Web-based accurate measurements of carotid lumen diameter and stenosis severity: An ultrasound-based clinical tool for stroke risk assessment during multicenter clinical trials

Luca Saba, Sumit K. Banchhor, Narendra D. Londhe, Tadashi Araki, John R. Laird, Ajay Gupta, Andrew Nicolaides, Jasjit S. Suri

Research output: Contribution to journalArticle

9 Citations (Scopus)

Abstract

Background This pilot study presents a completely automated, novel, smart, cloud-based, point-of-care system for (a) carotid lumen diameter (LD); (b) stenosis severity index (SSI) and (c) total lumen area (TLA) measurement using B-mode ultrasound. The proposed system was (i) validated against manual reading taken by the Neurologist and (ii) benchmarked against the commercially available system. Method One hundred patients (73 M/27 F, mean age: 68 ± 11 years), institutional review board approved, written informed consent, consisted of left/right common carotid artery (200 ultrasound scans) were acquired using a 7.5-MHz linear transducer. Results The measured mean LD for left and right carotids were (in mm): (i) for proposed system (6.49 ± 1.77, 6.66 ± 1.70); and (ii) for manual (6.29 ± 1.79, 6.45 ± 1.63), respectively and coefficient of correlation between cloud-based automated against manual were 0.98 (P < 0.0001) and 0.99 (P < 0.0001), respectively. The corresponding TLA error, Precision-of-Merit, and Figure-of-Merit when measured against the manual were: 4.56 ± 3.54%, 96.18 ± 3.21%, and 96.85%, respectively. The AUC for the receiving operating characteristics for the cloud-based system was: 1.0. Four statistical tests such as: Two-tailed z-test, Mann-Whitney test, Kolmogorov-Smirnov (KS) and one-way ANOVA were performed to demonstrate consistency and reliability. Conclusions The proposed system is reliable, accurate, fast, completely automated, anytime-anywhere solution for multi-center clinical trials and routine vascular screening.

Original languageEnglish (US)
Pages (from-to)306-317
Number of pages12
JournalComputers in Biology and Medicine
Volume91
DOIs
StatePublished - Dec 1 2017
Externally publishedYes

Fingerprint

Risk assessment
Multicenter Studies
Pathologic Constriction
Ultrasonics
Stroke
Point-of-Care Systems
Clinical Trials
Statistical tests
Research Ethics Committees
Common Carotid Artery
Nonparametric Statistics
Analysis of variance (ANOVA)
Informed Consent
Transducers
Area Under Curve
Blood Vessels
Reading
Analysis of Variance
Screening
Neurologists

Keywords

  • Carotid arteries
  • Cloud-based
  • Lumen diameter
  • Stenosis
  • Stroke
  • Total lumen area
  • Ultrasound

ASJC Scopus subject areas

  • Computer Science Applications
  • Health Informatics

Cite this

Web-based accurate measurements of carotid lumen diameter and stenosis severity : An ultrasound-based clinical tool for stroke risk assessment during multicenter clinical trials. / Saba, Luca; Banchhor, Sumit K.; Londhe, Narendra D.; Araki, Tadashi; Laird, John R.; Gupta, Ajay; Nicolaides, Andrew; Suri, Jasjit S.

In: Computers in Biology and Medicine, Vol. 91, 01.12.2017, p. 306-317.

Research output: Contribution to journalArticle

Saba, Luca ; Banchhor, Sumit K. ; Londhe, Narendra D. ; Araki, Tadashi ; Laird, John R. ; Gupta, Ajay ; Nicolaides, Andrew ; Suri, Jasjit S. / Web-based accurate measurements of carotid lumen diameter and stenosis severity : An ultrasound-based clinical tool for stroke risk assessment during multicenter clinical trials. In: Computers in Biology and Medicine. 2017 ; Vol. 91. pp. 306-317.
@article{cf44a6ee3b784e65a0dbdb7b30833853,
title = "Web-based accurate measurements of carotid lumen diameter and stenosis severity: An ultrasound-based clinical tool for stroke risk assessment during multicenter clinical trials",
abstract = "Background This pilot study presents a completely automated, novel, smart, cloud-based, point-of-care system for (a) carotid lumen diameter (LD); (b) stenosis severity index (SSI) and (c) total lumen area (TLA) measurement using B-mode ultrasound. The proposed system was (i) validated against manual reading taken by the Neurologist and (ii) benchmarked against the commercially available system. Method One hundred patients (73 M/27 F, mean age: 68 ± 11 years), institutional review board approved, written informed consent, consisted of left/right common carotid artery (200 ultrasound scans) were acquired using a 7.5-MHz linear transducer. Results The measured mean LD for left and right carotids were (in mm): (i) for proposed system (6.49 ± 1.77, 6.66 ± 1.70); and (ii) for manual (6.29 ± 1.79, 6.45 ± 1.63), respectively and coefficient of correlation between cloud-based automated against manual were 0.98 (P < 0.0001) and 0.99 (P < 0.0001), respectively. The corresponding TLA error, Precision-of-Merit, and Figure-of-Merit when measured against the manual were: 4.56 ± 3.54{\%}, 96.18 ± 3.21{\%}, and 96.85{\%}, respectively. The AUC for the receiving operating characteristics for the cloud-based system was: 1.0. Four statistical tests such as: Two-tailed z-test, Mann-Whitney test, Kolmogorov-Smirnov (KS) and one-way ANOVA were performed to demonstrate consistency and reliability. Conclusions The proposed system is reliable, accurate, fast, completely automated, anytime-anywhere solution for multi-center clinical trials and routine vascular screening.",
keywords = "Carotid arteries, Cloud-based, Lumen diameter, Stenosis, Stroke, Total lumen area, Ultrasound",
author = "Luca Saba and Banchhor, {Sumit K.} and Londhe, {Narendra D.} and Tadashi Araki and Laird, {John R.} and Ajay Gupta and Andrew Nicolaides and Suri, {Jasjit S.}",
year = "2017",
month = "12",
day = "1",
doi = "10.1016/j.compbiomed.2017.10.022",
language = "English (US)",
volume = "91",
pages = "306--317",
journal = "Computers in Biology and Medicine",
issn = "0010-4825",
publisher = "Elsevier Limited",

