Standard

3D regression neural network for the quantification of enlarged perivascular spaces in brain MRI. / Dubost, Florian; Adams, Hieab; Bortsova, Gerda; Ikram, M. Arfan; Niessen, Wiro; Niessen, Wiro; Vernooij, Meike; de Bruijne, Marleen; de Bruijne, Marleen.

In: Medical Image Analysis, Vol. 51, 2019, p. 89-100.

Research output: Contribution to journalArticleScientificpeer-review

Harvard

Dubost, F, Adams, H, Bortsova, G, Ikram, MA, Niessen, W, Niessen, W, Vernooij, M, de Bruijne, M & de Bruijne, M 2019, '3D regression neural network for the quantification of enlarged perivascular spaces in brain MRI', Medical Image Analysis, vol. 51, pp. 89-100. https://doi.org/10.1016/j.media.2018.10.008

APA

Dubost, F., Adams, H., Bortsova, G., Ikram, M. A., Niessen, W., Niessen, W., Vernooij, M., de Bruijne, M., & de Bruijne, M. (2019). 3D regression neural network for the quantification of enlarged perivascular spaces in brain MRI. Medical Image Analysis, 51, 89-100. https://doi.org/10.1016/j.media.2018.10.008

Vancouver

Author

Dubost, Florian ; Adams, Hieab ; Bortsova, Gerda ; Ikram, M. Arfan ; Niessen, Wiro ; Niessen, Wiro ; Vernooij, Meike ; de Bruijne, Marleen ; de Bruijne, Marleen. / 3D regression neural network for the quantification of enlarged perivascular spaces in brain MRI. In: Medical Image Analysis. 2019 ; Vol. 51. pp. 89-100.

BibTeX

@article{dca428a971504f2c8d63ad7d65387807,
title = "3D regression neural network for the quantification of enlarged perivascular spaces in brain MRI",
abstract = "{\textcopyright} 2018 Enlarged perivascular spaces (EPVS) in the brain are an emerging imaging marker for cerebral small vessel disease, and have been shown to be related to increased risk of various neurological diseases, including stroke and dementia. Automated quantification of EPVS would greatly help to advance research into its etiology and its potential as a risk indicator of disease. We propose a convolutional network regression method to quantify the extent of EPVS in the basal ganglia from 3D brain MRI. We first segment the basal ganglia and subsequently apply a 3D convolutional regression network designed for small object detection within this region of interest. The network takes an image as input, and outputs a quantification score of EPVS. The network has significantly more convolution operations than pooling ones and no final activation, allowing it to span the space of real numbers. We validated our approach using a dataset of 2000 brain MRI scans scored visually. Experiments with varying sizes of training and test sets showed that a good performance can be achieved with a training set of only 200 scans. With a training set of 1000 scans, the intraclass correlation coefficient (ICC) between our scoring method and the expert's visual score was 0.74. Our method outperforms by a large margin - more than 0.10 - four more conventional automated approaches based on intensities, scale-invariant feature transform, and random forest. We show that the network learns the structures of interest and investigate the influence of hyper-parameters on the performance. We also evaluate the reproducibility of our network using a set of 60 subjects scanned twice (scan-rescan reproducibility). On this set our network achieves an ICC of 0.93, while the intrarater agreement reaches 0.80. Furthermore, the automated EPVS scoring correlates similarly to age as visual scoring.",
keywords = "Deep learning, Dementia, Perivascular space, Regression, Virchow-Robin space, Weak labels",
author = "Florian Dubost and Hieab Adams and Gerda Bortsova and Ikram, {M. Arfan} and Wiro Niessen and Wiro Niessen and Meike Vernooij and {de Bruijne}, Marleen and {de Bruijne}, Marleen",
year = "2019",
doi = "10.1016/j.media.2018.10.008",
language = "English",
volume = "51",
pages = "89--100",
journal = "Medical Image Analysis",
issn = "1361-8415",
publisher = "Elsevier",

