Abstract
Several patterns of atrophy have been identified and strongly related to Alzheimer’s disease (AD) pathology and its progression. Morphological changes in brain shape have been identified up to ten years before clinical diagnoses of AD, making its early diagnosis more desirable. We propose novel geometric deep learning frameworks for the analysis of brain shape in the context of neurodegeneration caused by AD. Our deep neural networks learn low-dimensional shape descriptors of multiple neuroanatomical structures, instead of handcrafted features for each structure. A discriminative network using spiral convolution on 3D meshes is constructed for the in-vivo binary classification of AD from healthy controls (HCs) using a fast and efficient “spiral” convolution operator on 3D triangular mesh surfaces of human brain subcortical structures extracted from T1-weighted magnetic resonance imaging (MRI). Our network architecture consists of modular learning blocks using residual connections to improve overall classifier performance.
In this work: (1) a discriminative network is used to analyze the efficacy of disease classification using input data from multiple brain structures and compared to using a single hemisphere or a single structure. It also outperforms prior work using spectral graph convolution on the same the same tasks, as well as alternative methods that operate on intermediate point cloud representations of 3D shapes. (2) Additionally, visual interpretations for regions on the surface of brain structures that are associated to true positive AD predictions are generated and fall in accordance with the current reports on the structural localization of pathological changes associated to AD. (3) A conditional generative network is also implemented to analyze the effects of phenotypic priors given to the model (i.e. AD diagnosis) in generating subcortical structures. The generated surface meshes by our model indicate learned morphological differences in the presence of AD that agrees with the current literature on patterns of atrophy associated to the disease. In particular, our inference results demonstrate an overall reduction in subcortical mesh volume and surface area in the presence of AD, especially in the hippocampus. The low-dimensional shape descriptors obtained by our generative model are also evaluated in our discriminative baseline comparisons versus our discriminative network and the alternative shape-based approaches.
Highlights
Modular geometric deep learning framework for discriminative and generative anatomical shape analysis.
Novel anisotropic spiral convolution operator is utilized on direct morphable surface meshes of neuroanatomical structures to learn shape descriptors, rather than shape descriptors from intermediate shape representations (i.e. voxels and point clouds).
Discriminative framework outperforms state-of-the-art methods using learned shape descriptors for Alzheimer’s disease (AD) versus healthy control binary classification.
Visual interpretability of discriminative model’s decision making process by localizing areas on subcortical structures that are indicative of true positive AD classification results.
Generative framework uses conditional information to assess shape variations specific to AD diagnosis.
Extension to joint analysis of multiple anatomical structures demonstrates stronger discriminative performance of AD classification in comparison to single structure or hemisphere isolation.
Competing Interest Statement
The authors have declared no competing interest.
Footnotes
↵** Data used in preparation of this article were obtained from the Alzheimer’s Disease Neuroimaging Initiative (ADNI) database (adni.loni.usc.edu). As such, the investigators within the ADNI contributed to the design and implementation of ADNI and/or provided data but did not participate in analysis or writing of this report. A complete listing of ADNI investigators can be found at: http://adni.loni.usc.edu/wp-content/uploads/howtoapply/ADNIAcknowledgementList.pdf