Automatic Segmentation of Uterine Cavity and Placenta on MR Images Using Deep Learning

Maysam Shahedi; James D. Dormer; Quyen N. Do; Yin Xi; Matthew A. Lewis; Christina L. Herrera; Catherine Y. Spong; Ananth J. Madhuranthakam; Diane M. Twickler; Baowei Fei

doi:10.1117/12.2613286

Automatic Segmentation of Uterine Cavity and Placenta on MR Images Using Deep Learning

Maysam Shahedi, James D. Dormer, Quyen N. Do, Yin Xi, Matthew A. Lewis, Christina L. Herrera, Catherine Y. Spong, Ananth J. Madhuranthakam, Diane M. Twickler, Baowei Fei

Research output: Chapter in Book/Report/Conference proceeding › Conference contribution

1 Scopus citations

Abstract

Magnetic resonance imaging (MRI) is useful for the detection of abnormalities affecting maternal and fetal health. In this study, we used a fully convolutional neural network for simultaneous segmentation of the uterine cavity and placenta on MR images. We trained the network with MR images of 181 patients, with 157 for training and 24 for validation. The segmentation performance of the algorithm was evaluated using MR images of 60 additional patients that were not involved in training. The average Dice similarity coefficients achieved for the uterine cavity and placenta were 92% and 80%, respectively. The algorithm could estimate the volume of the uterine cavity and placenta with average errors of less than 1.1% compared to manual estimations. Automated segmentation, when incorporated into clinical use, has the potential to quantify, standardize, and improve placental assessment, resulting in improved outcomes for mothers and fetuses.

Original language	English (US)
Title of host publication	Medical Imaging 2022
Subtitle of host publication	Biomedical Applications in Molecular, Structural, and Functional Imaging
Editors	Barjor S. Gimi, Andrzej Krol
Publisher	SPIE
ISBN (Electronic)	9781510649477
DOIs	https://doi.org/10.1117/12.2613286
State	Published - 2022
Event	Medical Imaging 2022: Biomedical Applications in Molecular, Structural, and Functional Imaging - Virtual, Online Duration: Mar 21 2022 → Mar 27 2022

Publication series

Name	Progress in Biomedical Optics and Imaging - Proceedings of SPIE
Volume	12036
ISSN (Print)	1605-7422

Conference

Conference	Medical Imaging 2022: Biomedical Applications in Molecular, Structural, and Functional Imaging
City	Virtual, Online
Period	3/21/22 → 3/27/22

Keywords

Placenta
deep learning
image segmentation
magnetic resonance imaging (MRI)
uterine cavity
uterus

ASJC Scopus subject areas

Electronic, Optical and Magnetic Materials
Atomic and Molecular Physics, and Optics
Biomaterials
Radiology Nuclear Medicine and imaging

Access to Document

10.1117/12.2613286

Cite this

Shahedi, M., Dormer, J. D., Do, Q. N., Xi, Y., Lewis, M. A., Herrera, C. L., Spong, C. Y., Madhuranthakam, A. J., Twickler, D. M., & Fei, B. (2022). Automatic Segmentation of Uterine Cavity and Placenta on MR Images Using Deep Learning. In B. S. Gimi, & A. Krol (Eds.), Medical Imaging 2022: Biomedical Applications in Molecular, Structural, and Functional Imaging Article 1203611 (Progress in Biomedical Optics and Imaging - Proceedings of SPIE; Vol. 12036). SPIE. https://doi.org/10.1117/12.2613286

Automatic Segmentation of Uterine Cavity and Placenta on MR Images Using Deep Learning. / Shahedi, Maysam; Dormer, James D.; Do, Quyen N. et al.
Medical Imaging 2022: Biomedical Applications in Molecular, Structural, and Functional Imaging. ed. / Barjor S. Gimi; Andrzej Krol. SPIE, 2022. 1203611 (Progress in Biomedical Optics and Imaging - Proceedings of SPIE; Vol. 12036).

Research output: Chapter in Book/Report/Conference proceeding › Conference contribution

Shahedi, M, Dormer, JD, Do, QN , Xi, Y , Lewis, MA , Herrera, CL , Spong, CY , Madhuranthakam, AJ , Twickler, DM & Fei, B 2022, Automatic Segmentation of Uterine Cavity and Placenta on MR Images Using Deep Learning. in BS Gimi & A Krol (eds), Medical Imaging 2022: Biomedical Applications in Molecular, Structural, and Functional Imaging., 1203611, Progress in Biomedical Optics and Imaging - Proceedings of SPIE, vol. 12036, SPIE, Medical Imaging 2022: Biomedical Applications in Molecular, Structural, and Functional Imaging, Virtual, Online, 3/21/22. https://doi.org/10.1117/12.2613286

Shahedi M, Dormer JD, Do QN , Xi Y , Lewis MA , Herrera CL et al. Automatic Segmentation of Uterine Cavity and Placenta on MR Images Using Deep Learning. In Gimi BS, Krol A, editors, Medical Imaging 2022: Biomedical Applications in Molecular, Structural, and Functional Imaging. SPIE. 2022. 1203611. (Progress in Biomedical Optics and Imaging - Proceedings of SPIE). doi: 10.1117/12.2613286

