Title | Equivariant Spherical Deconvolution: Learning Sparse Orientation Distribution Functions from Spherical Data. |
Publication Type | Journal Article |
Year of Publication | 2021 |
Authors | Elaldi A, Dey N, Kim H, Gerig G |
Journal | Inf Process Med Imaging |
Volume | 12729 |
Pagination | 267-278 |
Date Published | 2021 Jun |
ISSN | 1011-2499 |
Abstract | We present a rotation-equivariant self-supervised learning framework for the sparse deconvolution of non-negative scalar fields on the unit sphere. Spherical signals with multiple peaks naturally arise in Diffusion MRI (dMRI), where each voxel consists of one or more signal sources corresponding to anisotropic tissue structure such as white matter. Due to spatial and spectral partial voluming, clinically-feasible dMRI struggles to resolve crossing-fiber white matter configurations, leading to extensive development in spherical deconvolution methodology to recover underlying fiber directions. However, these methods are typically linear and struggle with small crossing-angles and partial volume fraction estimation. In this work, we improve on current methodologies by nonlinearly estimating fiber structures via self-supervised spherical convolutional networks with guaranteed equivariance to spherical rotation. We perform validation via extensive single and multi-shell synthetic benchmarks demonstrating competitive performance against common base-lines. We further show improved downstream performance on fiber tractography measures on the Tractometer benchmark dataset. Finally, we show downstream improvements in terms of tractography and partial volume estimation on a multi-shell dataset of human subjects. |
DOI | 10.1007/978-3-030-78191-0_21 |
Alternate Journal | Inf Process Med Imaging |
PubMed ID | 37576905 |
PubMed Central ID | PMC10422024 |
Grant List | R01 ES032294 / ES / NIEHS NIH HHS / United States R01 HD088125 / HD / NICHD NIH HHS / United States R34 DA050287 / DA / NIDA NIH HHS / United States R01 MH122447 / MH / NIMH NIH HHS / United States R01 MH118362 / MH / NIMH NIH HHS / United States R01 HD055741 / HD / NICHD NIH HHS / United States R01 DA038215 / DA / NIDA NIH HHS / United States |