IGUANe: A 3D generalizable CycleGAN for multicenter harmonization of brain MR images

• Published in: Medical image analysis Vol. 99; p. 103388
• Main Authors: Roca, Vincent, Kuchcinski, Grégory, Pruvo, Jean-Pierre, Manouvriez, Dorian, Lopes, Renaud
• Format: Journal Article
• Language: English
• Published: Netherlands Elsevier B.V 01.01.2025
• Series: Med Image Anal
• Subjects: Adult; Aged; Alzheimer; Alzheimer Disease - diagnostic imaging; Brain - diagnostic imaging; Brain age; Brain MRI; Deep Learning; Harmonization; Humans; Image synthesis; Imaging, Three-Dimensional - methods; Life Sciences; Magnetic Resonance Imaging - methods; Middle Aged; Multisite; Image synthesis; Brain MRI; Alzheimer; Brain age; Harmonization; Multisite
• ISSN: 1361-8415; 1361-8423; 1361-8423
• DOI: 10.1016/j.media.2024.103388

In MRI studies, the aggregation of imaging data from multiple acquisition sites enhances sample size but may introduce site-related variabilities that hinder consistency in subsequent analyses. Deep learning methods for image translation have emerged as a solution for harmonizing MR images across sites. In this study, we introduce IGUANe (Image Generation with Unified Adversarial Networks), an original 3D model that leverages the strengths of domain translation and straightforward application of style transfer methods for multicenter brain MR image harmonization. IGUANe extends CycleGAN by integrating an arbitrary number of domains for training through a many-to-one architecture. The framework based on domain pairs enables the implementation of sampling strategies that prevent confusion between site-related and biological variabilities. During inference, the model can be applied to any image, even from an unknown acquisition site, making it a universal generator for harmonization. Trained on a dataset comprising T1-weighted images from 11 different scanners, IGUANe was evaluated on data from unseen sites. The assessments included the transformation of MR images with traveling subjects, the preservation of pairwise distances between MR images within domains, the evolution of volumetric patterns related to age and Alzheimer’s disease (AD), and the performance in age regression and patient classification tasks. Comparisons with other harmonization and normalization methods suggest that IGUANe better preserves individual information in MR images and is more suitable for maintaining and reinforcing variabilities related to age and AD. Future studies may further assess IGUANe in other multicenter contexts, either using the same model or retraining it for applications to different image modalities. Codes and the trained IGUANe model are available at https://github.com/RocaVincent/iguane_harmonization.git. [Display omitted] •We propose a 3D GAN for inter-site harmonization of T1-weighted brain MR images.•IGUANe extends CycleGAN and enables harmonization of images from unseen scanners.•IGUANe improves brain age prediction and the pattern of gray-matter atrophy.•IGUANe improves classification between healthy and Alzheimer participants.•IGUANe better enhances biological information than other harmonization methods.