Modeling the Neonatal Brain Development Using Implicit Neural Representations

TL;DR

This paper introduces an implicit neural representation model to predict neonatal brain development from MRI images, disentangling age and individual identity, and demonstrating efficient 3D data modeling.

Contribution

It proposes a novel INR-based approach with methods for disentangling age and identity, improving modeling of neonatal brain development.

Findings

The INR model accurately predicts 2D and 3D brain images over time.

Disentanglement methods effectively separate age from individual identity.

The approach is memory-efficient for 3D data modeling.

Abstract

The human brain undergoes rapid development during the third trimester of pregnancy. In this work, we model the neonatal development of the infant brain in this age range. As a basis, we use MR images of preterm- and term-birth neonates from the developing human connectome project (dHCP). We propose a neural network, specifically an implicit neural representation (INR), to predict 2D- and 3D images of varying time points. In order to model a subject-specific development process, it is necessary to disentangle the age from the subjects' identity in the latent space of the INR. We propose two methods, Subject Specific Latent Vectors (SSL) and Stochastic Global Latent Augmentation (SGLA), enabling this disentanglement. We perform an analysis of the results and compare our proposed model to an age-conditioned denoising diffusion model as a baseline. We also show that our method can be applied in a memory-efficient way, which is especially important for 3D data.