Learning Covariance-Based Multi-Scale Representation of Neuroimaging Measures for Alzheimer Classification
This work addresses the challenge of underdetermined systems in deep learning for medical applications like Alzheimer's disease diagnosis, offering an incremental improvement in model efficiency and interpretability.
The paper tackled the problem of training deep neural networks with limited medical imaging data by proposing a framework that uses a convolution transform based on scale-space theory and covariance structure to create an efficient high-dimensional representation, resulting in better performance and faster convergence on Alzheimer's disease classification from neuroimaging data.
Stacking excessive layers in DNN results in highly underdetermined system when training samples are limited, which is very common in medical applications. In this regard, we present a framework capable of deriving an efficient high-dimensional space with reasonable increase in model size. This is done by utilizing a transform (i.e., convolution) that leverages scale-space theory with covariance structure. The overall model trains on this transform together with a downstream classifier (i.e., Fully Connected layer) to capture the optimal multi-scale representation of the original data which corresponds to task-specific components in a dual space. Experiments on neuroimaging measures from Alzheimer's Disease Neuroimaging Initiative (ADNI) study show that our model performs better and converges faster than conventional models even when the model size is significantly reduced. The trained model is made interpretable using gradient information over the multi-scale transform to delineate personalized AD-specific regions in the brain.