Foundation vision-language models are currently transforming computer vision, and are on the rise in medical imaging fueled by their very promising generalization capabilities. However, the initial attempts to transfer this new paradigm to medical imaging have shown less impressive performances than those observed in other domains, due to the significant domain shift and the complex, expert domain knowledge inherent to medical-imaging tasks. Motivated by the need for domain-expert foundation models, we present FLAIR, a pre-trained vision-language model for universal retinal fundus image understanding.
View Article and Find Full Text PDFBackground: The evidence supporting the effectiveness of combined interventions in Alzheimer's disease (AD) patients remains inconclusive.
Objective: The aim of this study was to evaluate the mid- and long-term effectiveness of physical training, alone or combined with cognitive games, on cognitive performance in patients with moderate AD.
Methods: Seventy-nine AD patients (≈73% females, age of ≈70±1 years) were randomly divided into three groups: aerobic-based training (AT-group, = 27), aerobic-based training plus cognitive games (ACT-group, = 25), and a control group engaged in reading (CG, = 26), two sessions per week.
Introduction: The present study aimed to evaluate the effect of acute aerobic exercise on certain cognitive functions known to be affected by Alzheimer's disease (AD), with a particular emphasis on sex differences.
Methods: A total of 53 patients, with a mean age of 70.54 ± 0.