MICAFlow: Fast and robust MRI preprocessing bridging research neuroimaging and clinical practice.
Authors
Affiliations (3)
Affiliations (3)
- McConnell Brain Imaging Centre (BIC) and Centre of Excellence in Epilepsy at The Neuro (CEEN), Montreal Neurological Institute, McGill University, Montreal, Quebec, Canada.
- Neurophysiology Unit and Epilepsy Centre, AOU Modena, University of Modena and Reggio Emilia, Modena, Italy.
- Department of Neurosurgery, Beijing Tiantan Hospital, Capital Medical University, Beijing, China.
Abstract
MICAFlow is a fully automated MRI preprocessing pipeline designed to support translation of advanced neuroimaging workflows toward clinically feasible research and prospective clinical-evaluation settings. The pipeline emphasizes speed, robustness, and ease of use, focusing on structural and diffusion MRI. Key innovations include a Label-Augmented Modality-Agnostic Registration (LAMAReg) technique driven by deep learning segmentations for reliable cross-modal alignment, integration of state-of-the-art distortion corrections, and adherence to reproducible standards (Snakemake workflow, BIDSApp specifications). We describe the design of MICAFlow and evaluate its performance across heterogeneous datasets. First, accessibility: MICAFlow processes a multimodal MRI exam in minutes with clinically accessible hardware and without requiring GPU access, enabling same-day processing on clinically realistic hardware. Second, registration accuracy: LAMAReg achieves cutting-edge multimodal registration accuracy, yielding accurate alignment of diffusion MRI, FLAIR, and intra-subject T1-weighted images while remaining generally robust to common artifacts. Third, data reproducibility: Using identifiability, we show MICAFlow maintains consistent performance across diverse datasets, including subjects with pathology, and is closely comparable to contemporary pipelines. In sum, MICAFlow's combination of machine learning and efficient workflows produces research-grade preprocessing outputs with runtimes compatible with clinically oriented research workflows. This work demonstrates that advanced MRI preprocessing can be done fast and robustly, helping close the gap between research neuroimaging and future clinical evaluation of quantitative MRI techniques. The source code for MICAFlow is available here: https://github.com/MICA-MNI/MICAFlow, and for LAMAReg here: https://github.com/MICA-MNI/LAMAReg.