Coronary luminal and wall mask prediction using convolutional neural network

Y. Hong; Y. M. Hong; Y. Jang; S. Kim; B. Jeon; S. Jung; S. Ha; D. Han; H. Shim; H. J. Chang

doi:10.1109/ISBI.2017.7950696

Coronary luminal and wall mask prediction using convolutional neural network

Y. Hong, Y. M. Hong, Y. Jang, S. Kim, B. Jeon, S. Jung, S. Ha, D. Han, H. Shim, H. J. Chang

Department of Internal Medicine

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

3 Citations (Scopus)

Abstract

A significant amount of research has been done on the segmentation of coronary arteries. However, the resulting automated boundary delineation is still not suitable for clinical utilization. The convolutional neural network was driving advances in the medical image processing. We propose the brief convolutional network (BCN) that automatically produces the labeled mask with the luminal and wall boundaries of the coronary artery. We utilized 50 patients of CCTA - intravascular ultrasound matched image data sets. Training and testing were performed on 40 and 10 patient data sets, respectively. The prediction of luminal and wall mask was performed using stacked BCN on the each image view: axial, coronal, and sagittal of straightened curved planar reformation. We defined the vector that includes probability from BCN result on each image view and proposed amplified probability. We used an Adaptive Boost regressor with an extremely randomized tree regressor to determine the label for unknown probability vector.

Original language	English
Title of host publication	2017 IEEE 14th International Symposium on Biomedical Imaging, ISBI 2017
Publisher	IEEE Computer Society
Pages	1049-1052
Number of pages	4
ISBN (Electronic)	9781509011711
DOIs	https://doi.org/10.1109/ISBI.2017.7950696
Publication status	Published - 2017 Jun 15
Event	14th IEEE International Symposium on Biomedical Imaging, ISBI 2017 - Melbourne, Australia Duration: 2017 Apr 18 → 2017 Apr 21

Publication series

Name	Proceedings - International Symposium on Biomedical Imaging
ISSN (Print)	1945-7928
ISSN (Electronic)	1945-8452

Other

Other	14th IEEE International Symposium on Biomedical Imaging, ISBI 2017
Country/Territory	Australia
City	Melbourne
Period	17/4/18 → 17/4/21

Bibliographical note

Publisher Copyright:
© 2017 IEEE.

All Science Journal Classification (ASJC) codes

Biomedical Engineering
Radiology Nuclear Medicine and imaging

Access to Document

10.1109/ISBI.2017.7950696

Cite this

Hong, Y., Hong, Y. M., Jang, Y., Kim, S., Jeon, B., Jung, S., Ha, S., Han, D., Shim, H., & Chang, H. J. (2017). Coronary luminal and wall mask prediction using convolutional neural network. In 2017 IEEE 14th International Symposium on Biomedical Imaging, ISBI 2017 (pp. 1049-1052). [7950696] (Proceedings - International Symposium on Biomedical Imaging). IEEE Computer Society. https://doi.org/10.1109/ISBI.2017.7950696

@inproceedings{984dfbbe48454c5ab2550b3c4616d539,

title = "Coronary luminal and wall mask prediction using convolutional neural network",

abstract = "A significant amount of research has been done on the segmentation of coronary arteries. However, the resulting automated boundary delineation is still not suitable for clinical utilization. The convolutional neural network was driving advances in the medical image processing. We propose the brief convolutional network (BCN) that automatically produces the labeled mask with the luminal and wall boundaries of the coronary artery. We utilized 50 patients of CCTA - intravascular ultrasound matched image data sets. Training and testing were performed on 40 and 10 patient data sets, respectively. The prediction of luminal and wall mask was performed using stacked BCN on the each image view: axial, coronal, and sagittal of straightened curved planar reformation. We defined the vector that includes probability from BCN result on each image view and proposed amplified probability. We used an Adaptive Boost regressor with an extremely randomized tree regressor to determine the label for unknown probability vector.",

author = "Y. Hong and Hong, {Y. M.} and Y. Jang and S. Kim and B. Jeon and S. Jung and S. Ha and D. Han and H. Shim and Chang, {H. J.}",

note = "Publisher Copyright: {\textcopyright} 2017 IEEE.; 14th IEEE International Symposium on Biomedical Imaging, ISBI 2017 ; Conference date: 18-04-2017 Through 21-04-2017",

