# Interpretation of Brain Morphology in Association to Alzheimer's Disease Dementia Classification Using Graph Convolutional Networks on Triangulated Meshes

arXiv: https://arxiv.org/abs/2008.06151 · HTML: https://mlsanity.com/paper/2008.06151/

## Key facts

- Cited by 8 papers in the map (data through 14 Oct 2026).
- First posted on arXiv 14 Aug 2020.

## Built on by (most cited first, 8 of 8)

- [Multimodal Machine Learning in Image-Based and Clinical Biomedicine: Survey and Prospects](https://mlsanity.com/paper/2311.02332/) (2023)
- [TetCNN: Convolutional Neural Networks on Tetrahedral Meshes](https://mlsanity.com/paper/2302.03830/) (2023)
- [Applications of interpretable deep learning in neuroimaging: a comprehensive review](https://mlsanity.com/paper/2406.17792/) (2024)
- [Body Fat Estimation from Surface Meshes using Graph Neural Networks](https://mlsanity.com/paper/2308.02493/) (2023)
- [Isomorphic mesh generation from point clouds with multilayer perceptrons](https://mlsanity.com/paper/2210.14157/) (2022)
- [Single Domain Generalization for Alzheimer's Detection from 3D MRIs with Pseudo-Morphological Augmentations and Contrastive Learning](https://mlsanity.com/paper/2505.22465/) (2025)
- [X-SiT: Inherently Interpretable Surface Vision Transformers for Dementia Diagnosis](https://mlsanity.com/paper/2506.20267/) (2025)
- [Explainable Graph Neural Networks: Understanding Brain Connectivity and Biomarkers in Dementia](https://mlsanity.com/paper/2509.18568/) (2025)

## Abstract (arXiv)

We propose a mesh-based technique to aid in the classification of Alzheimer's disease dementia (ADD) using mesh representations of the cortex and subcortical structures. Deep learning methods for classification tasks that utilize structural neuroimaging often require extensive learning parameters to optimize. Frequently, these approaches for automated medical diagnosis also lack visual interpretability for areas in the brain involved in making a diagnosis. This work: (a) analyzes brain shape using surface information of the cortex and subcortical structures, (b) proposes a residual learning framework for state-of-the-art graph convolutional networks which offer a significant reduction in learnable parameters, and (c) offers visual interpretability of the network via class-specific gradient information that localizes important regions of interest in our inputs. With our proposed method leveraging the use of cortical and subcortical surface information, we outperform other machine learning methods with a 96.35% testing accuracy for the ADD vs. healthy control problem. We confirm the validity of our model by observing its performance in a 25-trial Monte Carlo cross-validation. The generated visualization maps in our study show correspondences with current knowledge regarding the structural localization of pathological changes in the brain associated to dementia of the Alzheimer's type.