CLIMB: Controllable Longitudinal Brain Image Generation using Mamba-based Latent Diffusion Model and Gaussian-aligned Autoencoder

TL;DR

CLIMB is a novel framework that models longitudinal brain MRI changes using a state space latent diffusion model and Gaussian-aligned autoencoder, enabling controllable and efficient brain image synthesis.

Contribution

It introduces a state space-based latent diffusion model with a Gaussian-aligned autoencoder for controllable, efficient longitudinal brain image generation incorporating multiple clinical variables.

Findings

Achieved a structural similarity index of 0.9433 on the ADNI dataset.

Reduced computational overhead compared to self-attention based models.

Effectively modeled brain structural evolution over time with multiple conditional variables.

Abstract

Latent diffusion models have emerged as powerful generative models in medical imaging, enabling the synthesis of high quality brain magnetic resonance imaging scans. In particular, predicting the evolution of a patients brain can aid in early intervention, prognosis, and treatment planning. In this study, we introduce CLIMB, Controllable Longitudinal brain Image generation via state space based latent diffusion model, an advanced framework for modeling temporal changes in brain structure. CLIMB is designed to model the structural evolution of the brain structure over time, utilizing a baseline MRI scan and its acquisition age as foundational inputs. Additionally, multiple conditional variables, including projected age, gender, disease status, genetic information, and brain structure volumes, are incorporated to enhance the temporal modeling of anatomical changes. Unlike existing LDM methods that rely on self attention modules, which effectively capture contextual information from input images but are computationally expensive, our approach leverages state space, a state space model architecture that substantially reduces computational overhead while preserving high-quality image synthesis. Furthermore, we introduce a Gaussian-aligned autoencoder that extracts latent representations conforming to prior distributions without the sampling noise inherent in conventional variational autoencoders. We train and evaluate our proposed model on the Alzheimers Disease Neuroimaging Initiative dataset, consisting of 6,306 MRI scans from 1,390 participants. By comparing generated images with real MRI scans, CLIMB achieves a structural similarity index of 0.9433, demonstrating notable improvements over existing methods.