Diffusion based multi-domain neuroimaging harmonization method with preservation of anatomical details

TL;DR

This paper introduces a diffusion model-based neuroimaging harmonization method that effectively minimizes batch effects across multiple domains while preserving anatomical details, outperforming GAN-based approaches in quality and consistency.

Contribution

The study demonstrates the superiority of diffusion models over GANs for multi-domain neuroimaging harmonization, with enhanced anatomical preservation and broader domain applicability.

Findings

Diffusion model achieves better harmonization than GANs.

The method preserves anatomical details effectively.

Improves consistency in PVS segmentation after harmonization.

Abstract

Multi-center neuroimaging studies face technical variability due to batch differences across sites, which potentially hinders data aggregation and impacts study reliability.Recent efforts in neuroimaging harmonization have aimed to minimize these technical gaps and reduce technical variability across batches. While Generative Adversarial Networks (GAN) has been a prominent method for addressing image harmonization tasks, GAN-harmonized images suffer from artifacts or anatomical distortions. Given the advancements of denoising diffusion probabilistic model which produces high-fidelity images, we have assessed the efficacy of the diffusion model for neuroimaging harmonization. we have demonstrated the diffusion model's superior capability in harmonizing images from multiple domains, while GAN-based methods are limited to harmonizing images between two domains per model. Our experiments highlight that the learned domain invariant anatomical condition reinforces the model to accurately preserve the anatomical details while differentiating batch differences at each diffusion step. Our proposed method has been tested on two public neuroimaging dataset ADNI1 and ABIDE II, yielding harmonization results with consistent anatomy preservation and superior FID score compared to the GAN-based methods. We have conducted multiple analysis including extensive quantitative and qualitative evaluations against the baseline models, ablation study showcasing the benefits of the learned conditions, and improvements in the consistency of perivascular spaces (PVS) segmentation through harmonization.