Automating carotid intima-media thickness video interpretation with convolutional neural networks

Jae Y. Shin, Nima Tajbakhsh, R. Todd Hurst, Christopher B. Kendall, Jianming Liang

Research output: Chapter in Book/Report/Conference proceedingConference contribution

10 Citations (Scopus)

Abstract

Cardiovascular disease (CVD) is the leading cause of mortality yet largely preventable, but the key to prevention is to identify at-risk individuals before adverse events. For predicting individual CVD risk, carotid intima-media thickness (CIMT), a noninvasive ultrasound method, has proven to be valuable, offering several advantages over CT coronary artery calcium score. However, each CIMT examination includes several ultrasound videos, and interpreting each of these CIMT videos involves three operations: (1) select three end-diastolic ultrasound frames (EUF) in the video, (2) localize a region of interest (ROI) in each selected frame, and (3) trace the lumen-intima interface and the media-adventitia interface in each ROI to measure CIMT. These operations are tedious, laborious, and time consuming, a serious limitation that hinders the widespread utilization of CIMT in clinical practice. To overcome this limitation, this paper presents a new system to automate CIMT video interpretation. Our extensive experiments demonstrate that the suggested system performs reliably. The reliable performance is attributable to our unified framework based on convolutional neural networks (CNNs) coupled with our informative image representation and effective post-processing of the CNN outputs, which are uniquely designed for each of the above three operations.

Original languageEnglish (US)
Title of host publication2016 IEEE Conference on Computer Vision and Pattern Recognition, CVPR 2016
PublisherIEEE Computer Society
Pages2526-2535
Number of pages10
Volume2016-January
ISBN (Electronic)9781467388511
StatePublished - 2016
Event2016 IEEE Conference on Computer Vision and Pattern Recognition, CVPR 2016 - Las Vegas, United States
Duration: Jun 26 2016Jul 1 2016

Other

Other2016 IEEE Conference on Computer Vision and Pattern Recognition, CVPR 2016
CountryUnited States
CityLas Vegas
Period6/26/167/1/16

Fingerprint

Ultrasonics
Neural networks
Calcium
Processing
Experiments

ASJC Scopus subject areas

  • Software
  • Computer Vision and Pattern Recognition

Cite this

Shin, J. Y., Tajbakhsh, N., Todd Hurst, R., Kendall, C. B., & Liang, J. (2016). Automating carotid intima-media thickness video interpretation with convolutional neural networks. In 2016 IEEE Conference on Computer Vision and Pattern Recognition, CVPR 2016 (Vol. 2016-January, pp. 2526-2535). IEEE Computer Society.

Automating carotid intima-media thickness video interpretation with convolutional neural networks. / Shin, Jae Y.; Tajbakhsh, Nima; Todd Hurst, R.; Kendall, Christopher B.; Liang, Jianming.

2016 IEEE Conference on Computer Vision and Pattern Recognition, CVPR 2016. Vol. 2016-January IEEE Computer Society, 2016. p. 2526-2535.

Research output: Chapter in Book/Report/Conference proceedingConference contribution

