ECG-based frame selection and curvature-based ROI detection for measuring carotid intima-media thickness

Haripriya Sharma, Ramsri G. Golla, Yu Zhang, Christopher B. Kendall, R. Todd Hurst, Nima Tajbakhsh, Jianming Liang

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

3 Citations (Scopus)

Abstract

Carotid intima-media thickness (CIMT) has proven to be sensitive for predicting individual risk of cardiovascular diseases (CVD). The CIMT is measured based on region of interest (ROIs) in end-diastolic ultrasound frames (EUFs). To interpret CIMT videos, in the current practice, the EUFs and ROIs must be manually selected, a process that is tedious and time consuming. To reduce CIMT interpretation time, this paper presents a novel method for automatically selecting EUFs and determining ROIs in ultrasound videos. The EUFs are selected based on the QRS complex of the electrocardiogram (ECG) signal associated with the ultrasound video, and the ROI is detected based on image intensity and curvature of the carotid artery bulb. Once a EUF is selected and its corresponding ROI is determined, our system measures CIMT using the snake algorithm extended with hard constraints [1,6-7] by computing the average thickness and maximum thickness, calculating the vascular age, and generating a patient report. In this study, we utilize 23 subjects. Each subject has 4 videos, and 3 EUFs are selected in each video, resulting in a total of 272 ROIs. By comparing with the reference provided by an expert for both frame selection and ROI detection, we achieve 92.96% sensitivity and 97.62% specificity for EUF selection, and 81.25% accuracy in ROI detection.

Original languageEnglish (US)
Title of host publicationProgress in Biomedical Optics and Imaging - Proceedings of SPIE
PublisherSPIE
Volume9040
ISBN (Print)9780819498335
DOIs
StatePublished - 2014
EventMedical Imaging 2014: Ultrasonic Imaging and Tomography - San Diego, CA, United States
Duration: Feb 18 2014Feb 20 2014

Other

OtherMedical Imaging 2014: Ultrasonic Imaging and Tomography
CountryUnited States
CitySan Diego, CA
Period2/18/142/20/14

Fingerprint

electrocardiography
Carotid Intima-Media Thickness
Electrocardiography
Ultrasonics
curvature
Snakes
Carotid Arteries
Blood Vessels
Cardiovascular Diseases
snakes
bulbs
Sensitivity and Specificity
arteries
sensitivity

Keywords

  • cardiovascular disease
  • carotid artery bulb
  • Carotid intima-media thickness (CIMT)
  • common carotid artery (CCA)
  • end-diastolic ultrasound frame
  • snakes: active contour models

ASJC Scopus subject areas

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

Cite this

Sharma, H., Golla, R. G., Zhang, Y., Kendall, C. B., Hurst, R. T., Tajbakhsh, N., & Liang, J. (2014). ECG-based frame selection and curvature-based ROI detection for measuring carotid intima-media thickness. In Progress in Biomedical Optics and Imaging - Proceedings of SPIE (Vol. 9040). [904016] SPIE. https://doi.org/10.1117/12.2043612

ECG-based frame selection and curvature-based ROI detection for measuring carotid intima-media thickness. / Sharma, Haripriya; Golla, Ramsri G.; Zhang, Yu; Kendall, Christopher B.; Hurst, R. Todd; Tajbakhsh, Nima; Liang, Jianming.

Progress in Biomedical Optics and Imaging - Proceedings of SPIE. Vol. 9040 SPIE, 2014. 904016.

