Image analysis for Alzheimer's disease prediction: Embracing pathological hallmarks for model architecture design
This work addresses Alzheimer's disease diagnosis for medical applications, representing an incremental improvement by combining existing methods.
The paper tackled Alzheimer's disease prediction by developing a neural network that simultaneously captures local and global brain changes from MRI, achieving an average precision score of 0.95±0.03 for classifying normal subjects and AD patients.
Alzheimer's disease (AD) is associated with local (e.g. brain tissue atrophy) and global brain changes (loss of cerebral connectivity), which can be detected by high-resolution structural magnetic resonance imaging. Conventionally, these changes and their relation to AD are investigated independently. Here, we introduce a novel, highly-scalable approach that simultaneously captures $\textit{local}$ and $\textit{global}$ changes in the diseased brain. It is based on a neural network architecture that combines patch-based, high-resolution 3D-CNNs with global topological features, evaluating multi-scale brain tissue connectivity. Our local-global approach reached competitive results with an average precision score of $0.95\pm0.03$ for the classification of cognitively normal subjects and AD patients (prevalence $\approx 55\%$).