Publications by authors named "G Baselli"
Article Synopsis
- Breast arterial calcifications (BAC) found in mammograms may indicate cardiovascular disease risk, and a study evaluated the performance of eleven pretrained CNNs, specifically focusing on their ability to detect BAC.
- The research analyzed mammograms from 1,493 women to classify images as BAC or non-BAC, using metrics like AUC-ROC and F-score to assess the effectiveness of the CNNs, with models like VGG and MobileNet showing promising results.
- The findings suggest that deep transfer learning can effectively automate BAC detection, with shallower networks requiring less training time while still yielding strong performance.
Inhibitor development is the most severe complication of hemophilia A (HA) care and is associated with increased morbidity and mortality. This study aimed to use a novel immunoglobulin G epitope mapping method to explore the factor VIII (FVIII)-specific epitope profile in the SIPPET cohort population and to develop an epitope mapping-based inhibitor prediction model. The population consisted of 122 previously untreated patients with severe HA who were followed up for 50 days of exposure to FVIII or 3 years, whichever occurred first.
View Article and Find Full Text PDFBackground & Aims: The PNPLA3 rs738409 C>G (encoding for I148M) variant is a risk locus for the fibrogenic progression of chronic liver diseases, a process driven by hepatic stellate cells (HSCs). We investigated how the PNPLA3 I148M variant affects HSC biology using transcriptomic data and validated findings in 3D-culture models.
Methods: RNA sequencing was performed on 2D-cultured primary human HSCs and liver biopsies of individuals with obesity, genotyped for the PNPLA3 I148M variant.
Background: The emotional domain is often impaired across many neurological diseases, for this reason it represents a relevant target of rehabilitation interventions. Functional changes in neural activity related to treatment can be assessed with functional MRI (fMRI) using emotion-generation tasks in longitudinal settings. Previous studies demonstrated that within-subject fMRI signal reliability can be affected by several factors such as repetition suppression, type of task and brain anatomy.
View Article and Find Full Text PDF