@inproceedings{5e4ced8f432e472495ab0f71ddf4aee5,

title = "Automatic Segmentation of Uterine Cavity and Placenta on MR Images Using Deep Learning",

abstract = "Magnetic resonance imaging (MRI) is useful for the detection of abnormalities affecting maternal and fetal health. In this study, we used a fully convolutional neural network for simultaneous segmentation of the uterine cavity and placenta on MR images. We trained the network with MR images of 181 patients, with 157 for training and 24 for validation. The segmentation performance of the algorithm was evaluated using MR images of 60 additional patients that were not involved in training. The average Dice similarity coefficients achieved for the uterine cavity and placenta were 92% and 80%, respectively. The algorithm could estimate the volume of the uterine cavity and placenta with average errors of less than 1.1% compared to manual estimations. Automated segmentation, when incorporated into clinical use, has the potential to quantify, standardize, and improve placental assessment, resulting in improved outcomes for mothers and fetuses.",

keywords = "Placenta, deep learning, image segmentation, magnetic resonance imaging (MRI), uterine cavity, uterus",

author = "Maysam Shahedi and Dormer, {James D.} and Do, {Quyen N.} and Yin Xi and Lewis, {Matthew A.} and Herrera, {Christina L.} and Spong, {Catherine Y.} and Madhuranthakam, {Ananth J.} and Twickler, {Diane M.} and Baowei Fei",

note = "Funding Information: This research was supported in part by the U.S. National Institutes of Health (NIH) grants (R01CA156775, R01CA204254, R01HL140325, and R21CA231911), by the Cancer Prevention and Research Institute of Texas (CPRIT) grant RP190588. Publisher Copyright: {\textcopyright} 2022 SPIE; Medical Imaging 2022: Biomedical Applications in Molecular, Structural, and Functional Imaging ; Conference date: 21-03-2022 Through 27-03-2022",

year = "2022",

doi = "10.1117/12.2613286",

language = "English (US)",

series = "Progress in Biomedical Optics and Imaging - Proceedings of SPIE",

publisher = "SPIE",

editor = "Gimi, {Barjor S.} and Andrzej Krol",

booktitle = "Medical Imaging 2022",

}

TY - GEN

T1 - Automatic Segmentation of Uterine Cavity and Placenta on MR Images Using Deep Learning

AU - Shahedi, Maysam

AU - Dormer, James D.

AU - Do, Quyen N.

AU - Xi, Yin

AU - Lewis, Matthew A.

AU - Herrera, Christina L.

AU - Spong, Catherine Y.

AU - Madhuranthakam, Ananth J.

AU - Twickler, Diane M.

AU - Fei, Baowei

N1 - Funding Information: This research was supported in part by the U.S. National Institutes of Health (NIH) grants (R01CA156775, R01CA204254, R01HL140325, and R21CA231911), by the Cancer Prevention and Research Institute of Texas (CPRIT) grant RP190588. Publisher Copyright: © 2022 SPIE

PY - 2022

Y1 - 2022

N2 - Magnetic resonance imaging (MRI) is useful for the detection of abnormalities affecting maternal and fetal health. In this study, we used a fully convolutional neural network for simultaneous segmentation of the uterine cavity and placenta on MR images. We trained the network with MR images of 181 patients, with 157 for training and 24 for validation. The segmentation performance of the algorithm was evaluated using MR images of 60 additional patients that were not involved in training. The average Dice similarity coefficients achieved for the uterine cavity and placenta were 92% and 80%, respectively. The algorithm could estimate the volume of the uterine cavity and placenta with average errors of less than 1.1% compared to manual estimations. Automated segmentation, when incorporated into clinical use, has the potential to quantify, standardize, and improve placental assessment, resulting in improved outcomes for mothers and fetuses.

AB - Magnetic resonance imaging (MRI) is useful for the detection of abnormalities affecting maternal and fetal health. In this study, we used a fully convolutional neural network for simultaneous segmentation of the uterine cavity and placenta on MR images. We trained the network with MR images of 181 patients, with 157 for training and 24 for validation. The segmentation performance of the algorithm was evaluated using MR images of 60 additional patients that were not involved in training. The average Dice similarity coefficients achieved for the uterine cavity and placenta were 92% and 80%, respectively. The algorithm could estimate the volume of the uterine cavity and placenta with average errors of less than 1.1% compared to manual estimations. Automated segmentation, when incorporated into clinical use, has the potential to quantify, standardize, and improve placental assessment, resulting in improved outcomes for mothers and fetuses.

KW - Placenta

KW - deep learning

KW - image segmentation

KW - magnetic resonance imaging (MRI)

KW - uterine cavity

KW - uterus

UR - http://www.scopus.com/inward/record.url?scp=85132042972&partnerID=8YFLogxK

UR - http://www.scopus.com/inward/citedby.url?scp=85132042972&partnerID=8YFLogxK

U2 - 10.1117/12.2613286

DO - 10.1117/12.2613286

M3 - Conference contribution

C2 - 36798450

AN - SCOPUS:85132042972

T3 - Progress in Biomedical Optics and Imaging - Proceedings of SPIE

BT - Medical Imaging 2022

A2 - Gimi, Barjor S.

A2 - Krol, Andrzej

PB - SPIE

T2 - Medical Imaging 2022: Biomedical Applications in Molecular, Structural, and Functional Imaging

Y2 - 21 March 2022 through 27 March 2022

ER -

Automatic Segmentation of Uterine Cavity and Placenta on MR Images Using Deep Learning

Abstract

Publication series

Conference

Keywords

ASJC Scopus subject areas

Access to Document

Other files and links

Fingerprint

Cite this