Three-dimensional ultrasound evaluation of the effects of pomegranate therapy on carotid plaque texture using locality preserving projection
Research output: Contribution to journal › Journal article › Research › peer-review
Standard
Three-dimensional ultrasound evaluation of the effects of pomegranate therapy on carotid plaque texture using locality preserving projection. / Chen, Xueli; Lin, Mingquan; Cui, He; Chen, Yimin; van Engelen, Arna; de Bruijne, Marleen; Azarpazhooh, M Reza; Sohrevardi, Seyed Mojtaba; Chow, Tommy W S; Spence, J David; Chiu, Bernard.
In: Computer Methods and Programs in Biomedicine, Vol. 184, 105276, 2020.Research output: Contribution to journal › Journal article › Research › peer-review
Harvard
APA
Vancouver
Author
Bibtex
}
RIS
TY - JOUR
T1 - Three-dimensional ultrasound evaluation of the effects of pomegranate therapy on carotid plaque texture using locality preserving projection
AU - Chen, Xueli
AU - Lin, Mingquan
AU - Cui, He
AU - Chen, Yimin
AU - van Engelen, Arna
AU - de Bruijne, Marleen
AU - Azarpazhooh, M Reza
AU - Sohrevardi, Seyed Mojtaba
AU - Chow, Tommy W S
AU - Spence, J David
AU - Chiu, Bernard
N1 - Copyright © 2019 Elsevier B.V. All rights reserved.
PY - 2020
Y1 - 2020
N2 - BACKGROUND AND OBJECTIVE: Dietary supplements are expected to confer a smaller beneficial effect than medical treatments. Therefore, there is a need to develop cost-effective biomarkers that can demonstrate the efficacy of such supplements for carotid atherosclerosis. The aim of this study is to develop such a biomarker based on the changes of 376 plaque textural features measured from 3D ultrasound images.METHODS: Since the number of features (376) was greater than the number of subjects (171) in this study, principal component analysis (PCA) was applied to reduce the dimensionality of feature vectors. To generate a scalar biomarker for each subject, elements in the reduced feature vectors produced by PCA were weighted using locality preserving projections (LPP) to capture essential patterns exhibited locally in the feature space. 96 subjects treated by pomegranate juice and tablets, and 75 subjects receiving placebo-matching juice and tablets were evaluated in this study. The discriminative power of the proposed biomarker was evaluated and compared with existing biomarkers using t-tests. As the cost of a clinical trial is directly related to the number of subjects enrolled, the cost-effectiveness of the proposed biomarker was evaluated by sample size estimation.RESULTS: The proposed biomarker was more able to discriminate plaque changes exhibited by the pomegranate and placebo groups than total plaque volume (TPV) according to the result of t-tests (TPV: p=0.34, Proposed biomarker: p=1.5×10-5). The sample size required by the new biomarker to detect a significant effect was 20 times smaller than that required by TPV.CONCLUSION: With the increase in cost-effectiveness afforded by the proposed biomarker, more proof-of-principle studies for novel treatment options could be performed.
AB - BACKGROUND AND OBJECTIVE: Dietary supplements are expected to confer a smaller beneficial effect than medical treatments. Therefore, there is a need to develop cost-effective biomarkers that can demonstrate the efficacy of such supplements for carotid atherosclerosis. The aim of this study is to develop such a biomarker based on the changes of 376 plaque textural features measured from 3D ultrasound images.METHODS: Since the number of features (376) was greater than the number of subjects (171) in this study, principal component analysis (PCA) was applied to reduce the dimensionality of feature vectors. To generate a scalar biomarker for each subject, elements in the reduced feature vectors produced by PCA were weighted using locality preserving projections (LPP) to capture essential patterns exhibited locally in the feature space. 96 subjects treated by pomegranate juice and tablets, and 75 subjects receiving placebo-matching juice and tablets were evaluated in this study. The discriminative power of the proposed biomarker was evaluated and compared with existing biomarkers using t-tests. As the cost of a clinical trial is directly related to the number of subjects enrolled, the cost-effectiveness of the proposed biomarker was evaluated by sample size estimation.RESULTS: The proposed biomarker was more able to discriminate plaque changes exhibited by the pomegranate and placebo groups than total plaque volume (TPV) according to the result of t-tests (TPV: p=0.34, Proposed biomarker: p=1.5×10-5). The sample size required by the new biomarker to detect a significant effect was 20 times smaller than that required by TPV.CONCLUSION: With the increase in cost-effectiveness afforded by the proposed biomarker, more proof-of-principle studies for novel treatment options could be performed.
U2 - 10.1016/j.cmpb.2019.105276
DO - 10.1016/j.cmpb.2019.105276
M3 - Journal article
C2 - 31887617
VL - 184
JO - Computer Methods and Programs in Biomedicine
JF - Computer Methods and Programs in Biomedicine
SN - 0169-2607
M1 - 105276
ER -
ID: 233538541