Deep Multi-Structural Shape Analysis: Application to Neuroanatomy
This work addresses the challenge of neuroanatomical shape analysis for medical diagnosis, offering a method that eliminates the need for manual feature engineering, though it appears incremental as it adapts existing techniques like spatial transformer networks and occlusion methods to point clouds.
The paper tackles the problem of analyzing neuroanatomical shapes for disease prediction and brain age regression by proposing a deep neural network that operates directly on raw point clouds without mesh processing or point correspondences, achieving performance demonstrated on Alzheimer's disease and mild cognitive impairment prediction and brain age regression.
We propose a deep neural network for supervised learning on neuroanatomical shapes. The network directly operates on raw point clouds without the need for mesh processing or the identification of point correspondences, as spatial transformer networks map the data to a canonical space. Instead of relying on hand-crafted shape descriptors, an optimal representation is learned in the end-to-end training stage of the network. The proposed network consists of multiple branches, so that features for multiple structures are learned simultaneously. We demonstrate the performance of our method on two applications: (i) the prediction of Alzheimer's disease and mild cognitive impairment and (ii) the regression of the brain age. Finally, we visualize the important parts of the anatomy for the prediction by adapting the occlusion method to point clouds.