Narrowing of the Middle Cerebral Artery: Artificial Intelligence Methods and Comparison of Transcranial Color Coded Duplex Sonography with Conventional TCD

Miroslaw Swiercz, Maciej Swiat, Mikolaj Pawlak, John Weigele, Roman Tarasewicz, Andrzej Sobolewski, Robert W. Hurst, Zenon D. Mariak, Elias R. Melhem, Jaroslaw Krejza

Research output: Contribution to journalArticle

Abstract

The goal of the study was to compare performances of transcranial color-coded duplex sonography (TCCS) and transcranial Doppler sonography (TCD) in the diagnosis of the middle cerebral artery (MCA) narrowing in the same population of patients using statistical and nonstatistical intelligent models for data analysis. We prospectively collected data from 179 consecutive routine digital subtraction angiography (DSA) procedures performed in 111 patients (mean age 54.17 ± 14.4 years; 59 women, 52 men) who underwent TCD and TCCS examinations simultaneously. Each patient was examined independently using both ultrasound techniques, 267 M1 segments of MCA were assessed and narrowings were classified as ≤50% and >50% lumen reduction. Diagnostic performance was estimated by two statistical and two artificial neural networks (ANN) classification methods. Separate models were constructed for the TCD and TCCS sonographic data, as well as for detection of "any narrowing" and "severe narrowing" of the MCA. Input for each classifier consisted of the peak-systolic, mean and end-diastolic velocities measured with each sonographic method; the output was MCA narrowing. Arterial narrowings less or equal 50% of lumen reduction were found in 55 and >50% narrowings in 26 out of 267 arteries, as indicated by DSA. In the category of "any narrowing" the rate of correct assignment by all models was 82% to 83% for TCCS and 79% to 81% for TCD. In the diagnosis of >50% narrowing the overall classification accuracy remained in the range of 89% to 90% for TCCS data and 90% to 91% for TCD data. For the diagnosis of any narrowing, the sensitivity of the TCCS was significantly higher than that of the TCD, while for diagnosis of >50% MCA narrowing, sensitivity of the TCCS was similar to sensitivity of the TCD. Our study showed that TCCS outperforms conventional TCD in detection of ≤50% MCA narrowing, whereas no significant difference in accuracy between both methods was found in the diagnosis of >50% MCA narrowing. (E-mail: jaroslaw.krejza@uphs.upenn.edu).

Original languageEnglish (US)
Pages (from-to)17-28
Number of pages12
JournalUltrasound in Medicine and Biology
Volume36
Issue number1
DOIs
StatePublished - Jan 2010
Externally publishedYes

Fingerprint

Doppler Transcranial Ultrasonography
artificial intelligence
Artificial Intelligence
Middle Cerebral Artery
arteries
Ultrasonography
Color
color
Digital Subtraction Angiography
lumens
angiography
subtraction
sensitivity
classifiers
Arteries
examination
output

Keywords

  • Artificial neural networks
  • MCA narrowing
  • Transcranial Doppler sonography

ASJC Scopus subject areas

  • Radiology Nuclear Medicine and imaging
  • Radiological and Ultrasound Technology
  • Biophysics

Cite this

Narrowing of the Middle Cerebral Artery : Artificial Intelligence Methods and Comparison of Transcranial Color Coded Duplex Sonography with Conventional TCD. / Swiercz, Miroslaw; Swiat, Maciej; Pawlak, Mikolaj; Weigele, John; Tarasewicz, Roman; Sobolewski, Andrzej; Hurst, Robert W.; Mariak, Zenon D.; Melhem, Elias R.; Krejza, Jaroslaw.

In: Ultrasound in Medicine and Biology, Vol. 36, No. 1, 01.2010, p. 17-28.

