Cargando…

Automatic segmentation of cerebral infarcts in follow-up computed tomography images with convolutional neural networks

BACKGROUND AND PURPOSE: Infarct volume is a valuable outcome measure in treatment trials of acute ischemic stroke and is strongly associated with functional outcome. Its manual volumetric assessment is, however, too demanding to be implemented in clinical practice. OBJECTIVE: To assess the value of...

Descripción completa

Detalles Bibliográficos
Autores principales: Sales Barros, Renan, Tolhuisen, Manon L, Boers, Anna MM, Jansen, Ivo, Ponomareva, Elena, Dippel, Diederik W J, van der Lugt, Aad, van Oostenbrugge, Robert J, van Zwam, Wim H, Berkhemer, Olvert A, Goyal, Mayank, Demchuk, Andrew M, Menon, Bijoy K, Mitchell, Peter, Hill, Michael D, Jovin, Tudor G, Davalos, Antoni, Campbell, Bruce C V, Saver, Jeffrey L, Roos, Yvo B W E M, Muir, Keith W., White, Phil, Bracard, Serge, Guillemin, Francis, Olabarriaga, Silvia Delgado, Majoie, Charles B L M, Marquering, Henk A
Formato: Online Artículo Texto
Lenguaje:English
Publicado: BMJ Publishing Group 2020
Materias:
Acceso en línea:https://www.ncbi.nlm.nih.gov/pmc/articles/PMC7476369/
https://www.ncbi.nlm.nih.gov/pubmed/31871069
http://dx.doi.org/10.1136/neurintsurg-2019-015471
_version_ 1783579693004357632
author Sales Barros, Renan
Tolhuisen, Manon L
Boers, Anna MM
Jansen, Ivo
Ponomareva, Elena
Dippel, Diederik W J
van der Lugt, Aad
van Oostenbrugge, Robert J
van Zwam, Wim H
Berkhemer, Olvert A
Goyal, Mayank
Demchuk, Andrew M
Menon, Bijoy K
Mitchell, Peter
Hill, Michael D
Jovin, Tudor G
Davalos, Antoni
Campbell, Bruce C V
Saver, Jeffrey L
Roos, Yvo B W E M
Muir, Keith W.
White, Phil
Bracard, Serge
Guillemin, Francis
Olabarriaga, Silvia Delgado
Majoie, Charles B L M
Marquering, Henk A
author_facet Sales Barros, Renan
Tolhuisen, Manon L
Boers, Anna MM
Jansen, Ivo
Ponomareva, Elena
Dippel, Diederik W J
van der Lugt, Aad
van Oostenbrugge, Robert J
van Zwam, Wim H
Berkhemer, Olvert A
Goyal, Mayank
Demchuk, Andrew M
Menon, Bijoy K
Mitchell, Peter
Hill, Michael D
Jovin, Tudor G
Davalos, Antoni
Campbell, Bruce C V
Saver, Jeffrey L
Roos, Yvo B W E M
Muir, Keith W.
White, Phil
Bracard, Serge
Guillemin, Francis
Olabarriaga, Silvia Delgado
Majoie, Charles B L M
Marquering, Henk A
author_sort Sales Barros, Renan
collection PubMed
description BACKGROUND AND PURPOSE: Infarct volume is a valuable outcome measure in treatment trials of acute ischemic stroke and is strongly associated with functional outcome. Its manual volumetric assessment is, however, too demanding to be implemented in clinical practice. OBJECTIVE: To assess the value of convolutional neural networks (CNNs) in the automatic segmentation of infarct volume in follow-up CT images in a large population of patients with acute ischemic stroke. MATERIALS AND METHODS: We included CT images of 1026 patients from a large pooling of patients with acute ischemic stroke. A reference standard for the infarct segmentation was generated by manual delineation. We introduce three CNN models for the segmentation of subtle, intermediate, and severe hypodense lesions. The fully automated infarct segmentation was defined as the combination of the results of these three CNNs. The results of the three-CNNs approach were compared with the results from a single CNN approach and with the reference standard segmentations. RESULTS: The median infarct volume was 48 mL (IQR 15–125 mL). Comparison between the volumes of the three-CNNs approach and manually delineated infarct volumes showed excellent agreement, with an intraclass correlation coefficient (ICC) of 0.88. Even better agreement was found for severe and intermediate hypodense infarcts, with ICCs of 0.98 and 0.93, respectively. Although the number of patients used for training in the single CNN approach was much larger, the accuracy of the three-CNNs approach strongly outperformed the single CNN approach, which had an ICC of 0.34. CONCLUSION: Convolutional neural networks are valuable and accurate in the quantitative assessment of infarct volumes, for both subtle and severe hypodense infarcts in follow-up CT images. Our proposed three-CNNs approach strongly outperforms a more straightforward single CNN approach.
