Segmentation of the Proximal Femur from MR Images using Deep Convolutional Neural Networks

Cem M. Deniz, Siyuan Xiang, R. Spencer Hallyburton, Arakua Welbeck, James S. Babb, Stephen Honig, Kyunghyun Cho, Gregory Chang

Research output: Contribution to journalArticle

Abstract

Magnetic resonance imaging (MRI) has been proposed as a complimentary method to measure bone quality and assess fracture risk. However, manual segmentation of MR images of bone is time-consuming, limiting the use of MRI measurements in the clinical practice. The purpose of this paper is to present an automatic proximal femur segmentation method that is based on deep convolutional neural networks (CNNs). This study had institutional review board approval and written informed consent was obtained from all subjects. A dataset of volumetric structural MR images of the proximal femur from 86 subjects were manually-segmented by an expert. We performed experiments by training two different CNN architectures with multiple number of initial feature maps, layers and dilation rates, and tested their segmentation performance against the gold standard of manual segmentations using four-fold cross-validation. Automatic segmentation of the proximal femur using CNNs achieved a high dice similarity score of 0.95 ± 0.02 with precision = 0.95 ± 0.02, and recall = 0.95 ± 0.03. The high segmentation accuracy provided by CNNs has the potential to help bring the use of structural MRI measurements of bone quality into clinical practice for management of osteoporosis.

Original languageEnglish (US)
Article number16485
JournalScientific reports
Volume8
Issue number1
DOIs
StatePublished - Dec 1 2018

Fingerprint

Femur
Magnetic Resonance Imaging
Bone and Bones
Research Ethics Committees
Practice Management
Informed Consent
Osteoporosis
Dilatation
Datasets

ASJC Scopus subject areas

  • General

Cite this

Deniz, C. M., Xiang, S., Hallyburton, R. S., Welbeck, A., Babb, J. S., Honig, S., ... Chang, G. (2018). Segmentation of the Proximal Femur from MR Images using Deep Convolutional Neural Networks. Scientific reports, 8(1), [16485]. https://doi.org/10.1038/s41598-018-34817-6

Segmentation of the Proximal Femur from MR Images using Deep Convolutional Neural Networks. / Deniz, Cem M.; Xiang, Siyuan; Hallyburton, R. Spencer; Welbeck, Arakua; Babb, James S.; Honig, Stephen; Cho, Kyunghyun; Chang, Gregory.

In: Scientific reports, Vol. 8, No. 1, 16485, 01.12.2018.

Research output: Contribution to journalArticle

Deniz, CM, Xiang, S, Hallyburton, RS, Welbeck, A, Babb, JS, Honig, S, Cho, K & Chang, G 2018, 'Segmentation of the Proximal Femur from MR Images using Deep Convolutional Neural Networks', Scientific reports, vol. 8, no. 1, 16485. https://doi.org/10.1038/s41598-018-34817-6
Deniz, Cem M. ; Xiang, Siyuan ; Hallyburton, R. Spencer ; Welbeck, Arakua ; Babb, James S. ; Honig, Stephen ; Cho, Kyunghyun ; Chang, Gregory. / Segmentation of the Proximal Femur from MR Images using Deep Convolutional Neural Networks. In: Scientific reports. 2018 ; Vol. 8, No. 1.
@article{af7e43d75b004191bab8b1ca6d5c94a8,
title = "Segmentation of the Proximal Femur from MR Images using Deep Convolutional Neural Networks",
abstract = "Magnetic resonance imaging (MRI) has been proposed as a complimentary method to measure bone quality and assess fracture risk. However, manual segmentation of MR images of bone is time-consuming, limiting the use of MRI measurements in the clinical practice. The purpose of this paper is to present an automatic proximal femur segmentation method that is based on deep convolutional neural networks (CNNs). This study had institutional review board approval and written informed consent was obtained from all subjects. A dataset of volumetric structural MR images of the proximal femur from 86 subjects were manually-segmented by an expert. We performed experiments by training two different CNN architectures with multiple number of initial feature maps, layers and dilation rates, and tested their segmentation performance against the gold standard of manual segmentations using four-fold cross-validation. Automatic segmentation of the proximal femur using CNNs achieved a high dice similarity score of 0.95 ± 0.02 with precision = 0.95 ± 0.02, and recall = 0.95 ± 0.03. The high segmentation accuracy provided by CNNs has the potential to help bring the use of structural MRI measurements of bone quality into clinical practice for management of osteoporosis.",
author = "Deniz, {Cem M.} and Siyuan Xiang and Hallyburton, {R. Spencer} and Arakua Welbeck and Babb, {James S.} and Stephen Honig and Kyunghyun Cho and Gregory Chang",
year = "2018",
month = "12",
day = "1",
doi = "10.1038/s41598-018-34817-6",
language = "English (US)",
volume = "8",
journal = "Scientific Reports",
issn = "2045-2322",
publisher = "Nature Publishing Group",
number = "1",

