorder, is projected to affect over 130 million people globally by 2050. While extensive efforts have focused on targeting molecular hallmarks such as amyloid-beta (Aβ) plaques and tau pathology, network-level dysfunction remains a critical but underexplored component of AD progression. [...]

Learning and memory are fundamental brain functions governed by rhythmic oscillatory activity, which synchronizes neural communication and modulates network dynamics. Distinct oscillatory patterns-theta (θ), beta (β), gamma (γ), and sharp wave-ripples (SWR)-coordinate neural ensemble activity, particularly in the hippocampal CA1-CA3 regions, where they play a crucial role in learning and memory. [...]