Stroke subtype classification by geometrical descriptors of lesion shape

Standard

Stroke subtype classification by geometrical descriptors of lesion shape. / Cheng, Bastian; Knaack, Christian; Forkert, Nils Daniel; Schnabel, Renate; Gerloff, Christian; Thomalla, Götz.

In: PLOS ONE, Vol. 12, No. 12, 2017, p. e0185063.

Research output: SCORING: Contribution to journalSCORING: Journal articleResearchpeer-review

Harvard

APA

Vancouver

Bibtex

@article{57c2a26a302e430f8254222020964f58,
title = "Stroke subtype classification by geometrical descriptors of lesion shape",
abstract = "BACKGROUND AND PURPOSE: Inference of etiology from lesion pattern in acute magnetic resonance imaging is valuable for management and prognosis of acute stroke patients. This study aims to assess the value of three-dimensional geometrical lesion-shape descriptors for stroke-subtype classification, specifically regarding stroke of cardioembolic origin.METHODS: Stroke Etiology was classified according to ASCOD in retrospectively selected patients with acute stroke. Lesions were segmented on diffusion-weighed datasets, and descriptors of lesion shape quantified: surface area, sphericity, bounding box volume, and ratio between bounding box and lesion volume. Morphological measures were compared between stroke subtypes classified by ASCOD and between patients with embolic stroke of cardiac and non-cardiac source.RESULTS: 150 patients (mean age 77 years; 95% CI, 65-80 years; median NIHSS 6, range 0-22) were included. Group comparison of lesion shape measures demonstrated that lesions caused by small-vessel disease were smaller and more spherical compared to other stroke subtypes. No significant differences of morphological measures were detected between patients with cardioembolic and non-cardioembolic stroke.CONCLUSION: Stroke lesions caused by small vessel disease can be distinguished from other stroke lesions based on distinctive morphological properties. However, within the group of embolic strokes, etiology could not be inferred from the morphology measures studied in our analysis.",
keywords = "Aged, Aged, 80 and over, Female, Humans, Magnetic Resonance Imaging, Male, Middle Aged, Retrospective Studies, Stroke, Journal Article",
author = "Bastian Cheng and Christian Knaack and Forkert, {Nils Daniel} and Renate Schnabel and Christian Gerloff and G{\"o}tz Thomalla",
year = "2017",
doi = "10.1371/journal.pone.0185063",
language = "English",
volume = "12",
pages = "e0185063",
journal = "PLOS ONE",
issn = "1932-6203",
publisher = "Public Library of Science",
number = "12",

}

RIS

TY - JOUR

T1 - Stroke subtype classification by geometrical descriptors of lesion shape

AU - Cheng, Bastian

AU - Knaack, Christian

AU - Forkert, Nils Daniel

AU - Schnabel, Renate

AU - Gerloff, Christian

AU - Thomalla, Götz

PY - 2017

Y1 - 2017

N2 - BACKGROUND AND PURPOSE: Inference of etiology from lesion pattern in acute magnetic resonance imaging is valuable for management and prognosis of acute stroke patients. This study aims to assess the value of three-dimensional geometrical lesion-shape descriptors for stroke-subtype classification, specifically regarding stroke of cardioembolic origin.METHODS: Stroke Etiology was classified according to ASCOD in retrospectively selected patients with acute stroke. Lesions were segmented on diffusion-weighed datasets, and descriptors of lesion shape quantified: surface area, sphericity, bounding box volume, and ratio between bounding box and lesion volume. Morphological measures were compared between stroke subtypes classified by ASCOD and between patients with embolic stroke of cardiac and non-cardiac source.RESULTS: 150 patients (mean age 77 years; 95% CI, 65-80 years; median NIHSS 6, range 0-22) were included. Group comparison of lesion shape measures demonstrated that lesions caused by small-vessel disease were smaller and more spherical compared to other stroke subtypes. No significant differences of morphological measures were detected between patients with cardioembolic and non-cardioembolic stroke.CONCLUSION: Stroke lesions caused by small vessel disease can be distinguished from other stroke lesions based on distinctive morphological properties. However, within the group of embolic strokes, etiology could not be inferred from the morphology measures studied in our analysis.

AB - BACKGROUND AND PURPOSE: Inference of etiology from lesion pattern in acute magnetic resonance imaging is valuable for management and prognosis of acute stroke patients. This study aims to assess the value of three-dimensional geometrical lesion-shape descriptors for stroke-subtype classification, specifically regarding stroke of cardioembolic origin.METHODS: Stroke Etiology was classified according to ASCOD in retrospectively selected patients with acute stroke. Lesions were segmented on diffusion-weighed datasets, and descriptors of lesion shape quantified: surface area, sphericity, bounding box volume, and ratio between bounding box and lesion volume. Morphological measures were compared between stroke subtypes classified by ASCOD and between patients with embolic stroke of cardiac and non-cardiac source.RESULTS: 150 patients (mean age 77 years; 95% CI, 65-80 years; median NIHSS 6, range 0-22) were included. Group comparison of lesion shape measures demonstrated that lesions caused by small-vessel disease were smaller and more spherical compared to other stroke subtypes. No significant differences of morphological measures were detected between patients with cardioembolic and non-cardioembolic stroke.CONCLUSION: Stroke lesions caused by small vessel disease can be distinguished from other stroke lesions based on distinctive morphological properties. However, within the group of embolic strokes, etiology could not be inferred from the morphology measures studied in our analysis.

KW - Aged

KW - Aged, 80 and over

KW - Female

KW - Humans

KW - Magnetic Resonance Imaging

KW - Male

KW - Middle Aged

KW - Retrospective Studies

KW - Stroke

KW - Journal Article

U2 - 10.1371/journal.pone.0185063

DO - 10.1371/journal.pone.0185063

M3 - SCORING: Journal article

C2 - 29216218

VL - 12

SP - e0185063

JO - PLOS ONE

JF - PLOS ONE

SN - 1932-6203

IS - 12

ER -