}

TY - JOUR

T1 - Segmentation of the Proximal Femur from MR Images using Deep Convolutional Neural Networks

AU - Deniz, Cem M.

AU - Xiang, Siyuan

AU - Hallyburton, R. Spencer

AU - Welbeck, Arakua

AU - Babb, James S.

AU - Honig, Stephen

AU - Cho, Kyunghyun

AU - Chang, Gregory

PY - 2018/12/1

Y1 - 2018/12/1

N2 - Magnetic resonance imaging (MRI) has been proposed as a complimentary method to measure bone quality and assess fracture risk. However, manual segmentation of MR images of bone is time-consuming, limiting the use of MRI measurements in the clinical practice. The purpose of this paper is to present an automatic proximal femur segmentation method that is based on deep convolutional neural networks (CNNs). This study had institutional review board approval and written informed consent was obtained from all subjects. A dataset of volumetric structural MR images of the proximal femur from 86 subjects were manually-segmented by an expert. We performed experiments by training two different CNN architectures with multiple number of initial feature maps, layers and dilation rates, and tested their segmentation performance against the gold standard of manual segmentations using four-fold cross-validation. Automatic segmentation of the proximal femur using CNNs achieved a high dice similarity score of 0.95 ± 0.02 with precision = 0.95 ± 0.02, and recall = 0.95 ± 0.03. The high segmentation accuracy provided by CNNs has the potential to help bring the use of structural MRI measurements of bone quality into clinical practice for management of osteoporosis.

AB - Magnetic resonance imaging (MRI) has been proposed as a complimentary method to measure bone quality and assess fracture risk. However, manual segmentation of MR images of bone is time-consuming, limiting the use of MRI measurements in the clinical practice. The purpose of this paper is to present an automatic proximal femur segmentation method that is based on deep convolutional neural networks (CNNs). This study had institutional review board approval and written informed consent was obtained from all subjects. A dataset of volumetric structural MR images of the proximal femur from 86 subjects were manually-segmented by an expert. We performed experiments by training two different CNN architectures with multiple number of initial feature maps, layers and dilation rates, and tested their segmentation performance against the gold standard of manual segmentations using four-fold cross-validation. Automatic segmentation of the proximal femur using CNNs achieved a high dice similarity score of 0.95 ± 0.02 with precision = 0.95 ± 0.02, and recall = 0.95 ± 0.03. The high segmentation accuracy provided by CNNs has the potential to help bring the use of structural MRI measurements of bone quality into clinical practice for management of osteoporosis.

UR - http://www.scopus.com/inward/record.url?scp=85056088310&partnerID=8YFLogxK

UR - http://www.scopus.com/inward/citedby.url?scp=85056088310&partnerID=8YFLogxK

U2 - 10.1038/s41598-018-34817-6

DO - 10.1038/s41598-018-34817-6

M3 - Article

VL - 8

JO - Scientific Reports

JF - Scientific Reports

SN - 2045-2322

IS - 1

M1 - 16485

ER -