Research output: Contribution to journalArticle

Swiercz, M, Swiat, M, Pawlak, M, Weigele, J, Tarasewicz, R, Sobolewski, A, Hurst, RW, Mariak, ZD, Melhem, ER & Krejza, J 2010, 'Narrowing of the Middle Cerebral Artery: Artificial Intelligence Methods and Comparison of Transcranial Color Coded Duplex Sonography with Conventional TCD', Ultrasound in Medicine and Biology, vol. 36, no. 1, pp. 17-28. https://doi.org/10.1016/j.ultrasmedbio.2009.05.005
Swiercz, Miroslaw ; Swiat, Maciej ; Pawlak, Mikolaj ; Weigele, John ; Tarasewicz, Roman ; Sobolewski, Andrzej ; Hurst, Robert W. ; Mariak, Zenon D. ; Melhem, Elias R. ; Krejza, Jaroslaw. / Narrowing of the Middle Cerebral Artery : Artificial Intelligence Methods and Comparison of Transcranial Color Coded Duplex Sonography with Conventional TCD. In: Ultrasound in Medicine and Biology. 2010 ; Vol. 36, No. 1. pp. 17-28.
@article{7e1cb9b6eee54acca3a76790a3475e8b,
title = "Narrowing of the Middle Cerebral Artery: Artificial Intelligence Methods and Comparison of Transcranial Color Coded Duplex Sonography with Conventional TCD",
abstract = "The goal of the study was to compare performances of transcranial color-coded duplex sonography (TCCS) and transcranial Doppler sonography (TCD) in the diagnosis of the middle cerebral artery (MCA) narrowing in the same population of patients using statistical and nonstatistical intelligent models for data analysis. We prospectively collected data from 179 consecutive routine digital subtraction angiography (DSA) procedures performed in 111 patients (mean age 54.17 ± 14.4 years; 59 women, 52 men) who underwent TCD and TCCS examinations simultaneously. Each patient was examined independently using both ultrasound techniques, 267 M1 segments of MCA were assessed and narrowings were classified as ≤50{\%} and >50{\%} lumen reduction. Diagnostic performance was estimated by two statistical and two artificial neural networks (ANN) classification methods. Separate models were constructed for the TCD and TCCS sonographic data, as well as for detection of {"}any narrowing{"} and {"}severe narrowing{"} of the MCA. Input for each classifier consisted of the peak-systolic, mean and end-diastolic velocities measured with each sonographic method; the output was MCA narrowing. Arterial narrowings less or equal 50{\%} of lumen reduction were found in 55 and >50{\%} narrowings in 26 out of 267 arteries, as indicated by DSA. In the category of {"}any narrowing{"} the rate of correct assignment by all models was 82{\%} to 83{\%} for TCCS and 79{\%} to 81{\%} for TCD. In the diagnosis of >50{\%} narrowing the overall classification accuracy remained in the range of 89{\%} to 90{\%} for TCCS data and 90{\%} to 91{\%} for TCD data. For the diagnosis of any narrowing, the sensitivity of the TCCS was significantly higher than that of the TCD, while for diagnosis of >50{\%} MCA narrowing, sensitivity of the TCCS was similar to sensitivity of the TCD. Our study showed that TCCS outperforms conventional TCD in detection of ≤50{\%} MCA narrowing, whereas no significant difference in accuracy between both methods was found in the diagnosis of >50{\%} MCA narrowing. (E-mail: jaroslaw.krejza@uphs.upenn.edu).",
keywords = "Artificial neural networks, MCA narrowing, Transcranial Doppler sonography",
author = "Miroslaw Swiercz and Maciej Swiat and Mikolaj Pawlak and John Weigele and Roman Tarasewicz and Andrzej Sobolewski and Hurst, {Robert W.} and Mariak, {Zenon D.} and Melhem, {Elias R.} and Jaroslaw Krejza",
year = "2010",
month = "1",
doi = "10.1016/j.ultrasmedbio.2009.05.005",
language = "English (US)",
volume = "36",
pages = "17--28",
journal = "Ultrasound in Medicine and Biology",
issn = "0301-5629",
publisher = "Elsevier USA",
number = "1",

}

TY - JOUR

T1 - Narrowing of the Middle Cerebral Artery

T2 - Artificial Intelligence Methods and Comparison of Transcranial Color Coded Duplex Sonography with Conventional TCD

AU - Swiercz, Miroslaw

AU - Swiat, Maciej

AU - Pawlak, Mikolaj

AU - Weigele, John

AU - Tarasewicz, Roman

AU - Sobolewski, Andrzej

AU - Hurst, Robert W.

AU - Mariak, Zenon D.

AU - Melhem, Elias R.

