Tissue Probability Based Registration of Diffusion-Weighted Magnetic Resonance Imaging.

<bold>Background: </bold>Current registration methods for diffusion-MRI (dMRI) data mostly focus on white matter (WM) areas. Recently, dMRI has been employed for the characterization of gray matter (GM) microstructure, emphasizing the need for registration methods that consider all tissue types.<bold>Purpose: </bold>To develop a dMRI registration method based on GM, WM, and cerebrospinal fluid (CSF) tissue probability maps (TPMs).<bold>Study Type: </bold>Retrospective longitudinal study.<bold>Population: </bold>Thirty-two healthy participants were scanned twice (legacy data), divided into a training-set (n = 16) and a test-set (n = 16), and 35 randomly-selected participants from the Human Connectome Project.<bold>Field Strength/sequence: </bold>3.0T, diffusion-weighted spin-echo echo-planar sequence; T1-weighted spoiled gradient-recalled echo (SPGR) sequence.<bold>Assessment: </bold>A joint segmentation-registration approach was implemented: Diffusion tensor imaging (DTI) maps were classified into TPMs using machine-learning approaches. The resulting GM, WM, and CSF probability maps were employed as features for image alignment. Validation was performed on the test dataset and the HCP dataset. Registration performance was compared with current mainstream registration tools.<bold>Statistical Tests: </bold>Classifiers used for segmentation were evaluated using leave-one-out cross-validation and scored using Dice-index. Registration success was evaluated by voxel-wise variance, normalized cross-correlation of registered DTI maps, intra- and inter-subject similarity of the registered TPMs, and region-based intra-subject similarity using an anatomical atlas. One-way ANOVAs were performed to compare between our method and other registration tools.<bold>Results: </bold>The proposed method outperformed mainstream registration tools as indicated by lower voxel-wise variance of registered DTI maps (SD decrease of 10%) and higher similarity between registered TPMs within and across participants, for all tissue types (Dice increase of 0.1-0.2; P < 0.05).<bold>Data Conclusion: </bold>A joint segmentation-registration approach based on diffusion-driven TPMs provides a more accurate registration of dMRI data, outperforming other registration tools. Our method offers a "translation" of diffusion data into structural information in the form of TPMs, allowing to directly align diffusion and structural images.<bold>Level Of Evidence: </bold>1 Technical Efficacy Stage: 1. [ABSTRACT FROM AUTHOR]