Research ExplorerPublicationsLow Rank and Sparse Matrix Decomposition as Stroke Segmentat...

Low Rank and Sparse Matrix Decomposition as Stroke Segmentation Prior: Useful or Not? A Random Forest-Based Evaluation Study

Standard

Low Rank and Sparse Matrix Decomposition as Stroke Segmentation Prior: Useful or Not? A Random Forest-Based Evaluation Study. / Werner, Rene; Schetelig, Daniel; Sothmann, Thilo; Mücke, Eike ; Wilms, Matthias; Cheng, Bastian; Forkert, Nils Daniel.

Bildverarbeitung für die Medizin 2017: Algorithmen - Systeme - Anwendungen. ed. / Klaus Hermann Maier-Hein; Thomas Deserno; Heinz Handels; Thomas Tolxdorff. 1. ed. Springer, 2017. p. 161-166 (Informatik aktuell).

Research output: SCORING: Contribution to book/anthology › SCORING: Contribution to collected editions/anthologies › Research › peer-review

Harvard

Werner, R, Schetelig, D, Sothmann, T, Mücke, E, Wilms, M, Cheng, B & Forkert, ND 2017, Low Rank and Sparse Matrix Decomposition as Stroke Segmentation Prior: Useful or Not? A Random Forest-Based Evaluation Study. in KH Maier-Hein, T Deserno, H Handels & T Tolxdorff (eds), Bildverarbeitung für die Medizin 2017: Algorithmen - Systeme - Anwendungen. 1 edn, Informatik aktuell, Springer, pp. 161-166. https://doi.org/10.1007/978-3-662-54345-0_39

APA

Werner, R., Schetelig, D., Sothmann, T., Mücke, E., Wilms, M., Cheng, B., & Forkert, N. D. (2017). Low Rank and Sparse Matrix Decomposition as Stroke Segmentation Prior: Useful or Not? A Random Forest-Based Evaluation Study. In K. H. Maier-Hein, T. Deserno, H. Handels, & T. Tolxdorff (Eds.), Bildverarbeitung für die Medizin 2017: Algorithmen - Systeme - Anwendungen (1 ed., pp. 161-166). (Informatik aktuell). Springer. https://doi.org/10.1007/978-3-662-54345-0_39

Vancouver

Werner R, Schetelig D, Sothmann T, Mücke E, Wilms M, Cheng B et al. Low Rank and Sparse Matrix Decomposition as Stroke Segmentation Prior: Useful or Not? A Random Forest-Based Evaluation Study. In Maier-Hein KH, Deserno T, Handels H, Tolxdorff T, editors, Bildverarbeitung für die Medizin 2017: Algorithmen - Systeme - Anwendungen. 1 ed. Springer. 2017. p. 161-166. (Informatik aktuell). https://doi.org/10.1007/978-3-662-54345-0_39

Bibtex

@inbook{0b00e53aec70410fa75f1fe0be8a9860,
title = "Low Rank and Sparse Matrix Decomposition as Stroke Segmentation Prior: Useful or Not? A Random Forest-Based Evaluation Study",
abstract = "Manual ischemic stroke lesion segmentation in MR image data is a time-consuming task subject to inter-rater variability. Reliable automated lesion segmentation is of high interest for clinical trials and research in ischemic stroke. However, recent segmentation challenges (e.g. ISLES 2015) illustrate that current state-of-the-art approaches still lack accuracy and ischemic stroke segmentation remains a complicated problem. Within this context, low rank-&-sparse matrix decomposition (also known as robust PCA, RPCA) and RPCA-based non-linear subject-toatlas registration could provide valuable segmentation prior information. The aim of this study is to evaluate the suitability of RPCA and RPCAbased registration for ischemic stroke segmentation in follow-up FLAIR MR data sets. Building on a top-ranked segmentation approach of ISLES 2015, the performance of RPCA sparse component image information as random forest (RF) feature is evaluated. A comprehensive feature-byfeature comparison of the segmentation performance with and without RPCA sparse component information as RF feature illustrate the potential of low rank-&-sparse decomposition to improve stroke segmentation.",
author = "Rene Werner and Daniel Schetelig and Thilo Sothmann and Eike M{\"u}cke and Matthias Wilms and Bastian Cheng and Forkert, {Nils Daniel}",
year = "2017",
doi = "10.1007/978-3-662-54345-0_39",
language = "English",
isbn = "978-3-662-54344-3",
series = "Informatik aktuell",
publisher = "Springer",
pages = "161--166",
editor = "Maier-Hein, {Klaus Hermann} and Thomas Deserno and Heinz Handels and Thomas Tolxdorff",
booktitle = "Bildverarbeitung f{\"u}r die Medizin 2017",
address = "Germany",
edition = "1",

