Publications by authors named "Roberto Paolella"
Article Synopsis
- Predicting recovery outcomes after mild traumatic brain injury (mTBI) is difficult, especially since conventional MRI often shows normal results despite incomplete recovery in patients.
- Advanced imaging techniques like diffusion MRI (dMRI) can reveal microstructural brain changes, possibly improving the accuracy of outcome predictions using machine learning models known as linear support vector classifiers (linearSVCs).
- The study involved analyzing dMRI data from 179 mTBI patients and 85 controls, aiming to differentiate between patients with complete versus incomplete recovery, while also experimenting with a method called ComBat to standardize imaging data and enhance classification accuracy.
Most data-driven methods are very susceptible to data variability. This problem is particularly apparent when applying Deep Learning (DL) to brain Magnetic Resonance Imaging (MRI), where intensities and contrasts vary due to acquisition protocol, scanner- and center-specific factors. Most publicly available brain MRI datasets originate from the same center and are homogeneous in terms of scanner and used protocol.
View Article and Find Full Text PDFMRI diffusion data suffers from significant inter- and intra-site variability, which hinders multi-site and/or longitudinal diffusion studies. This variability may arise from a range of factors, such as hardware, reconstruction algorithms and acquisition settings. To allow a reliable comparison and joint analysis of diffusion data across sites and over time, there is a clear need for robust data harmonization methods.
View Article and Find Full Text PDF