Allows construction of a similarity measure between brain scans. BrainPrint facilitates the statistical analysis by computing distances between shape descriptors without the need for establishing direct correspondences. It focuses entirely on the geometric properties of the brain and consequently it is a characterization that is robust to intensity variations between scans. This tool is especially beneficial when working with large datasets.
Accesses age prediction models created by using machine learning based analysis of neuroimaging data. NAPR system allows external users to predict the age of individual subjects using their own MRI data. The approach will allow for rigorous evaluation and comparison of age prediction methods and ultimately lead to age prediction models that are accurate enough to be utilized for clinical applications. It provides a system for out-of-sample model testing, which is the most rigorous model evaluation technique available.
A modular ensemble of 21 deep neural networks (DNNs) of varying depth, structure and optimization to predict human chronological age using a basic blood test. Aging.AI allows any patient with blood test data to predict their age and sex. The ensemble approach may facilitate integration of multi-modal data linked to chronological age and sex that may lead to simple, minimally invasive, and affordable methods of tracking integrated biomarkers of aging in humans and performing cross-species feature importance analysis.
0 - 0 of 0
1 - 2 of 2