year = "2017",

month = jun,

day = "15",

doi = "10.1109/ISBI.2017.7950696",

language = "English",

series = "Proceedings - International Symposium on Biomedical Imaging",

publisher = "IEEE Computer Society",

pages = "1049--1052",

booktitle = "2017 IEEE 14th International Symposium on Biomedical Imaging, ISBI 2017",

address = "United States",

}

Hong, Y, Hong, YM, Jang, Y, Kim, S, Jeon, B, Jung, S, Ha, S, Han, D, Shim, H & Chang, HJ 2017, Coronary luminal and wall mask prediction using convolutional neural network. in 2017 IEEE 14th International Symposium on Biomedical Imaging, ISBI 2017., 7950696, Proceedings - International Symposium on Biomedical Imaging, IEEE Computer Society, pp. 1049-1052, 14th IEEE International Symposium on Biomedical Imaging, ISBI 2017, Melbourne, Australia, 17/4/18. https://doi.org/10.1109/ISBI.2017.7950696

Coronary luminal and wall mask prediction using convolutional neural network. / Hong, Y.; Hong, Y. M.; Jang, Y. et al.

2017 IEEE 14th International Symposium on Biomedical Imaging, ISBI 2017. IEEE Computer Society, 2017. p. 1049-1052 7950696 (Proceedings - International Symposium on Biomedical Imaging).

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

TY - GEN

T1 - Coronary luminal and wall mask prediction using convolutional neural network

AU - Hong, Y.

AU - Hong, Y. M.

AU - Jang, Y.

AU - Kim, S.

AU - Jeon, B.

AU - Jung, S.

AU - Ha, S.

AU - Han, D.

AU - Shim, H.

AU - Chang, H. J.

PY - 2017/6/15

Y1 - 2017/6/15

N2 - A significant amount of research has been done on the segmentation of coronary arteries. However, the resulting automated boundary delineation is still not suitable for clinical utilization. The convolutional neural network was driving advances in the medical image processing. We propose the brief convolutional network (BCN) that automatically produces the labeled mask with the luminal and wall boundaries of the coronary artery. We utilized 50 patients of CCTA - intravascular ultrasound matched image data sets. Training and testing were performed on 40 and 10 patient data sets, respectively. The prediction of luminal and wall mask was performed using stacked BCN on the each image view: axial, coronal, and sagittal of straightened curved planar reformation. We defined the vector that includes probability from BCN result on each image view and proposed amplified probability. We used an Adaptive Boost regressor with an extremely randomized tree regressor to determine the label for unknown probability vector.

AB - A significant amount of research has been done on the segmentation of coronary arteries. However, the resulting automated boundary delineation is still not suitable for clinical utilization. The convolutional neural network was driving advances in the medical image processing. We propose the brief convolutional network (BCN) that automatically produces the labeled mask with the luminal and wall boundaries of the coronary artery. We utilized 50 patients of CCTA - intravascular ultrasound matched image data sets. Training and testing were performed on 40 and 10 patient data sets, respectively. The prediction of luminal and wall mask was performed using stacked BCN on the each image view: axial, coronal, and sagittal of straightened curved planar reformation. We defined the vector that includes probability from BCN result on each image view and proposed amplified probability. We used an Adaptive Boost regressor with an extremely randomized tree regressor to determine the label for unknown probability vector.

UR - http://www.scopus.com/inward/record.url?scp=85023191132&partnerID=8YFLogxK

UR - http://www.scopus.com/inward/citedby.url?scp=85023191132&partnerID=8YFLogxK

U2 - 10.1109/ISBI.2017.7950696

DO - 10.1109/ISBI.2017.7950696

M3 - Conference contribution

AN - SCOPUS:85023191132

T3 - Proceedings - International Symposium on Biomedical Imaging

SP - 1049

EP - 1052

BT - 2017 IEEE 14th International Symposium on Biomedical Imaging, ISBI 2017

PB - IEEE Computer Society

T2 - 14th IEEE International Symposium on Biomedical Imaging, ISBI 2017

Y2 - 18 April 2017 through 21 April 2017

ER -

Coronary luminal and wall mask prediction using convolutional neural network

Abstract

Publication series

Other

Bibliographical note

All Science Journal Classification (ASJC) codes

Access to Document

Other files and links

Fingerprint

Cite this