}

RIS

TY - JOUR

T1 - 3D regression neural network for the quantification of enlarged perivascular spaces in brain MRI

AU - Dubost, Florian

AU - Adams, Hieab

AU - Bortsova, Gerda

AU - Ikram, M. Arfan

AU - Niessen, Wiro

AU - Niessen, Wiro

AU - Vernooij, Meike

AU - de Bruijne, Marleen

AU - de Bruijne, Marleen

PY - 2019

Y1 - 2019

N2 - © 2018 Enlarged perivascular spaces (EPVS) in the brain are an emerging imaging marker for cerebral small vessel disease, and have been shown to be related to increased risk of various neurological diseases, including stroke and dementia. Automated quantification of EPVS would greatly help to advance research into its etiology and its potential as a risk indicator of disease. We propose a convolutional network regression method to quantify the extent of EPVS in the basal ganglia from 3D brain MRI. We first segment the basal ganglia and subsequently apply a 3D convolutional regression network designed for small object detection within this region of interest. The network takes an image as input, and outputs a quantification score of EPVS. The network has significantly more convolution operations than pooling ones and no final activation, allowing it to span the space of real numbers. We validated our approach using a dataset of 2000 brain MRI scans scored visually. Experiments with varying sizes of training and test sets showed that a good performance can be achieved with a training set of only 200 scans. With a training set of 1000 scans, the intraclass correlation coefficient (ICC) between our scoring method and the expert's visual score was 0.74. Our method outperforms by a large margin - more than 0.10 - four more conventional automated approaches based on intensities, scale-invariant feature transform, and random forest. We show that the network learns the structures of interest and investigate the influence of hyper-parameters on the performance. We also evaluate the reproducibility of our network using a set of 60 subjects scanned twice (scan-rescan reproducibility). On this set our network achieves an ICC of 0.93, while the intrarater agreement reaches 0.80. Furthermore, the automated EPVS scoring correlates similarly to age as visual scoring.

AB - © 2018 Enlarged perivascular spaces (EPVS) in the brain are an emerging imaging marker for cerebral small vessel disease, and have been shown to be related to increased risk of various neurological diseases, including stroke and dementia. Automated quantification of EPVS would greatly help to advance research into its etiology and its potential as a risk indicator of disease. We propose a convolutional network regression method to quantify the extent of EPVS in the basal ganglia from 3D brain MRI. We first segment the basal ganglia and subsequently apply a 3D convolutional regression network designed for small object detection within this region of interest. The network takes an image as input, and outputs a quantification score of EPVS. The network has significantly more convolution operations than pooling ones and no final activation, allowing it to span the space of real numbers. We validated our approach using a dataset of 2000 brain MRI scans scored visually. Experiments with varying sizes of training and test sets showed that a good performance can be achieved with a training set of only 200 scans. With a training set of 1000 scans, the intraclass correlation coefficient (ICC) between our scoring method and the expert's visual score was 0.74. Our method outperforms by a large margin - more than 0.10 - four more conventional automated approaches based on intensities, scale-invariant feature transform, and random forest. We show that the network learns the structures of interest and investigate the influence of hyper-parameters on the performance. We also evaluate the reproducibility of our network using a set of 60 subjects scanned twice (scan-rescan reproducibility). On this set our network achieves an ICC of 0.93, while the intrarater agreement reaches 0.80. Furthermore, the automated EPVS scoring correlates similarly to age as visual scoring.

KW - Deep learning

KW - Dementia

KW - Perivascular space

KW - Regression

KW - Virchow-Robin space

KW - Weak labels

UR - http://www.scopus.com/inward/record.url?scp=85055753914&partnerID=8YFLogxK

U2 - 10.1016/j.media.2018.10.008

DO - 10.1016/j.media.2018.10.008

M3 - Article

AN - SCOPUS:85055753914

VL - 51

SP - 89

EP - 100

JO - Medical Image Analysis

JF - Medical Image Analysis

SN - 1361-8415

ER -

ID: 47372675