InstantGroup: Instant Template Generation for Scalable Group of Brain MRI Registration

TL;DR

InstantGroup introduces a fast, scalable framework for brain MRI template generation using VAE models, significantly reducing runtime while maintaining high quality and accuracy across different group sizes.

Contribution

The paper proposes a novel VAE-based framework with dual backbones and modules that enable rapid, scalable, and unbiased groupwise MRI template generation.

Findings

Generates templates within seconds for various group sizes.

Achieves superior registration accuracy compared to baselines.

Maintains template unbiasedness across experiments.

Abstract

Template generation is a critical step in groupwise image registration, which involves aligning a group of subjects into a common space. While existing methods can generate high-quality template images, they often incur substantial time costs or are limited by fixed group scales. In this paper, we present InstantGroup, an efficient groupwise template generation framework based on variational autoencoder (VAE) models that leverage latent representations' arithmetic properties, enabling scalability to groups of any size. InstantGroup features a Dual VAE backbone with shared-weight twin networks to handle pairs of inputs and incorporates a Displacement Inversion Module (DIM) to maintain template unbiasedness and a Subject-Template Alignment Module (STAM) to improve template quality and registration accuracy. Experiments on 3D brain MRI scans from the OASIS and ADNI datasets reveal that InstantGroup dramatically reduces runtime, generating templates within seconds for various group sizes while maintaining superior performance compared to state-of-the-art baselines on quantitative metrics, including unbiasedness and registration accuracy.