# Neural Processes Mixed-Effect Models for Deep Normative Modeling of Clinical Neuroimaging Data

arXiv: https://arxiv.org/abs/1812.04998 · HTML: https://mlsanity.com/paper/1812.04998/

## Key facts

- Cited by 6 papers in the map (data through 14 Oct 2026).
- First posted on arXiv 12 Dec 2018.

## Built on by (most cited first, 6 of 6)

- [The Neural Process Family: Survey, Applications and Perspectives](https://mlsanity.com/paper/2209.00517/) (2022)
- [Continuous-Time Deep Glioma Growth Models](https://mlsanity.com/paper/2106.12917/) (2021)
- [Normative Modeling using Multimodal Variational Autoencoders to Identify Abnormal Brain Structural Patterns in Alzheimer Disease](https://mlsanity.com/paper/2110.04903/) (2021)
- [Promises and pitfalls of deep neural networks in neuroimaging-based psychiatric research](https://mlsanity.com/paper/2301.08525/) (2023)
- [Real-time Adaptation for Condition Monitoring Signal Prediction using Label-aware Neural Processes](https://mlsanity.com/paper/2403.16377/) (2024)
- [Analyzing heterogeneity in Alzheimer Disease using multimodal normative modeling on imaging-based ATN biomarkers](https://mlsanity.com/paper/2404.05748/) (2024)

## Abstract (arXiv)

Normative modeling has recently been introduced as a promising approach for modeling variation of neuroimaging measures across individuals in order to derive biomarkers of psychiatric disorders. Current implementations rely on Gaussian process regression, which provides coherent estimates of uncertainty needed for the method but also suffers from drawbacks including poor scaling to large datasets and a reliance on fixed parametric kernels. In this paper, we propose a deep normative modeling framework based on neural processes (NPs) to solve these problems. To achieve this, we define a stochastic process formulation for mixed-effect models and show how NPs can be adopted for spatially structured mixed-effect modeling of neuroimaging data. This enables us to learn optimal feature representations and covariance structure for the random-effect and noise via global latent variables. In this scheme, predictive uncertainty can be approximated by sampling from the distribution of these global latent variables. On a publicly available clinical fMRI dataset, we compare the novelty detection performance of multivariate normative models estimated by the proposed NP approach to a baseline multi-task Gaussian process regression approach and show substantial improvements for certain diagnostic problems.