format Online
Article
Text
id pubmed-7476369
institution National Center for Biotechnology Information
language English
publishDate 2020
publisher BMJ Publishing Group
record_format MEDLINE/PubMed
spelling pubmed-74763692020-09-30 Automatic segmentation of cerebral infarcts in follow-up computed tomography images with convolutional neural networks Sales Barros, Renan Tolhuisen, Manon L Boers, Anna MM Jansen, Ivo Ponomareva, Elena Dippel, Diederik W J van der Lugt, Aad van Oostenbrugge, Robert J van Zwam, Wim H Berkhemer, Olvert A Goyal, Mayank Demchuk, Andrew M Menon, Bijoy K Mitchell, Peter Hill, Michael D Jovin, Tudor G Davalos, Antoni Campbell, Bruce C V Saver, Jeffrey L Roos, Yvo B W E M Muir, Keith W. White, Phil Bracard, Serge Guillemin, Francis Olabarriaga, Silvia Delgado Majoie, Charles B L M Marquering, Henk A J Neurointerv Surg Ischemic Stroke BACKGROUND AND PURPOSE: Infarct volume is a valuable outcome measure in treatment trials of acute ischemic stroke and is strongly associated with functional outcome. Its manual volumetric assessment is, however, too demanding to be implemented in clinical practice. OBJECTIVE: To assess the value of convolutional neural networks (CNNs) in the automatic segmentation of infarct volume in follow-up CT images in a large population of patients with acute ischemic stroke. MATERIALS AND METHODS: We included CT images of 1026 patients from a large pooling of patients with acute ischemic stroke. A reference standard for the infarct segmentation was generated by manual delineation. We introduce three CNN models for the segmentation of subtle, intermediate, and severe hypodense lesions. The fully automated infarct segmentation was defined as the combination of the results of these three CNNs. The results of the three-CNNs approach were compared with the results from a single CNN approach and with the reference standard segmentations. RESULTS: The median infarct volume was 48 mL (IQR 15–125 mL). Comparison between the volumes of the three-CNNs approach and manually delineated infarct volumes showed excellent agreement, with an intraclass correlation coefficient (ICC) of 0.88. Even better agreement was found for severe and intermediate hypodense infarcts, with ICCs of 0.98 and 0.93, respectively. Although the number of patients used for training in the single CNN approach was much larger, the accuracy of the three-CNNs approach strongly outperformed the single CNN approach, which had an ICC of 0.34. CONCLUSION: Convolutional neural networks are valuable and accurate in the quantitative assessment of infarct volumes, for both subtle and severe hypodense infarcts in follow-up CT images. Our proposed three-CNNs approach strongly outperforms a more straightforward single CNN approach. BMJ Publishing Group 2020-09 2019-12-23 /pmc/articles/PMC7476369/ /pubmed/31871069 http://dx.doi.org/10.1136/neurintsurg-2019-015471 Text en © Author(s) (or their employer(s)) 2020. Re-use permitted under CC BY-NC. No commercial re-use. See rights and permissions. Published by BMJ. http://creativecommons.org/licenses/by-nc/4.0/This is an open access article distributed in accordance with the Creative Commons Attribution Non Commercial (CC BY-NC 4.0) license, which permits others to distribute, remix, adapt, build upon this work non-commercially, and license their derivative works on different terms, provided the original work is properly cited, appropriate credit is given, any changes made indicated, and the use is non-commercial. See: http://creativecommons.org/licenses/by-nc/4.0/.
spellingShingle Ischemic Stroke
Sales Barros, Renan
Tolhuisen, Manon L
Boers, Anna MM
Jansen, Ivo
Ponomareva, Elena
Dippel, Diederik W J
van der Lugt, Aad
van Oostenbrugge, Robert J
van Zwam, Wim H
Berkhemer, Olvert A
Goyal, Mayank
Demchuk, Andrew M
Menon, Bijoy K
Mitchell, Peter
Hill, Michael D
Jovin, Tudor G
Davalos, Antoni
Campbell, Bruce C V
Saver, Jeffrey L
Roos, Yvo B W E M
Muir, Keith W.
