Automatic Quality Control and Error Correction in MRI linear registration via a Residual Parameter Prediction Network for T1w MRI
- 1McGill University
Abstract
Errors in linear registration can propagate to downstream nonlinear registration and bias volumetric estimations, deformation-based morphometry (DBM) and voxel-based morphometry (VBM) analyses. Subtle linear registration errors are particularly challenging as they are difficult to detect and may not result in obvious failures in nonlinear registration but still affect downstream results. Therefore, accurate identification and correction of these errors are critical. In this study, we present the Residual Affine COefficient Optimization Network (RACOON), a framework designed to identify and correct linear registration errors in T1w MRI scans registered to the MNI-ICBM152 space. RACOON's correction module achieved a residual misalignment RMSE of 0.778 mm on synthetic dataset, comparable to the variability observed among repeated QC-passed registrations using the same pipeline. For the classification module, RACOON achieved a balanced accuracy of 76.8% and a precision of 74.4%, outperforming existing state-of-the-art methods. RACOON is open source and publicly available at https://github.com/ZhaojinChen/RACOON.
Related
- CIR-DDG: backbone-agnostic residual correction of antibody-antigen affinity changes with explicit cross-chain geometry
- MRFlow: Mechanism-Structured Residual Flow Matching for Virtual Cell Perturbation Prediction
- FedEpitope: Parameter-Efficient Federated Protein Language Models for Linear B-Cell Epitope Prediction
- An optimized machine learning approach for reliable agronomic parameter prediction in precision farming systems
- Going beyond labels: Semi-supervised learning for enzyme kinetic parameter prediction
BibTeX
@misc{chen2026automatic,
title = {{Automatic Quality Control and Error Correction in MRI linear registration via a Residual Parameter Prediction Network for T1w MRI}},
author = {Z. Chen and R. Moqadam and A. Metz and W. Adame Gonzalez and Y. Zeighami and M. Dadar},
howpublished = {bioRxiv},
year = {2026},
month = sep,
doi = {10.64898/2026.09.10.750693},
url = {https://www.biorxiv.org/content/10.64898/2026.09.10.750693v1},
note = {CC BY},
}
RIS
TY - UNPB
TI - Automatic Quality Control and Error Correction in MRI linear registration via a Residual Parameter Prediction Network for T1w MRI
AU - Z. Chen
AU - R. Moqadam
AU - A. Metz
AU - W. Adame Gonzalez
AU - Y. Zeighami
AU - M. Dadar
PY - 2026
DA - 2026/09/10
PB - bioRxiv
DO - 10.64898/2026.09.10.750693
UR - https://www.biorxiv.org/content/10.64898/2026.09.10.750693v1
AB - Errors in linear registration can propagate to downstream nonlinear registration and bias volumetric estimations, deformation-based morphometry (DBM) and voxel-based morphometry (VBM) analyses. Subtle linear registration errors are particularly challenging as they are difficult to detect and may not result in obvious failures in nonlinear registration but still affect downstream results. Therefore, accurate identification and correction of these errors are critical. In this study, we present the Residual Affine COefficient Optimization Network (RACOON), a framework designed to identify and correct linear registration errors in T1w MRI scans registered to the MNI-ICBM152 space. RACOON's correction module achieved a residual misalignment RMSE of 0.778 mm on synthetic dataset, comparable to the variability observed among repeated QC-passed registrations using the same pipeline. For the classification module, RACOON achieved a balanced accuracy of 76.8% and a precision of 74.4%, outperforming existing state-of-the-art methods. RACOON is open source and publicly available at https://github.com/ZhaojinChen/RACOON.
ER -