Segmentation of uterus and placenta in MR images using a fully convolutional neural network

Maysam Shahedi; James D. Dormer; T. T. Anusha Devi; Quyen N. Do; Yin Xi; Matthew A. Lewis; Ananth J. Madhuranthakam; Diane M. Twickler; Baowei Fei

doi:10.1117/12.2549873

Segmentation of uterus and placenta in MR images using a fully convolutional neural network

Maysam Shahedi, James D. Dormer, T. T. Anusha Devi, Quyen N. Do, Yin Xi, Matthew A. Lewis, Ananth J. Madhuranthakam, Diane M. Twickler, Baowei Fei

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

12 Scopus citations

Abstract

Segmentation of the uterine cavity and placenta in fetal magnetic resonance (MR) imaging is useful for the detection of abnormalities that affect maternal and fetal health. In this study, we used a fully convolutional neural network for 3D segmentation of the uterine cavity and placenta while a minimal operator interaction was incorporated for training and testing the network. The user interaction guided the network to localize the placenta more accurately. We trained the network with 70 training and 10 validation MRI cases and evaluated the algorithm segmentation performance using 20 cases. The average Dice similarity coefficient was 92% and 82% for the uterine cavity and placenta, respectively. The algorithm could estimate the volume of the uterine cavity and placenta with average errors of 2% and 9%, respectively. The results demonstrate that the deep learning-based segmentation and volume estimation is possible and can potentially be useful for clinical applications of human placental imaging.

Original language	English (US)
Title of host publication	Medical Imaging 2020
Subtitle of host publication	Computer-Aided Diagnosis
Editors	Horst K. Hahn, Maciej A. Mazurowski
Publisher	SPIE
ISBN (Electronic)	9781510633957
DOIs	https://doi.org/10.1117/12.2549873
State	Published - 2020
Event	Medical Imaging 2020: Computer-Aided Diagnosis - Houston, United States Duration: Feb 16 2020 → Feb 19 2020

Publication series

Name	Progress in Biomedical Optics and Imaging - Proceedings of SPIE
Volume	11314
ISSN (Print)	1605-7422

Conference

Conference	Medical Imaging 2020: Computer-Aided Diagnosis
Country/Territory	United States
City	Houston
Period	2/16/20 → 2/19/20

Keywords

convolutional neural network
fetal magnetic resonance imaging.
image segmentation
placenta
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

10.1117/12.2549873

Cite this

Shahedi, M., Dormer, J. D., Anusha Devi, T. T., Do, Q. N., Xi, Y., Lewis, M. A., Madhuranthakam, A. J., Twickler, D. M., & Fei, B. (2020). Segmentation of uterus and placenta in MR images using a fully convolutional neural network. In H. K. Hahn, & M. A. Mazurowski (Eds.), Medical Imaging 2020: Computer-Aided Diagnosis Article 113141R (Progress in Biomedical Optics and Imaging - Proceedings of SPIE; Vol. 11314). SPIE. https://doi.org/10.1117/12.2549873

Segmentation of uterus and placenta in MR images using a fully convolutional neural network. / Shahedi, Maysam; Dormer, James D.; Anusha Devi, T. T. et al.
Medical Imaging 2020: Computer-Aided Diagnosis. ed. / Horst K. Hahn; Maciej A. Mazurowski. SPIE, 2020. 113141R (Progress in Biomedical Optics and Imaging - Proceedings of SPIE; Vol. 11314).

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

Shahedi, M, Dormer, JD, Anusha Devi, TT, Do, QN , Xi, Y , Lewis, MA , Madhuranthakam, AJ , Twickler, DM & Fei, B 2020, Segmentation of uterus and placenta in MR images using a fully convolutional neural network. in HK Hahn & MA Mazurowski (eds), Medical Imaging 2020: Computer-Aided Diagnosis., 113141R, Progress in Biomedical Optics and Imaging - Proceedings of SPIE, vol. 11314, SPIE, Medical Imaging 2020: Computer-Aided Diagnosis, Houston, United States, 2/16/20. https://doi.org/10.1117/12.2549873

