LAMAR | Label Augmented Modality Agnostic Registration

We introduced a novel approach for more accurate registration between modalities. This python based workflow combines deep learning-based segmentation and numerical solutions (ANTs) to generate precise warpfields, even for modalities with low signal-to-noise ratio, signal dropout and strong geometric distortions, such as diffusion MRI and fMRI acquisitions.

Installation Steps

Prerequisites

• Python 3.9, 3.10, or 3.11

pip install lamar

References

1. Billot, Benjamin, et al. "Robust machine learning segmentation for large-scale analysis of heterogeneous clinical brain MRI datasets." Proceedings of the National Academy of Sciences 120.9 (2023): e2216399120.
2. Avants, Brian B., Nick Tustison, and Gang Song. "Advanced normalization tools (ANTS)." Insight j 2.365 (2009): 1-35.