More articles from FUNCTIONAL
- Resting-State Brain Activity for Early Prediction Outcome in Postanoxic Patients in a Coma with Indeterminate Clinical Prognosis
The authors used resting-state fMRI in a prospective study to compare whole-brain functional connectivity between patients with good and poor outcomes, implementing support vector machine learning. They automatically predicted coma outcome using resting-state fMRI and also compared the prediction based on resting-state fMRI with the outcome prediction based on DWI. Of 17 eligible patients who completed the study procedure (among 351 patients screened), 9 regained consciousness and 8 remained comatose. They found higher functional connectivity in patients recovering consciousness, with greater changes occurring within and between the occipitoparietal and temporofrontal regions. Coma outcome prognostication based on resting-state fMRI machine learning was very accurate, notably for identifying patients with good outcome. They conclude that resting-state fMRI might bridge the gap left in early prognostication of postanoxic patients in a coma by identifying those with both good and poor outcomes.
- Application of Deep Learning to Predict Standardized Uptake Value Ratio and Amyloid Status on 18F-Florbetapir PET Using ADNI Data
Using the Alzheimer's Disease Neuroimaging Initiative dataset, the authors identified 2582 18F-florbetapir PET scans, which were separated into positive and negative cases by using a standardized uptake value ratio threshold of 1.1. They trained convolutional neural networks to predict standardized uptake value ratio and classify amyloid status. The best performance was seen for ResNet-50 by using regression before classification, 3 input PET slices, and pretraining, with a standardized uptake value ratio root-mean-squared error of 0.054, corresponding to 95.1% correct amyloid status prediction. The best trained network was more accurate than humans (96% versus a mean of 88%, respectively). They conclude that deep learning algorithms can estimate standardized uptake value ratio and use this to classify 18F-florbetapir PET scans and have promise to automate this laborious calculation.
- Sensitivity of the Inhomogeneous Magnetization Transfer Imaging Technique to Spinal Cord Damage in Multiple Sclerosis
Anatomic images covering the cervical spinal cord from the C1 to C6 levels and DTI, magnetization transfer/inhomogeneous magnetization transfer images at the C2/C5 levels were acquired in 19 patients with MS and 19 paired healthy controls. Anatomic images were segmented in spinal cord GM and WM, both manually and using the AMU40 atlases. MS lesions were manually delineated. MR imaging metrics were analyzed within normal-appearing and lesion regions in anterolateral and posterolateral WM and compared using Wilcoxon rank tests and z scores. The use of a multiparametric MR imaging protocol combined with an automatic template-based GM/WM segmentation approach in the current study outlined a higher sensitivity of the ihMT technique toward spinal cord pathophysiologic changes in MS compared with atrophy measurements, DTI, and conventional MT. The authors also conclude that the clinical correlations between ihMTR and functional impairment observed in patients with MS also argue for its potential clinical relevance, paving the way for future longitudinal multicentric clinical trials in MS.