# SurfGNN: A robust surface-based prediction model with interpretability for coactivation maps of spatial and cortical features

arXiv: https://arxiv.org/abs/2411.05825 · HTML: https://mlsanity.com/paper/2411.05825/

## Key facts

- Cited by 3 papers in the map (data through 14 Oct 2026).
- Builds on 19 of its 67 references that are in the map.
- First posted on arXiv 5 Nov 2024.

## Builds on (most cited first, 19 of 19)

- [Graph Attention Networks](https://mlsanity.com/paper/1710.10903/) (2017)
- [Grad-CAM: Visual Explanations from Deep Networks via Gradient-based Localization](https://mlsanity.com/paper/1610.02391/) (2016)
- [Neural Message Passing for Quantum Chemistry](https://mlsanity.com/paper/1704.01212/) (2017)
- [A Comprehensive Survey on Graph Neural Networks](https://mlsanity.com/paper/1901.00596/) (2019)
- [Geometric deep learning on graphs and manifolds using mixture model CNNs](https://mlsanity.com/paper/1611.08402/) (2016)
- [Spherical CNNs](https://mlsanity.com/paper/1801.10130/) (2018)
- [Explainability in Graph Neural Networks: A Taxonomic Survey](https://mlsanity.com/paper/2012.15445/) (2020)
- [Stronger, Faster and More Explainable: A Graph Convolutional Baseline for Skeleton-based Action Recognition](https://mlsanity.com/paper/2010.09978/) (2020)
- [Spherical CNNs on Unstructured Grids](https://mlsanity.com/paper/1901.02039/) (2019)
- [Graph Pooling for Graph Neural Networks: Progress, Challenges, and Opportunities](https://mlsanity.com/paper/2204.07321/) (2022)
- [Spherical U-Net on Cortical Surfaces: Methods and Applications](https://mlsanity.com/paper/1904.00906/) (2019)
- [Counterfactual Graphs for Explainable Classification of Brain Networks](https://mlsanity.com/paper/2106.08640/) (2021)
- [Testing the robustness of attribution methods for convolutional neural networks in MRI-based Alzheimer's disease classification](https://mlsanity.com/paper/1909.08856/) (2019)
- [Surface Vision Transformers: Attention-Based Modelling applied to Cortical Analysis](https://mlsanity.com/paper/2203.16414/) (2022)
- [Explainable Brain Age Prediction using coVariance Neural Networks](https://mlsanity.com/paper/2305.18370/) (2023)
- [ICAM-reg: Interpretable Classification and Regression with Feature Attribution for Mapping Neurological Phenotypes in Individual Scans](https://mlsanity.com/paper/2103.02561/) (2021)
- [Geometric Convolutional Neural Network for Analyzing Surface-Based Neuroimaging Data](https://mlsanity.com/paper/1708.00587/) (2017)
- [The Multiscale Surface Vision Transformer](https://mlsanity.com/paper/2303.11909/) (2023)
- [NeuroExplainer: Fine-Grained Attention Decoding to Uncover Cortical Development Patterns of Preterm Infants](https://mlsanity.com/paper/2301.00815/) (2023)

## Built on by (most cited first, 3 of 3)

- [SurfAge-Net: A Hierarchical Surface-Based Network for Interpretable Fine-Grained Brain Age Prediction](https://mlsanity.com/paper/2602.06994/) (2026)
- [Cross-Subject EEG Emotion Recognition Based on Temporal Asynchronous Alignment Contrastive Learning](https://mlsanity.com/paper/2605.22379/) (2026)
- [vSV-ViT: Variable-size SuperVertex Vision Transformer for Cortical Surface Learning in Alzheimer's Disease](https://mlsanity.com/paper/2605.26514/) (2026)

## Abstract (arXiv)

Current brain surface-based prediction models often overlook the variability of regional attributes at the cortical feature level. While graph neural networks (GNNs) excel at capturing regional differences, they encounter challenges when dealing with complex, high-density graph structures. In this work, we consider the cortical surface mesh as a sparse graph and propose an interpretable prediction model-Surface Graph Neural Network (SurfGNN). SurfGNN employs topology-sampling learning (TSL) and region-specific learning (RSL) structures to manage individual cortical features at both lower and higher scales of the surface mesh, effectively tackling the challenges posed by the overly abundant mesh nodes and addressing the issue of heterogeneity in cortical regions. Building on this, a novel score-weighted fusion (SWF) method is implemented to merge nodal representations associated with each cortical feature for prediction. We apply our model to a neonatal brain age prediction task using a dataset of harmonized MR images from 481 subjects (503 scans). SurfGNN outperforms all existing state-of-the-art methods, demonstrating an improvement of at least 9.0% and achieving a mean absolute error (MAE) of 0.827+0.056 in postmenstrual weeks. Furthermore, it generates feature-level activation maps, indicating its capability to identify robust regional variations in different morphometric contributions for prediction.