Forskning ved Københavns Universitet - Københavns Universitet

Forside

Longitudinal assessment of carotid plaque texture in three-dimensional ultrasound images based on semi-supervised graph-based dimensionality reduction and feature selection

Publikation: Bidrag til tidsskriftTidsskriftartikel

Standard

Longitudinal assessment of carotid plaque texture in three-dimensional ultrasound images based on semi-supervised graph-based dimensionality reduction and feature selection. / Lin, Mingquan; Cui, He; Chen, Weifu; van Engelen, Arna; de Bruijne, Marleen; Azarpazhooh, M. Reza; Sohrevardi, Seyed Mojtaba; Spence, J. David; Chiu, Bernard.

I: Computers in Biology and Medicine, Bind 116, 103586, 01.2020.

Publikation: Bidrag til tidsskriftTidsskriftartikel

Harvard

Lin, M, Cui, H, Chen, W, van Engelen, A, de Bruijne, M, Azarpazhooh, MR, Sohrevardi, SM, Spence, JD & Chiu, B 2020, 'Longitudinal assessment of carotid plaque texture in three-dimensional ultrasound images based on semi-supervised graph-based dimensionality reduction and feature selection', Computers in Biology and Medicine, bind 116, 103586. https://doi.org/10.1016/j.compbiomed.2019.103586

APA

Lin, M., Cui, H., Chen, W., van Engelen, A., de Bruijne, M., Azarpazhooh, M. R., ... Chiu, B. (2020). Longitudinal assessment of carotid plaque texture in three-dimensional ultrasound images based on semi-supervised graph-based dimensionality reduction and feature selection. Computers in Biology and Medicine, 116, [103586]. https://doi.org/10.1016/j.compbiomed.2019.103586

Vancouver

Lin M, Cui H, Chen W, van Engelen A, de Bruijne M, Azarpazhooh MR o.a. Longitudinal assessment of carotid plaque texture in three-dimensional ultrasound images based on semi-supervised graph-based dimensionality reduction and feature selection. Computers in Biology and Medicine. 2020 jan;116. 103586. https://doi.org/10.1016/j.compbiomed.2019.103586

Author

Lin, Mingquan ; Cui, He ; Chen, Weifu ; van Engelen, Arna ; de Bruijne, Marleen ; Azarpazhooh, M. Reza ; Sohrevardi, Seyed Mojtaba ; Spence, J. David ; Chiu, Bernard. / Longitudinal assessment of carotid plaque texture in three-dimensional ultrasound images based on semi-supervised graph-based dimensionality reduction and feature selection. I: Computers in Biology and Medicine. 2020 ; Bind 116.

Bibtex

@article{196ad98082ec4e40a37b67c081dfdc10,
title = "Longitudinal assessment of carotid plaque texture in three-dimensional ultrasound images based on semi-supervised graph-based dimensionality reduction and feature selection",
abstract = "With continuous development of therapeutic options for atherosclerosis, image-based biomarkers sensitive to the effect of new interventions are required to be developed for cost-effective clinical evaluation. Although 3D ultrasound measurement of total plaque volume (TPV) showed the efficacy of high-dose statin, more sensitive biomarkers are needed to establish the efficacy of dietary supplements expected to confer a smaller beneficial effect. This study involved 171 subjects who participated in a one-year placebo-controlled trial evaluating the effect of pomegranate. A framework involving a feature selection technique known as discriminative feature selection (DFS) and a semi-supervised graph-based regression (SSGBR) technique was proposed for sensitive detection of plaque textural changes over the trial. 376 textual features of plaques were extracted from 3D ultrasound images acquired at baseline and a follow-up session. A scalar biomarker for each subject were generated by SSGBR based on prominent textural features selected by DFS. The ability of this biomarker for discriminating pomegranate from placebo subjects was quantified by the p-values obtained in Mann–Whitney U test. The discriminative power of SSGBR was compared with global and local dimensionality reduction techniques, including linear discriminant analysis (LDA), maximum margin criterion (MMC) and Laplacian Eigenmap (LE). Only SSGBR (p=4.12×10−6) and normalized LE (p=0.002) detected a difference between the two groups at the 5{\%} significance level. As compared with ΔTPV, SSGBR reduced the sample size required to establish a significant difference by a factor of 60. The application of this framework will substantially reduce the cost incurred in clinical trials.",
keywords = "3D ultrasound imaging, Carotid atherosclerosis, Discriminative feature selection (DFS), Plaque texture, Pomegranate therapy, Semi-supervised graph-based regression (SSGBR)",
author = "Mingquan Lin and He Cui and Weifu Chen and {van Engelen}, Arna and {de Bruijne}, Marleen and Azarpazhooh, {M. Reza} and Sohrevardi, {Seyed Mojtaba} and Spence, {J. David} and Bernard Chiu",
year = "2020",
month = "1",
doi = "10.1016/j.compbiomed.2019.103586",
language = "English",
volume = "116",
journal = "Computers in Biology and Medicine",
issn = "0010-4825",
publisher = "Pergamon Press",