AU - Krejza, Jaroslaw

PY - 2010/1

Y1 - 2010/1

N2 - The goal of the study was to compare performances of transcranial color-coded duplex sonography (TCCS) and transcranial Doppler sonography (TCD) in the diagnosis of the middle cerebral artery (MCA) narrowing in the same population of patients using statistical and nonstatistical intelligent models for data analysis. We prospectively collected data from 179 consecutive routine digital subtraction angiography (DSA) procedures performed in 111 patients (mean age 54.17 ± 14.4 years; 59 women, 52 men) who underwent TCD and TCCS examinations simultaneously. Each patient was examined independently using both ultrasound techniques, 267 M1 segments of MCA were assessed and narrowings were classified as ≤50% and >50% lumen reduction. Diagnostic performance was estimated by two statistical and two artificial neural networks (ANN) classification methods. Separate models were constructed for the TCD and TCCS sonographic data, as well as for detection of "any narrowing" and "severe narrowing" of the MCA. Input for each classifier consisted of the peak-systolic, mean and end-diastolic velocities measured with each sonographic method; the output was MCA narrowing. Arterial narrowings less or equal 50% of lumen reduction were found in 55 and >50% narrowings in 26 out of 267 arteries, as indicated by DSA. In the category of "any narrowing" the rate of correct assignment by all models was 82% to 83% for TCCS and 79% to 81% for TCD. In the diagnosis of >50% narrowing the overall classification accuracy remained in the range of 89% to 90% for TCCS data and 90% to 91% for TCD data. For the diagnosis of any narrowing, the sensitivity of the TCCS was significantly higher than that of the TCD, while for diagnosis of >50% MCA narrowing, sensitivity of the TCCS was similar to sensitivity of the TCD. Our study showed that TCCS outperforms conventional TCD in detection of ≤50% MCA narrowing, whereas no significant difference in accuracy between both methods was found in the diagnosis of >50% MCA narrowing. (E-mail: jaroslaw.krejza@uphs.upenn.edu).

AB - The goal of the study was to compare performances of transcranial color-coded duplex sonography (TCCS) and transcranial Doppler sonography (TCD) in the diagnosis of the middle cerebral artery (MCA) narrowing in the same population of patients using statistical and nonstatistical intelligent models for data analysis. We prospectively collected data from 179 consecutive routine digital subtraction angiography (DSA) procedures performed in 111 patients (mean age 54.17 ± 14.4 years; 59 women, 52 men) who underwent TCD and TCCS examinations simultaneously. Each patient was examined independently using both ultrasound techniques, 267 M1 segments of MCA were assessed and narrowings were classified as ≤50% and >50% lumen reduction. Diagnostic performance was estimated by two statistical and two artificial neural networks (ANN) classification methods. Separate models were constructed for the TCD and TCCS sonographic data, as well as for detection of "any narrowing" and "severe narrowing" of the MCA. Input for each classifier consisted of the peak-systolic, mean and end-diastolic velocities measured with each sonographic method; the output was MCA narrowing. Arterial narrowings less or equal 50% of lumen reduction were found in 55 and >50% narrowings in 26 out of 267 arteries, as indicated by DSA. In the category of "any narrowing" the rate of correct assignment by all models was 82% to 83% for TCCS and 79% to 81% for TCD. In the diagnosis of >50% narrowing the overall classification accuracy remained in the range of 89% to 90% for TCCS data and 90% to 91% for TCD data. For the diagnosis of any narrowing, the sensitivity of the TCCS was significantly higher than that of the TCD, while for diagnosis of >50% MCA narrowing, sensitivity of the TCCS was similar to sensitivity of the TCD. Our study showed that TCCS outperforms conventional TCD in detection of ≤50% MCA narrowing, whereas no significant difference in accuracy between both methods was found in the diagnosis of >50% MCA narrowing. (E-mail: jaroslaw.krejza@uphs.upenn.edu).

KW - Artificial neural networks

KW - MCA narrowing

KW - Transcranial Doppler sonography

UR - http://www.scopus.com/inward/record.url?scp=71849109787&partnerID=8YFLogxK

UR - http://www.scopus.com/inward/citedby.url?scp=71849109787&partnerID=8YFLogxK

U2 - 10.1016/j.ultrasmedbio.2009.05.005

DO - 10.1016/j.ultrasmedbio.2009.05.005

M3 - Article

C2 - 19854564

AN - SCOPUS:71849109787

VL - 36

SP - 17

EP - 28

JO - Ultrasound in Medicine and Biology

JF - Ultrasound in Medicine and Biology

SN - 0301-5629

IS - 1

ER -