# NeuroExplainer: Fine-Grained Attention Decoding to Uncover Cortical Development Patterns of Preterm Infants

arXiv: https://arxiv.org/abs/2301.00815 · HTML: https://mlsanity.com/paper/2301.00815/

## Key facts

- Cited by 1 papers in the map (data through 14 Oct 2026).
- Builds on 23 of its 51 references that are in the map.
- First posted on arXiv 1 Jan 2023.

## Builds on (most cited first, 23 of 23)

- [Attention Is All You Need](https://mlsanity.com/paper/1706.03762/) (2017)
- [Grad-CAM: Visual Explanations from Deep Networks via Gradient-based Localization](https://mlsanity.com/paper/1610.02391/) (2016)
- [Learning Deep Features for Discriminative Localization](https://mlsanity.com/paper/1512.04150/) (2015)
- [A Survey on Deep Learning in Medical Image Analysis](https://mlsanity.com/paper/1702.05747/) (2017)
- [SmoothGrad: removing noise by adding noise](https://mlsanity.com/paper/1706.03825/) (2017)
- [Geometric deep learning on graphs and manifolds using mixture model CNNs](https://mlsanity.com/paper/1611.08402/) (2016)
- [Deep Learning for Medical Image Analysis](https://mlsanity.com/paper/1708.08987/) (2017)
- [Explainability in Graph Neural Networks: A Taxonomic Survey](https://mlsanity.com/paper/2012.15445/) (2020)
- [Techniques for Interpretable Machine Learning](https://mlsanity.com/paper/1808.00033/) (2018)
- [Not-so-supervised: a survey of semi-supervised, multi-instance, and transfer learning in medical image analysis](https://mlsanity.com/paper/1804.06353/) (2018)
- [Deep neural network models for computational histopathology: A survey](https://mlsanity.com/paper/1912.12378/) (2019)
- [Convolutional Neural Networks for Classification of Alzheimer's Disease: Overview and Reproducible Evaluation](https://mlsanity.com/paper/1904.07773/) (2019)
- [MeshNet: Mesh Neural Network for 3D Shape Representation](https://mlsanity.com/paper/1811.11424/) (2018)
- [Subdivision-Based Mesh Convolution Networks](https://mlsanity.com/paper/2106.02285/) (2021)
- [Interpretable Graph Neural Networks for Connectome-Based Brain Disorder Analysis](https://mlsanity.com/paper/2207.00813/) (2022)
- [Spherical U-Net on Cortical Surfaces: Methods and Applications](https://mlsanity.com/paper/1904.00906/) (2019)
- [RMDL: Recalibrated multi-instance deep learning for whole slide gastric image classification](https://mlsanity.com/paper/2010.06440/) (2020)
- [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)
- [A Deep-Discrete Learning Framework for Spherical Surface Registration](https://mlsanity.com/paper/2203.12999/) (2022)
- [Going Beyond Saliency Maps: Training Deep Models to Interpret Deep Models](https://mlsanity.com/paper/2102.08239/) (2021)
- [Deep Modeling of Growth Trajectories for Longitudinal Prediction of Missing Infant Cortical Surfaces](https://mlsanity.com/paper/2009.02797/) (2020)
- [An explainability framework for cortical surface-based deep learning](https://mlsanity.com/paper/2203.08312/) (2022)

## Built on by (most cited first, 1 of 1)

- [SurfGNN: A robust surface-based prediction model with interpretability for coactivation maps of spatial and cortical features](https://mlsanity.com/paper/2411.05825/) (2024)

## Abstract (arXiv)

Deploying reliable deep learning techniques in interdisciplinary applications needs learned models to output accurate and (even more importantly) explainable predictions. Existing approaches typically explicate network outputs in a post-hoc fashion, under an implicit assumption that faithful explanations come from accurate predictions/classifications. We have an opposite claim that explanations boost (or even determine) classification. That is, end-to-end learning of explanation factors to augment discriminative representation extraction could be a more intuitive strategy to inversely assure fine-grained explainability, e.g., in those neuroimaging and neuroscience studies with high-dimensional data containing noisy, redundant, and task-irrelevant information. In this paper, we propose such an explainable geometric deep network dubbed as NeuroExplainer, with applications to uncover altered infant cortical development patterns associated with preterm birth. Given fundamental cortical attributes as network input, our NeuroExplainer adopts a hierarchical attention-decoding framework to learn fine-grained attentions and respective discriminative representations to accurately recognize preterm infants from term-born infants at term-equivalent age. NeuroExplainer learns the hierarchical attention-decoding modules under subject-level weak supervision coupled with targeted regularizers deduced from domain knowledge regarding brain development. These prior-guided constraints implicitly maximizes the explainability metrics (i.e., fidelity, sparsity, and stability) in network training, driving the learned network to output detailed explanations and accurate classifications. Experimental results on the public dHCP benchmark suggest that NeuroExplainer led to quantitatively reliable explanation results that are qualitatively consistent with representative neuroimaging studies.