A deep learning-based multisite neuroimage harmonization framework established with a traveling-subject dataset

• Published in: NeuroImage (Orlando, Fla.) Vol. 257; p. 119297
• Main Authors: Tian, Dezheng, Zeng, Zilong, Sun, Xiaoyi, Tong, Qiqi, Li, Huanjie, He, Hongjian, Gao, Jia-Hong, He, Yong, Xia, Mingrui
• Format: Journal Article
• Language: English
• Published: United States Elsevier Inc 15.08.2022; Elsevier Limited; Elsevier
• Subjects: Big data; Brain mapping; Brain research; Cognitive ability; Convolutional network; Datasets; Deep learning; Gray matter; Machine learning; Magnetic resonance imaging; Medical imaging; Multicenter; Neurodevelopmental disorders; Neuroimaging; Site effect; Structure-function relationships; Substantia grisea; Convolutional network; Big data; Multicenter; Gray matter; Site effect; Machine learning
• ISSN: 1053-8119; 1095-9572; 1095-9572
• DOI: 10.1016/j.neuroimage.2022.119297

•A DL-based harmonization framework was established with a traveling subject dataset.•Site and brain factors were learned by the proposed framework from gray matter volumes.•Better harmonization performance was achieved relative to that of statistics-based methods.•The proposed harmonization method offered flexible expandability for adding new sites. The accumulation of multisite large-sample MRI datasets collected during large brain research projects in the last decade has provided critical resources for understanding the neurobiological mechanisms underlying cognitive functions and brain disorders. However, the significant site effects observed in imaging data and their derived structural and functional features have prevented the derivation of consistent findings across multiple studies. The development of harmonization methods that can effectively eliminate complex site effects while maintaining biological characteristics in neuroimaging data has become a vital and urgent requirement for multisite imaging studies. Here, we propose a deep learning-based framework to harmonize imaging data obtained from pairs of sites, in which site factors and brain features can be disentangled and encoded. We trained the proposed framework with a publicly available traveling subject dataset from the Strategic Research Program for Brain Sciences (SRPBS) and harmonized the gray matter volume maps derived from eight source sites to a target site. The proposed framework significantly eliminated intersite differences in gray matter volumes. The embedded encoders successfully captured both the abstract textures of site factors and the concrete brain features. Moreover, the proposed framework exhibited outstanding performance relative to conventional statistical harmonization methods in terms of site effect removal, data distribution homogenization, and intrasubject similarity improvement. Finally, the proposed harmonization network provided fixable expandability, through which new sites could be linked to the target site via indirect schema without retraining the whole model. Together, the proposed method offers a powerful and interpretable deep learning-based harmonization framework for multisite neuroimaging data that can enhance reliability and reproducibility in multisite studies regarding brain development and brain disorders. [Display omitted]