4th order tensors for multi-fiber resolution and segmentation in white matter

Kód výsledku v IS VaVaI

<a href="https://www.isvavai.cz/riv?ss=detail&h=RIV%2F00216224%3A14310%2F20%3A00114778" target="_blank" >RIV/00216224:14310/20:00114778 - isvavai.cz</a>

Nalezeny alternativní kódy

RIV/68407700:21230/20:00354559

Výsledek na webu

<a href="https://dl.acm.org/doi/10.1145/3444884.3444892" target="_blank" >https://dl.acm.org/doi/10.1145/3444884.3444892</a>

DOI - Digital Object Identifier

<a href="http://dx.doi.org/10.1145/3444884.3444892" target="_blank" >10.1145/3444884.3444892</a>

Jazyk výsledku

angličtina

Název v původním jazyce

4th order tensors for multi-fiber resolution and segmentation in white matter

Popis výsledku v původním jazyce

Since its inception, DTI modality has become an essential tool in the clinical scenario. In principle, it is rooted in the emergence of symmetric positive definite (SPD) second-order tensors modelling the difusion. The inability of DTI to model regions of white matter with fibers crossing/merging leads to the emergence of higher order tensors. In this work, we compare various approaches how to use 4th order tensors to model such regions. There are three different projections of these 3D 4th order tensors to the 2nd order tensors of dimensions either three or six. Two of these projections are consistent in terms of preserving mean diffusivity and isometry. The images of all three projections are SPD, so they belong to a Riemannian symmetric space. Following previous work of the authors, we use the standard k-means segmentation method after dimension reduction with affinity matrix based on reasonable similarity measures, with the goal to compare the various projections to 2nd order tensors. We are using the natural affine and log-Euclidean (LogE) metrics. The segmentation of curved structures and fiber crossing regions is performed under the presence of several levels of Rician noise. The experiments provide evidence that 3D 2nd order reduction works much better than the 6D one, while diagonal components (DC) projections are able to reveal the maximum diffusion direction.

Název v anglickém jazyce

4th order tensors for multi-fiber resolution and segmentation in white matter

Popis výsledku anglicky

Since its inception, DTI modality has become an essential tool in the clinical scenario. In principle, it is rooted in the emergence of symmetric positive definite (SPD) second-order tensors modelling the difusion. The inability of DTI to model regions of white matter with fibers crossing/merging leads to the emergence of higher order tensors. In this work, we compare various approaches how to use 4th order tensors to model such regions. There are three different projections of these 3D 4th order tensors to the 2nd order tensors of dimensions either three or six. Two of these projections are consistent in terms of preserving mean diffusivity and isometry. The images of all three projections are SPD, so they belong to a Riemannian symmetric space. Following previous work of the authors, we use the standard k-means segmentation method after dimension reduction with affinity matrix based on reasonable similarity measures, with the goal to compare the various projections to 2nd order tensors. We are using the natural affine and log-Euclidean (LogE) metrics. The segmentation of curved structures and fiber crossing regions is performed under the presence of several levels of Rician noise. The experiments provide evidence that 3D 2nd order reduction works much better than the 6D one, while diagonal components (DC) projections are able to reveal the maximum diffusion direction.

Druh

D - Stať ve sborníku

CEP obor

—

OECD FORD obor

10201 - Computer sciences, information science, bioinformathics (hardware development to be 2.2, social aspect to be 5.8)

Projekt

Výsledek vznikl pri realizaci vícero projektů. Více informací v záložce Projekty.

Návaznosti

P - Projekt vyzkumu a vyvoje financovany z verejnych zdroju (s odkazem do CEP)

Rok uplatnění

2020

Kód důvěrnosti údajů

S - Úplné a pravdivé údaje o projektu nepodléhají ochraně podle zvláštních právních předpisů

Název statě ve sborníku

2020 7th International Conference on Biomedical and Bioinformatics Engineering (ICBBE ’20)

ISBN

9781450388221

ISSN

—

e-ISSN

—

Počet stran výsledku

7

Strana od-do

36-42

Název nakladatele

Association for Computing Machinery

Místo vydání

New York

Místo konání akce

Kyoto

Datum konání akce

6. 11. 2020

Typ akce podle státní příslušnosti

CST - Celostátní akce

Kód UT WoS článku

—