White, Phil
Bracard, Serge
Guillemin, Francis
Olabarriaga, Silvia Delgado
Majoie, Charles B L M
Marquering, Henk A
Automatic segmentation of cerebral infarcts in follow-up computed tomography images with convolutional neural networks
title Automatic segmentation of cerebral infarcts in follow-up computed tomography images with convolutional neural networks
title_full Automatic segmentation of cerebral infarcts in follow-up computed tomography images with convolutional neural networks
title_fullStr Automatic segmentation of cerebral infarcts in follow-up computed tomography images with convolutional neural networks
title_full_unstemmed Automatic segmentation of cerebral infarcts in follow-up computed tomography images with convolutional neural networks
title_short Automatic segmentation of cerebral infarcts in follow-up computed tomography images with convolutional neural networks
title_sort automatic segmentation of cerebral infarcts in follow-up computed tomography images with convolutional neural networks
topic Ischemic Stroke
url https://www.ncbi.nlm.nih.gov/pmc/articles/PMC7476369/
https://www.ncbi.nlm.nih.gov/pubmed/31871069
http://dx.doi.org/10.1136/neurintsurg-2019-015471
work_keys_str_mv AT salesbarrosrenan automaticsegmentationofcerebralinfarctsinfollowupcomputedtomographyimageswithconvolutionalneuralnetworks
AT tolhuisenmanonl automaticsegmentationofcerebralinfarctsinfollowupcomputedtomographyimageswithconvolutionalneuralnetworks
AT boersannamm automaticsegmentationofcerebralinfarctsinfollowupcomputedtomographyimageswithconvolutionalneuralnetworks
AT jansenivo automaticsegmentationofcerebralinfarctsinfollowupcomputedtomographyimageswithconvolutionalneuralnetworks
AT ponomarevaelena automaticsegmentationofcerebralinfarctsinfollowupcomputedtomographyimageswithconvolutionalneuralnetworks
AT dippeldiederikwj automaticsegmentationofcerebralinfarctsinfollowupcomputedtomographyimageswithconvolutionalneuralnetworks
AT vanderlugtaad automaticsegmentationofcerebralinfarctsinfollowupcomputedtomographyimageswithconvolutionalneuralnetworks
AT vanoostenbruggerobertj automaticsegmentationofcerebralinfarctsinfollowupcomputedtomographyimageswithconvolutionalneuralnetworks
AT vanzwamwimh automaticsegmentationofcerebralinfarctsinfollowupcomputedtomographyimageswithconvolutionalneuralnetworks
AT berkhemerolverta automaticsegmentationofcerebralinfarctsinfollowupcomputedtomographyimageswithconvolutionalneuralnetworks
AT goyalmayank automaticsegmentationofcerebralinfarctsinfollowupcomputedtomographyimageswithconvolutionalneuralnetworks
AT demchukandrewm automaticsegmentationofcerebralinfarctsinfollowupcomputedtomographyimageswithconvolutionalneuralnetworks
AT menonbijoyk automaticsegmentationofcerebralinfarctsinfollowupcomputedtomographyimageswithconvolutionalneuralnetworks
AT mitchellpeter automaticsegmentationofcerebralinfarctsinfollowupcomputedtomographyimageswithconvolutionalneuralnetworks
AT hillmichaeld automaticsegmentationofcerebralinfarctsinfollowupcomputedtomographyimageswithconvolutionalneuralnetworks
AT jovintudorg automaticsegmentationofcerebralinfarctsinfollowupcomputedtomographyimageswithconvolutionalneuralnetworks
AT davalosantoni automaticsegmentationofcerebralinfarctsinfollowupcomputedtomographyimageswithconvolutionalneuralnetworks
AT campbellbrucecv automaticsegmentationofcerebralinfarctsinfollowupcomputedtomographyimageswithconvolutionalneuralnetworks
AT saverjeffreyl automaticsegmentationofcerebralinfarctsinfollowupcomputedtomographyimageswithconvolutionalneuralnetworks
AT roosyvobwem automaticsegmentationofcerebralinfarctsinfollowupcomputedtomographyimageswithconvolutionalneuralnetworks
AT muirkeithw automaticsegmentationofcerebralinfarctsinfollowupcomputedtomographyimageswithconvolutionalneuralnetworks
AT whitephil automaticsegmentationofcerebralinfarctsinfollowupcomputedtomographyimageswithconvolutionalneuralnetworks
AT bracardserge automaticsegmentationofcerebralinfarctsinfollowupcomputedtomographyimageswithconvolutionalneuralnetworks
AT guilleminfrancis automaticsegmentationofcerebralinfarctsinfollowupcomputedtomographyimageswithconvolutionalneuralnetworks
AT olabarriagasilviadelgado automaticsegmentationofcerebralinfarctsinfollowupcomputedtomographyimageswithconvolutionalneuralnetworks
AT majoiecharlesblm automaticsegmentationofcerebralinfarctsinfollowupcomputedtomographyimageswithconvolutionalneuralnetworks
AT marqueringhenka automaticsegmentationofcerebralinfarctsinfollowupcomputedtomographyimageswithconvolutionalneuralnetworks