}

RIS

TY - JOUR

T1 - Longitudinal assessment of carotid plaque texture in three-dimensional ultrasound images based on semi-supervised graph-based dimensionality reduction and feature selection

AU - Lin, Mingquan

AU - Cui, He

AU - Chen, Weifu

AU - van Engelen, Arna

AU - de Bruijne, Marleen

AU - Azarpazhooh, M. Reza

AU - Sohrevardi, Seyed Mojtaba

AU - Spence, J. David

AU - Chiu, Bernard

PY - 2020/1

Y1 - 2020/1

N2 - With continuous development of therapeutic options for atherosclerosis, image-based biomarkers sensitive to the effect of new interventions are required to be developed for cost-effective clinical evaluation. Although 3D ultrasound measurement of total plaque volume (TPV) showed the efficacy of high-dose statin, more sensitive biomarkers are needed to establish the efficacy of dietary supplements expected to confer a smaller beneficial effect. This study involved 171 subjects who participated in a one-year placebo-controlled trial evaluating the effect of pomegranate. A framework involving a feature selection technique known as discriminative feature selection (DFS) and a semi-supervised graph-based regression (SSGBR) technique was proposed for sensitive detection of plaque textural changes over the trial. 376 textual features of plaques were extracted from 3D ultrasound images acquired at baseline and a follow-up session. A scalar biomarker for each subject were generated by SSGBR based on prominent textural features selected by DFS. The ability of this biomarker for discriminating pomegranate from placebo subjects was quantified by the p-values obtained in Mann–Whitney U test. The discriminative power of SSGBR was compared with global and local dimensionality reduction techniques, including linear discriminant analysis (LDA), maximum margin criterion (MMC) and Laplacian Eigenmap (LE). Only SSGBR (p=4.12×10−6) and normalized LE (p=0.002) detected a difference between the two groups at the 5% significance level. As compared with ΔTPV, SSGBR reduced the sample size required to establish a significant difference by a factor of 60. The application of this framework will substantially reduce the cost incurred in clinical trials.

AB - With continuous development of therapeutic options for atherosclerosis, image-based biomarkers sensitive to the effect of new interventions are required to be developed for cost-effective clinical evaluation. Although 3D ultrasound measurement of total plaque volume (TPV) showed the efficacy of high-dose statin, more sensitive biomarkers are needed to establish the efficacy of dietary supplements expected to confer a smaller beneficial effect. This study involved 171 subjects who participated in a one-year placebo-controlled trial evaluating the effect of pomegranate. A framework involving a feature selection technique known as discriminative feature selection (DFS) and a semi-supervised graph-based regression (SSGBR) technique was proposed for sensitive detection of plaque textural changes over the trial. 376 textual features of plaques were extracted from 3D ultrasound images acquired at baseline and a follow-up session. A scalar biomarker for each subject were generated by SSGBR based on prominent textural features selected by DFS. The ability of this biomarker for discriminating pomegranate from placebo subjects was quantified by the p-values obtained in Mann–Whitney U test. The discriminative power of SSGBR was compared with global and local dimensionality reduction techniques, including linear discriminant analysis (LDA), maximum margin criterion (MMC) and Laplacian Eigenmap (LE). Only SSGBR (p=4.12×10−6) and normalized LE (p=0.002) detected a difference between the two groups at the 5% significance level. As compared with ΔTPV, SSGBR reduced the sample size required to establish a significant difference by a factor of 60. The application of this framework will substantially reduce the cost incurred in clinical trials.

KW - 3D ultrasound imaging

KW - Carotid atherosclerosis

KW - Discriminative feature selection (DFS)

KW - Plaque texture

KW - Pomegranate therapy

KW - Semi-supervised graph-based regression (SSGBR)

UR - http://www.scopus.com/inward/record.url?scp=85076635390&partnerID=8YFLogxK

U2 - 10.1016/j.compbiomed.2019.103586

DO - 10.1016/j.compbiomed.2019.103586

M3 - Journal article

AN - SCOPUS:85076635390

VL - 116

JO - Computers in Biology and Medicine

JF - Computers in Biology and Medicine

SN - 0010-4825

M1 - 103586

ER -

ID: 233538237