Shin, JY, Tajbakhsh, N, Todd Hurst, R, Kendall, CB & Liang, J 2016, Automating carotid intima-media thickness video interpretation with convolutional neural networks. in 2016 IEEE Conference on Computer Vision and Pattern Recognition, CVPR 2016. vol. 2016-January, IEEE Computer Society, pp. 2526-2535, 2016 IEEE Conference on Computer Vision and Pattern Recognition, CVPR 2016, Las Vegas, United States, 6/26/16.
Shin JY, Tajbakhsh N, Todd Hurst R, Kendall CB, Liang J. Automating carotid intima-media thickness video interpretation with convolutional neural networks. In 2016 IEEE Conference on Computer Vision and Pattern Recognition, CVPR 2016. Vol. 2016-January. IEEE Computer Society. 2016. p. 2526-2535
Shin, Jae Y. ; Tajbakhsh, Nima ; Todd Hurst, R. ; Kendall, Christopher B. ; Liang, Jianming. / Automating carotid intima-media thickness video interpretation with convolutional neural networks. 2016 IEEE Conference on Computer Vision and Pattern Recognition, CVPR 2016. Vol. 2016-January IEEE Computer Society, 2016. pp. 2526-2535
@inproceedings{f7d626a65e2747dab58384749875f45b,
title = "Automating carotid intima-media thickness video interpretation with convolutional neural networks",
abstract = "Cardiovascular disease (CVD) is the leading cause of mortality yet largely preventable, but the key to prevention is to identify at-risk individuals before adverse events. For predicting individual CVD risk, carotid intima-media thickness (CIMT), a noninvasive ultrasound method, has proven to be valuable, offering several advantages over CT coronary artery calcium score. However, each CIMT examination includes several ultrasound videos, and interpreting each of these CIMT videos involves three operations: (1) select three end-diastolic ultrasound frames (EUF) in the video, (2) localize a region of interest (ROI) in each selected frame, and (3) trace the lumen-intima interface and the media-adventitia interface in each ROI to measure CIMT. These operations are tedious, laborious, and time consuming, a serious limitation that hinders the widespread utilization of CIMT in clinical practice. To overcome this limitation, this paper presents a new system to automate CIMT video interpretation. Our extensive experiments demonstrate that the suggested system performs reliably. The reliable performance is attributable to our unified framework based on convolutional neural networks (CNNs) coupled with our informative image representation and effective post-processing of the CNN outputs, which are uniquely designed for each of the above three operations.",
author = "Shin, {Jae Y.} and Nima Tajbakhsh and {Todd Hurst}, R. and Kendall, {Christopher B.} and Jianming Liang",
year = "2016",
language = "English (US)",
volume = "2016-January",
pages = "2526--2535",
booktitle = "2016 IEEE Conference on Computer Vision and Pattern Recognition, CVPR 2016",
publisher = "IEEE Computer Society",

}

TY - GEN

T1 - Automating carotid intima-media thickness video interpretation with convolutional neural networks

AU - Shin, Jae Y.

AU - Tajbakhsh, Nima

AU - Todd Hurst, R.

AU - Kendall, Christopher B.

AU - Liang, Jianming

PY - 2016

Y1 - 2016

N2 - Cardiovascular disease (CVD) is the leading cause of mortality yet largely preventable, but the key to prevention is to identify at-risk individuals before adverse events. For predicting individual CVD risk, carotid intima-media thickness (CIMT), a noninvasive ultrasound method, has proven to be valuable, offering several advantages over CT coronary artery calcium score. However, each CIMT examination includes several ultrasound videos, and interpreting each of these CIMT videos involves three operations: (1) select three end-diastolic ultrasound frames (EUF) in the video, (2) localize a region of interest (ROI) in each selected frame, and (3) trace the lumen-intima interface and the media-adventitia interface in each ROI to measure CIMT. These operations are tedious, laborious, and time consuming, a serious limitation that hinders the widespread utilization of CIMT in clinical practice. To overcome this limitation, this paper presents a new system to automate CIMT video interpretation. Our extensive experiments demonstrate that the suggested system performs reliably. The reliable performance is attributable to our unified framework based on convolutional neural networks (CNNs) coupled with our informative image representation and effective post-processing of the CNN outputs, which are uniquely designed for each of the above three operations.

AB - Cardiovascular disease (CVD) is the leading cause of mortality yet largely preventable, but the key to prevention is to identify at-risk individuals before adverse events. For predicting individual CVD risk, carotid intima-media thickness (CIMT), a noninvasive ultrasound method, has proven to be valuable, offering several advantages over CT coronary artery calcium score. However, each CIMT examination includes several ultrasound videos, and interpreting each of these CIMT videos involves three operations: (1) select three end-diastolic ultrasound frames (EUF) in the video, (2) localize a region of interest (ROI) in each selected frame, and (3) trace the lumen-intima interface and the media-adventitia interface in each ROI to measure CIMT. These operations are tedious, laborious, and time consuming, a serious limitation that hinders the widespread utilization of CIMT in clinical practice. To overcome this limitation, this paper presents a new system to automate CIMT video interpretation. Our extensive experiments demonstrate that the suggested system performs reliably. The reliable performance is attributable to our unified framework based on convolutional neural networks (CNNs) coupled with our informative image representation and effective post-processing of the CNN outputs, which are uniquely designed for each of the above three operations.

UR - http://www.scopus.com/inward/record.url?scp=84986266392&partnerID=8YFLogxK

UR - http://www.scopus.com/inward/citedby.url?scp=84986266392&partnerID=8YFLogxK

M3 - Conference contribution

VL - 2016-January

SP - 2526

EP - 2535

BT - 2016 IEEE Conference on Computer Vision and Pattern Recognition, CVPR 2016

PB - IEEE Computer Society

ER -