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

Sharma, H, Golla, RG, Zhang, Y, Kendall, CB, Hurst, RT, Tajbakhsh, N & Liang, J 2014, ECG-based frame selection and curvature-based ROI detection for measuring carotid intima-media thickness. in Progress in Biomedical Optics and Imaging - Proceedings of SPIE. vol. 9040, 904016, SPIE, Medical Imaging 2014: Ultrasonic Imaging and Tomography, San Diego, CA, United States, 2/18/14. https://doi.org/10.1117/12.2043612
Sharma H, Golla RG, Zhang Y, Kendall CB, Hurst RT, Tajbakhsh N et al. ECG-based frame selection and curvature-based ROI detection for measuring carotid intima-media thickness. In Progress in Biomedical Optics and Imaging - Proceedings of SPIE. Vol. 9040. SPIE. 2014. 904016 https://doi.org/10.1117/12.2043612
Sharma, Haripriya ; Golla, Ramsri G. ; Zhang, Yu ; Kendall, Christopher B. ; Hurst, R. Todd ; Tajbakhsh, Nima ; Liang, Jianming. / ECG-based frame selection and curvature-based ROI detection for measuring carotid intima-media thickness. Progress in Biomedical Optics and Imaging - Proceedings of SPIE. Vol. 9040 SPIE, 2014.
@inproceedings{f2ebb198e43c4d3297f6c139d1517f1b,
title = "ECG-based frame selection and curvature-based ROI detection for measuring carotid intima-media thickness",
abstract = "Carotid intima-media thickness (CIMT) has proven to be sensitive for predicting individual risk of cardiovascular diseases (CVD). The CIMT is measured based on region of interest (ROIs) in end-diastolic ultrasound frames (EUFs). To interpret CIMT videos, in the current practice, the EUFs and ROIs must be manually selected, a process that is tedious and time consuming. To reduce CIMT interpretation time, this paper presents a novel method for automatically selecting EUFs and determining ROIs in ultrasound videos. The EUFs are selected based on the QRS complex of the electrocardiogram (ECG) signal associated with the ultrasound video, and the ROI is detected based on image intensity and curvature of the carotid artery bulb. Once a EUF is selected and its corresponding ROI is determined, our system measures CIMT using the snake algorithm extended with hard constraints [1,6-7] by computing the average thickness and maximum thickness, calculating the vascular age, and generating a patient report. In this study, we utilize 23 subjects. Each subject has 4 videos, and 3 EUFs are selected in each video, resulting in a total of 272 ROIs. By comparing with the reference provided by an expert for both frame selection and ROI detection, we achieve 92.96{\%} sensitivity and 97.62{\%} specificity for EUF selection, and 81.25{\%} accuracy in ROI detection.",
keywords = "cardiovascular disease, carotid artery bulb, Carotid intima-media thickness (CIMT), common carotid artery (CCA), end-diastolic ultrasound frame, snakes: active contour models",
author = "Haripriya Sharma and Golla, {Ramsri G.} and Yu Zhang and Kendall, {Christopher B.} and Hurst, {R. Todd} and Nima Tajbakhsh and Jianming Liang",
year = "2014",
doi = "10.1117/12.2043612",
language = "English (US)",
isbn = "9780819498335",
volume = "9040",
booktitle = "Progress in Biomedical Optics and Imaging - Proceedings of SPIE",
publisher = "SPIE",

}

TY - GEN

T1 - ECG-based frame selection and curvature-based ROI detection for measuring carotid intima-media thickness

AU - Sharma, Haripriya

AU - Golla, Ramsri G.

AU - Zhang, Yu

AU - Kendall, Christopher B.

AU - Hurst, R. Todd

AU - Tajbakhsh, Nima

AU - Liang, Jianming

PY - 2014

Y1 - 2014

N2 - Carotid intima-media thickness (CIMT) has proven to be sensitive for predicting individual risk of cardiovascular diseases (CVD). The CIMT is measured based on region of interest (ROIs) in end-diastolic ultrasound frames (EUFs). To interpret CIMT videos, in the current practice, the EUFs and ROIs must be manually selected, a process that is tedious and time consuming. To reduce CIMT interpretation time, this paper presents a novel method for automatically selecting EUFs and determining ROIs in ultrasound videos. The EUFs are selected based on the QRS complex of the electrocardiogram (ECG) signal associated with the ultrasound video, and the ROI is detected based on image intensity and curvature of the carotid artery bulb. Once a EUF is selected and its corresponding ROI is determined, our system measures CIMT using the snake algorithm extended with hard constraints [1,6-7] by computing the average thickness and maximum thickness, calculating the vascular age, and generating a patient report. In this study, we utilize 23 subjects. Each subject has 4 videos, and 3 EUFs are selected in each video, resulting in a total of 272 ROIs. By comparing with the reference provided by an expert for both frame selection and ROI detection, we achieve 92.96% sensitivity and 97.62% specificity for EUF selection, and 81.25% accuracy in ROI detection.

AB - Carotid intima-media thickness (CIMT) has proven to be sensitive for predicting individual risk of cardiovascular diseases (CVD). The CIMT is measured based on region of interest (ROIs) in end-diastolic ultrasound frames (EUFs). To interpret CIMT videos, in the current practice, the EUFs and ROIs must be manually selected, a process that is tedious and time consuming. To reduce CIMT interpretation time, this paper presents a novel method for automatically selecting EUFs and determining ROIs in ultrasound videos. The EUFs are selected based on the QRS complex of the electrocardiogram (ECG) signal associated with the ultrasound video, and the ROI is detected based on image intensity and curvature of the carotid artery bulb. Once a EUF is selected and its corresponding ROI is determined, our system measures CIMT using the snake algorithm extended with hard constraints [1,6-7] by computing the average thickness and maximum thickness, calculating the vascular age, and generating a patient report. In this study, we utilize 23 subjects. Each subject has 4 videos, and 3 EUFs are selected in each video, resulting in a total of 272 ROIs. By comparing with the reference provided by an expert for both frame selection and ROI detection, we achieve 92.96% sensitivity and 97.62% specificity for EUF selection, and 81.25% accuracy in ROI detection.

KW - cardiovascular disease

KW - carotid artery bulb

KW - Carotid intima-media thickness (CIMT)

KW - common carotid artery (CCA)

KW - end-diastolic ultrasound frame

KW - snakes: active contour models

UR - http://www.scopus.com/inward/record.url?scp=84901792305&partnerID=8YFLogxK

UR - http://www.scopus.com/inward/citedby.url?scp=84901792305&partnerID=8YFLogxK

U2 - 10.1117/12.2043612

DO - 10.1117/12.2043612

M3 - Conference contribution

SN - 9780819498335

VL - 9040

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

PB - SPIE

ER -