Cargando…

Segmentation of acute stroke infarct core using image-level labels on CT-angiography

Acute ischemic stroke is a leading cause of death and disability in the world. Treatment decisions, especially around emergent revascularization procedures, rely heavily on size and location of the infarct core. Currently, accurate assessment of this measure is challenging. While MRI-DWI is consider...

Descripción completa

Detalles Bibliográficos
Autores principales: Giancardo, Luca, Niktabe, Arash, Ocasio, Laura, Abdelkhaleq, Rania, Salazar-Marioni, Sergio, Sheth, Sunil A.
Formato: Online Artículo Texto
Lenguaje:English
Publicado: Elsevier 2023
Materias:
Acceso en línea:https://www.ncbi.nlm.nih.gov/pmc/articles/PMC10011814/
https://www.ncbi.nlm.nih.gov/pubmed/36893661
http://dx.doi.org/10.1016/j.nicl.2023.103362
_version_ 1784906481960747008
author Giancardo, Luca
Niktabe, Arash
Ocasio, Laura
Abdelkhaleq, Rania
Salazar-Marioni, Sergio
Sheth, Sunil A.
author_facet Giancardo, Luca
Niktabe, Arash
Ocasio, Laura
Abdelkhaleq, Rania
Salazar-Marioni, Sergio
Sheth, Sunil A.
author_sort Giancardo, Luca
collection PubMed
description Acute ischemic stroke is a leading cause of death and disability in the world. Treatment decisions, especially around emergent revascularization procedures, rely heavily on size and location of the infarct core. Currently, accurate assessment of this measure is challenging. While MRI-DWI is considered the gold standard, its availability is limited for most patients suffering from stroke. Another well-studied imaging modality is CT-Perfusion (CTP) which is much more common than MRI-DWI in acute stroke care, but not as precise as MRI-DWI, and it is still unavailable in many stroke hospitals. A method to determine infarct core using CT-Angiography (CTA), a much more available imaging modality albeit with significantly less contrast in stroke core area than CTP or MRI-DWI, would enable significantly better treatment decisions for stroke patients throughout the world. Existing deep-learning-based approaches for stroke core estimation have to face the trade-off between voxel-level segmentation / image-level labels and the difficulty of obtaining large enough samples of high-quality DWI images. The former occurs when algorithms can either output voxel-level labeling which is more informative but requires a significant effort by annotators, or image-level labels that allow for much simpler labeling of the images but results in less informative and interpretable output; the latter is a common issue that forces training either on small training sets using DWI as the target or larger, but noisier, dataset using CT-Perfusion (CTP) as the target. In this work, we present a deep learning approach including a new weighted gradient-based approach to obtain stroke core segmentation with image-level labeling, specifically the size of the acute stroke core volume. Additionally, this strategy allows us to train using labels derived from CTP estimations. We find that the proposed approach outperforms segmentation approaches trained on voxel-level data and the CTP estimation themselves.
format Online
Article
Text
id pubmed-10011814
institution National Center for Biotechnology Information
language English
publishDate 2023
publisher Elsevier
record_format MEDLINE/PubMed
spelling pubmed-100118142023-03-15 Segmentation of acute stroke infarct core using image-level labels on CT-angiography Giancardo, Luca Niktabe, Arash Ocasio, Laura Abdelkhaleq, Rania Salazar-Marioni, Sergio Sheth, Sunil A. Neuroimage Clin Regular Article Acute ischemic stroke is a leading cause of death and disability in the world. Treatment decisions, especially around emergent revascularization procedures, rely heavily on size and location of the infarct core. Currently, accurate assessment of this measure is challenging. While MRI-DWI is considered the gold standard, its availability is limited for most patients suffering from stroke. Another well-studied imaging modality is CT-Perfusion (CTP) which is much more common than MRI-DWI in acute stroke care, but not as precise as MRI-DWI, and it is still unavailable in many stroke hospitals. A method to determine infarct core using CT-Angiography (CTA), a much more available imaging modality albeit with significantly less contrast in stroke core area than CTP or MRI-DWI, would enable significantly better treatment decisions for stroke patients throughout the world. Existing deep-learning-based approaches for stroke core estimation have to face the trade-off between voxel-level segmentation / image-level labels and the difficulty of obtaining large enough samples of high-quality DWI images. The former occurs when algorithms can either output voxel-level labeling which is more informative but requires a significant effort by annotators, or image-level labels that allow for much simpler labeling of the images but results in less informative and interpretable output; the latter is a common issue that forces training either on small training sets using DWI as the target or larger, but noisier, dataset using CT-Perfusion (CTP) as the target. In this work, we present a deep learning approach including a new weighted gradient-based approach to obtain stroke core segmentation with image-level labeling, specifically the size of the acute stroke core volume. Additionally, this strategy allows us to train using labels derived from CTP estimations. We find that the proposed approach outperforms segmentation approaches trained on voxel-level data and the CTP estimation themselves. Elsevier 2023-02-27 /pmc/articles/PMC10011814/ /pubmed/36893661 http://dx.doi.org/10.1016/j.nicl.2023.103362 Text en © 2023 The Authors https://creativecommons.org/licenses/by-nc-nd/4.0/This is an open access article under the CC BY-NC-ND license (http://creativecommons.org/licenses/by-nc-nd/4.0/).
spellingShingle Regular Article
Giancardo, Luca
Niktabe, Arash
Ocasio, Laura
Abdelkhaleq, Rania
Salazar-Marioni, Sergio
Sheth, Sunil A.
Segmentation of acute stroke infarct core using image-level labels on CT-angiography
title Segmentation of acute stroke infarct core using image-level labels on CT-angiography
title_full Segmentation of acute stroke infarct core using image-level labels on CT-angiography
title_fullStr Segmentation of acute stroke infarct core using image-level labels on CT-angiography
title_full_unstemmed Segmentation of acute stroke infarct core using image-level labels on CT-angiography
title_short Segmentation of acute stroke infarct core using image-level labels on CT-angiography
title_sort segmentation of acute stroke infarct core using image-level labels on ct-angiography
topic Regular Article
url https://www.ncbi.nlm.nih.gov/pmc/articles/PMC10011814/
https://www.ncbi.nlm.nih.gov/pubmed/36893661
http://dx.doi.org/10.1016/j.nicl.2023.103362
work_keys_str_mv AT giancardoluca segmentationofacutestrokeinfarctcoreusingimagelevellabelsonctangiography
AT niktabearash segmentationofacutestrokeinfarctcoreusingimagelevellabelsonctangiography
AT ocasiolaura segmentationofacutestrokeinfarctcoreusingimagelevellabelsonctangiography
AT abdelkhaleqrania segmentationofacutestrokeinfarctcoreusingimagelevellabelsonctangiography
AT salazarmarionisergio segmentationofacutestrokeinfarctcoreusingimagelevellabelsonctangiography
AT shethsunila segmentationofacutestrokeinfarctcoreusingimagelevellabelsonctangiography