.png){kind=icon}
.png){kind=icon}
Return
Scanner-agnostic MRI harmonization via SSIM-guided disentanglement
.png){kind=icon}
OA
AI
L
L
F
T
DOI：10.3389/frai.2026.1813948.png)
.png){kind=icon}
Original request for help.png){kind=icon}
Share.png){kind=icon}
Save
Abstract
En 中文
IntroductionThe variability introduced by differences in MRI scanner models; acquisition protocols; and imaging sites hinders consistent analysis and generalizability across multicenter studies.MethodsWe present a novel image-based harmonization framework for 3D T1-weighted brain MRI; which disentangles anatomical content from scanner- and site-specific variations. The model incorporates a differentiable loss based on the Structural Similarity Index Measure (SSIM) to preserve biologically meaningful features while reducing inter-site variability. This formulation allows luminance; contrast; and structural components to be modeled separately during optimization. Training and validation were performed on multiple publicly available datasets spanning diverse scanners and sites; with testing on both healthy individuals and populations with pathological conditions. The proposed approach was evaluated across multiple target settings; including scanner-site-specific targets and a style-agnostic target; and compared with representative image-based harmonization benchmark methods.ResultsAcross these target settings; harmonization produced consistent and high-quality outputs. Visual comparisons; voxel intensity distributions; and SSIM-based metrics demonstrated that harmonized images achieved improved alignment across acquisition settings while preserving anatomical fidelity. In the style-agnostic setting; within-subject original–harmonized comparisons showed high anatomical preservation; with the structural component of SSIM reaching 0.975 ± 0.007. Appearance consistency also improved; with Wasserstein distances between mean voxel intensity distributions decreasing from 8.45 ± 5.35 before harmonization to 1.77 ± 0.62; and luminance similarity increasing from 0.952 ± 0.037 to 0.982 ± 0.017. Downstream analyses further confirmed the effectiveness of the proposed approach. For brain age prediction; mean absolute error decreased from 4.08 ± 1.16 to 2.81 ± 0.55 years following style-agnostic harmonization. For Alzheimer's disease classification; the area under the ROC curve improved from 0.857 ± 0.038 to 0.899 ± 0.024. Compared with the considered benchmark methods; the proposed framework showed stronger image-level harmonization and more consistent downstream improvements under the adopted evaluation protocol.DiscussionOverall; the proposed framework enhances cross-site image consistency; preserves anatomically relevant information; and improves downstream predictive performance; providing a robust and generalizable solution for large-scale multicenter neuroimaging studies.
Keywords:
magnetic resonance imaging
disentanglement
Alzheimer's disease classification
brain age prediction
I2I translation
image harmonization
SSIM-based loss
Journal
F
IF:
4.7
Papers:
2.2K
Citations:
4.4K
Organization
Cited Papers