BundleMAP : Anatomically localized classification, regression, and hypothesis testing in diffusion MRI

Diffusion MRI (dMRI) provides rich information on the white matter of the human brain, enabling insight into neurological disease, normal aging, and neuroplasticity. We present BundleMAP, an approach to extracting features from dMRI data that can be used for supervised classification, regression, and hypothesis testing. Our features are based on aggregating measurements along nerve fiber bundles, enabling visualization and anatomical interpretation. The main idea behind BundleMAP is to use the ISOMAP manifold learning technique to jointly parametrize nerve fiber bundles. We combine this idea with mechanisms for outlier removal and feature selection to obtain a practical machine learning pipeline. We demonstrate that it increases accuracy of disease detection and estimation of disease activity, and that it improves the power of statistical tests.

Schmidt-Wilcke, TobiasUniversity Hospital Bergmannsheil (author)
Sundgren, Pia C.Lund University,Lunds universitet,Diagnostisk radiologi, Lund,Sektion V,Institutionen för kliniska vetenskaper, Lund,Medicinska fakulteten,Neuroradiologi,Forskargrupper vid Lunds universitet,Diagnostic Radiology, (Lund),Section V,Department of Clinical Sciences, Lund,Faculty of Medicine,Neuroradiology,Lund University Research Groups,University of Michigan(Swepub:lu)med-psu (author)
Abbasloo, AminUniversity of Bonn (author)
Schölkopf, BernhardMax Planck Institute for Intelligent Systems (author)
Schultz, ThomasUniversity of Bonn (author)
University of BonnUniversity Hospital Bergmannsheil (creator_code:org_t)

By the author/editor: Khatami, Mohamma ...; Schmidt-Wilcke, ...; Sundgren, Pia C.; Abbasloo, Amin; Schölkopf, Bernh ...; Schultz, Thomas

About the subject

MEDICAL AND HEALTH SCIENCES: MEDICAL AND HEAL ...; and Clinical Medicin ...; and Radiology Nuclea ...

Kungliga biblioteket hanterar dina personuppgifter i enlighet med EU:s dataskyddsförordning (2018), GDPR. Läs mer om hur det funkar här.
Så här hanterar KB dina uppgifter vid användning av denna tjänst.