@inproceedings{26cc8762539a466db074f20532be9c0d,

title = "Segmentation of uterus and placenta in MR images using a fully convolutional neural network",

abstract = "Segmentation of the uterine cavity and placenta in fetal magnetic resonance (MR) imaging is useful for the detection of abnormalities that affect maternal and fetal health. In this study, we used a fully convolutional neural network for 3D segmentation of the uterine cavity and placenta while a minimal operator interaction was incorporated for training and testing the network. The user interaction guided the network to localize the placenta more accurately. We trained the network with 70 training and 10 validation MRI cases and evaluated the algorithm segmentation performance using 20 cases. The average Dice similarity coefficient was 92% and 82% for the uterine cavity and placenta, respectively. The algorithm could estimate the volume of the uterine cavity and placenta with average errors of 2% and 9%, respectively. The results demonstrate that the deep learning-based segmentation and volume estimation is possible and can potentially be useful for clinical applications of human placental imaging.",

keywords = "convolutional neural network, fetal magnetic resonance imaging., image segmentation, placenta, uterus",

author = "Maysam Shahedi and Dormer, {James D.} and {Anusha Devi}, {T. T.} and Do, {Quyen N.} and Yin Xi and Lewis, {Matthew A.} 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) and by the Cancer Prevention and Research Institute of Texas (CPRIT) grant RP190588. Publisher Copyright: {\textcopyright} 2020 SPIE.; Medical Imaging 2020: Computer-Aided Diagnosis ; Conference date: 16-02-2020 Through 19-02-2020",

year = "2020",

doi = "10.1117/12.2549873",

language = "English (US)",

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

publisher = "SPIE",

editor = "Hahn, {Horst K.} and Mazurowski, {Maciej A.}",

booktitle = "Medical Imaging 2020",

}

TY - GEN

T1 - Segmentation of uterus and placenta in MR images using a fully convolutional neural network

AU - Shahedi, Maysam

AU - Dormer, James D.

AU - Anusha Devi, T. T.

AU - Do, Quyen N.

AU - Xi, Yin

AU - Lewis, Matthew A.

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) and by the Cancer Prevention and Research Institute of Texas (CPRIT) grant RP190588. Publisher Copyright: © 2020 SPIE.

PY - 2020

Y1 - 2020

N2 - Segmentation of the uterine cavity and placenta in fetal magnetic resonance (MR) imaging is useful for the detection of abnormalities that affect maternal and fetal health. In this study, we used a fully convolutional neural network for 3D segmentation of the uterine cavity and placenta while a minimal operator interaction was incorporated for training and testing the network. The user interaction guided the network to localize the placenta more accurately. We trained the network with 70 training and 10 validation MRI cases and evaluated the algorithm segmentation performance using 20 cases. The average Dice similarity coefficient was 92% and 82% for the uterine cavity and placenta, respectively. The algorithm could estimate the volume of the uterine cavity and placenta with average errors of 2% and 9%, respectively. The results demonstrate that the deep learning-based segmentation and volume estimation is possible and can potentially be useful for clinical applications of human placental imaging.

AB - Segmentation of the uterine cavity and placenta in fetal magnetic resonance (MR) imaging is useful for the detection of abnormalities that affect maternal and fetal health. In this study, we used a fully convolutional neural network for 3D segmentation of the uterine cavity and placenta while a minimal operator interaction was incorporated for training and testing the network. The user interaction guided the network to localize the placenta more accurately. We trained the network with 70 training and 10 validation MRI cases and evaluated the algorithm segmentation performance using 20 cases. The average Dice similarity coefficient was 92% and 82% for the uterine cavity and placenta, respectively. The algorithm could estimate the volume of the uterine cavity and placenta with average errors of 2% and 9%, respectively. The results demonstrate that the deep learning-based segmentation and volume estimation is possible and can potentially be useful for clinical applications of human placental imaging.

KW - convolutional neural network

KW - fetal magnetic resonance imaging.

KW - image segmentation

KW - placenta

KW - uterus

UR - http://www.scopus.com/inward/record.url?scp=85085476220&partnerID=8YFLogxK

UR - http://www.scopus.com/inward/citedby.url?scp=85085476220&partnerID=8YFLogxK

U2 - 10.1117/12.2549873

DO - 10.1117/12.2549873

M3 - Conference contribution

C2 - 32476702

AN - SCOPUS:85085476220

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

BT - Medical Imaging 2020

A2 - Hahn, Horst K.

A2 - Mazurowski, Maciej A.

PB - SPIE

T2 - Medical Imaging 2020: Computer-Aided Diagnosis

Y2 - 16 February 2020 through 19 February 2020

ER -

Segmentation of uterus and placenta in MR images using a fully convolutional neural network

Abstract

Publication series

Conference

Keywords

ASJC Scopus subject areas

Access to Document

Other files and links

Fingerprint

Cite this