}

TY - JOUR

T1 - Web-based accurate measurements of carotid lumen diameter and stenosis severity

T2 - An ultrasound-based clinical tool for stroke risk assessment during multicenter clinical trials

AU - Saba, Luca

AU - Banchhor, Sumit K.

AU - Londhe, Narendra D.

AU - Araki, Tadashi

AU - Laird, John R.

AU - Gupta, Ajay

AU - Nicolaides, Andrew

AU - Suri, Jasjit S.

PY - 2017/12/1

Y1 - 2017/12/1

N2 - Background This pilot study presents a completely automated, novel, smart, cloud-based, point-of-care system for (a) carotid lumen diameter (LD); (b) stenosis severity index (SSI) and (c) total lumen area (TLA) measurement using B-mode ultrasound. The proposed system was (i) validated against manual reading taken by the Neurologist and (ii) benchmarked against the commercially available system. Method One hundred patients (73 M/27 F, mean age: 68 ± 11 years), institutional review board approved, written informed consent, consisted of left/right common carotid artery (200 ultrasound scans) were acquired using a 7.5-MHz linear transducer. Results The measured mean LD for left and right carotids were (in mm): (i) for proposed system (6.49 ± 1.77, 6.66 ± 1.70); and (ii) for manual (6.29 ± 1.79, 6.45 ± 1.63), respectively and coefficient of correlation between cloud-based automated against manual were 0.98 (P < 0.0001) and 0.99 (P < 0.0001), respectively. The corresponding TLA error, Precision-of-Merit, and Figure-of-Merit when measured against the manual were: 4.56 ± 3.54%, 96.18 ± 3.21%, and 96.85%, respectively. The AUC for the receiving operating characteristics for the cloud-based system was: 1.0. Four statistical tests such as: Two-tailed z-test, Mann-Whitney test, Kolmogorov-Smirnov (KS) and one-way ANOVA were performed to demonstrate consistency and reliability. Conclusions The proposed system is reliable, accurate, fast, completely automated, anytime-anywhere solution for multi-center clinical trials and routine vascular screening.

AB - Background This pilot study presents a completely automated, novel, smart, cloud-based, point-of-care system for (a) carotid lumen diameter (LD); (b) stenosis severity index (SSI) and (c) total lumen area (TLA) measurement using B-mode ultrasound. The proposed system was (i) validated against manual reading taken by the Neurologist and (ii) benchmarked against the commercially available system. Method One hundred patients (73 M/27 F, mean age: 68 ± 11 years), institutional review board approved, written informed consent, consisted of left/right common carotid artery (200 ultrasound scans) were acquired using a 7.5-MHz linear transducer. Results The measured mean LD for left and right carotids were (in mm): (i) for proposed system (6.49 ± 1.77, 6.66 ± 1.70); and (ii) for manual (6.29 ± 1.79, 6.45 ± 1.63), respectively and coefficient of correlation between cloud-based automated against manual were 0.98 (P < 0.0001) and 0.99 (P < 0.0001), respectively. The corresponding TLA error, Precision-of-Merit, and Figure-of-Merit when measured against the manual were: 4.56 ± 3.54%, 96.18 ± 3.21%, and 96.85%, respectively. The AUC for the receiving operating characteristics for the cloud-based system was: 1.0. Four statistical tests such as: Two-tailed z-test, Mann-Whitney test, Kolmogorov-Smirnov (KS) and one-way ANOVA were performed to demonstrate consistency and reliability. Conclusions The proposed system is reliable, accurate, fast, completely automated, anytime-anywhere solution for multi-center clinical trials and routine vascular screening.

KW - Carotid arteries

KW - Cloud-based

KW - Lumen diameter

KW - Stenosis

KW - Stroke

KW - Total lumen area

KW - Ultrasound

UR - http://www.scopus.com/inward/record.url?scp=85032724962&partnerID=8YFLogxK

UR - http://www.scopus.com/inward/citedby.url?scp=85032724962&partnerID=8YFLogxK

U2 - 10.1016/j.compbiomed.2017.10.022

DO - 10.1016/j.compbiomed.2017.10.022

M3 - Article

AN - SCOPUS:85032724962

VL - 91

SP - 306

EP - 317

JO - Computers in Biology and Medicine

JF - Computers in Biology and Medicine

SN - 0010-4825

ER -