}

RIS

TY - CHAP

T1 - Low Rank and Sparse Matrix Decomposition as Stroke Segmentation Prior: Useful or Not? A Random Forest-Based Evaluation Study

AU - Werner, Rene

AU - Schetelig, Daniel

AU - Sothmann, Thilo

AU - Mücke, Eike

AU - Wilms, Matthias

AU - Cheng, Bastian

AU - Forkert, Nils Daniel

PY - 2017

Y1 - 2017

N2 - Manual ischemic stroke lesion segmentation in MR image data is a time-consuming task subject to inter-rater variability. Reliable automated lesion segmentation is of high interest for clinical trials and research in ischemic stroke. However, recent segmentation challenges (e.g. ISLES 2015) illustrate that current state-of-the-art approaches still lack accuracy and ischemic stroke segmentation remains a complicated problem. Within this context, low rank-&-sparse matrix decomposition (also known as robust PCA, RPCA) and RPCA-based non-linear subject-toatlas registration could provide valuable segmentation prior information. The aim of this study is to evaluate the suitability of RPCA and RPCAbased registration for ischemic stroke segmentation in follow-up FLAIR MR data sets. Building on a top-ranked segmentation approach of ISLES 2015, the performance of RPCA sparse component image information as random forest (RF) feature is evaluated. A comprehensive feature-byfeature comparison of the segmentation performance with and without RPCA sparse component information as RF feature illustrate the potential of low rank-&-sparse decomposition to improve stroke segmentation.

AB - Manual ischemic stroke lesion segmentation in MR image data is a time-consuming task subject to inter-rater variability. Reliable automated lesion segmentation is of high interest for clinical trials and research in ischemic stroke. However, recent segmentation challenges (e.g. ISLES 2015) illustrate that current state-of-the-art approaches still lack accuracy and ischemic stroke segmentation remains a complicated problem. Within this context, low rank-&-sparse matrix decomposition (also known as robust PCA, RPCA) and RPCA-based non-linear subject-toatlas registration could provide valuable segmentation prior information. The aim of this study is to evaluate the suitability of RPCA and RPCAbased registration for ischemic stroke segmentation in follow-up FLAIR MR data sets. Building on a top-ranked segmentation approach of ISLES 2015, the performance of RPCA sparse component image information as random forest (RF) feature is evaluated. A comprehensive feature-byfeature comparison of the segmentation performance with and without RPCA sparse component information as RF feature illustrate the potential of low rank-&-sparse decomposition to improve stroke segmentation.

U2 - 10.1007/978-3-662-54345-0_39

DO - 10.1007/978-3-662-54345-0_39

M3 - SCORING: Contribution to collected editions/anthologies

SN - 978-3-662-54344-3

T3 - Informatik aktuell

SP - 161

EP - 166

BT - Bildverarbeitung für die Medizin 2017

A2 - Maier-Hein, Klaus Hermann

A2 - Deserno, Thomas

A2 - Handels, Heinz

A2 - Tolxdorff, Thomas

PB - Springer

ER -