Identification of high-risk carotid plaque with MRI-based radiomics and machine learning

Zhang, Ranying; Zhang, Qingwei; Ji, Aihua; Lv, Peng; Zhang, Jingjing; Fu, Caixia; Lin, Jia Wei

doi:10.1007/s00330-020-07361-z

Cited by 64 publications

(57 citation statements)

References 25 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…In the near future, it may be shown that hemodynamic changes brought about by vascular anomalies are the cause of cerebrovascular disease. Especially, as some authors suggest, the relation between the cerebrovascular events and the radiomics [18][19][20]; however, there have not been any reported relations about the anomalous origin of the right VA and radiomics. Therefore, radiomics are a possible application to clarify the potential relationships in the future.…”

Section: Discussionmentioning

confidence: 95%

Anomalous Origin of the Right Vertebral Artery

et al. 2021

View full text Add to dashboard Cite

An anomalous origin of the right vertebral artery (VA) is a rare anomaly that is much rarer than that of the left VA. It can be divided into a few patterns, including aortic origin, right carotid or brachiocephalic arterial origin, and duplicated origin. In embryological development, the VA is made up of a longitudinal anastomosis between cervical segments. The mechanism of the anomalous origin of the right VA can be explained by the persistence of the cervical segmental artery and the regression point of the 4th right aortic arch. Although the anomaly is usually found incidentally on imaging modalities, it can be a potential cause of complication during surgical and interventional procedures. However, there are a lot of reports about the radiomics of the anomaly. Therefore, we discuss the potential relationship between the anomalous origin of the right VA and radiomics. As the take-home message, understanding several patterns of anomalous origin of the right VA with their embryology and imaging findings is important for surgical and endovascular interventions to avoid intraprocedural complications.

show abstract

Section: Discussionmentioning

confidence: 95%

Anomalous Origin of the Right Vertebral Artery

et al. 2021

View full text Add to dashboard Cite

show abstract

“…Recently, following this suggestion, several researchers have attempted a radiomics-based methodology to overcome the limitation of visual assessment and provide a more objective method to characterize carotid atherosclerotic plaques (41)(42)(43). Zaccagna et al (41) assessed the potential role of CT texture analysis in identifying vulnerable patients with carotid artery atherosclerosis.…”

Section: Discussionmentioning

confidence: 99%

“…The authors identi ed a set of radiomics features that are robust, nonredundant and have superior predictive performance for the classi cation of culprit versus nonculprit carotid arteries in patients with stroke and TIA. Finally, Zhang et al (43) successfully implemented a high-risk plaque MRI-based model using radiomics features and machine learning for differentiating symptomatic from asymptomatic carotid plaques. This MRI-based radiomics model was found to be superior to the traditional model in the identi cation of high-risk plaques.…”

Section: Discussionmentioning

confidence: 99%

“…The rst attempts employed CT-based (22) and ultrasound-based (23) texture analysis to discriminate symptomatic carotid plaques reporting promising results. CT-and MRI-based machine learning algorithms were successfully implementedto accurately distinguish symptomatic from asymptomatic carotid plaques and proved to be superior to the traditional model in the identi cation of high-risk plaques (22,24). Le et al (25) evaluated the ability of several robust features to identify culprit and nonculprit arteries using different machine learning algorithms and reported an average area under the curve of 0.73 and accuracy of 69%.…”

Section: Introductionmentioning

confidence: 99%

See 1 more Smart Citation

CT Angiography-Based Radiomics as a Tool for Carotid Plaque Characterization and Surgery Patient Selection: A Pilot Study

Cilla

Macchia

Lenkowicz

et al. 2021

Preprint

View full text Add to dashboard Cite

Objectives: Radiomics is a quantitative method able to analyze a high-throughput extraction of minable imaging features. Herein, we aim to develop a CT angiography-based radiomics analysis and machine learning model for carotid plaques to discriminate vulnerable from no vulnerable plaques.Methods: Thirty consecutive patients with carotid atherosclerosis were enrolled in this pilot study. At surgery, a binary classification of plaques was adopted (“hard” vs “soft”). Feature extraction was performed using the R software package Moddicom. Pairwise feature interdependencies were evaluated using the Spearman rank correlation coefficient. A univariate analysis was performed to assess the association between each feature and the plaque classification and chose top-ranked features. The feature predictive value was investigated using binary logistic regression. A stepwise backward elimination procedure was performed to minimize the Akaike information criterion (AIC). The final significant features were used to build the models for binary classification of carotid plaques, including logistic regression (LR), support vector machine (SVM), and classification and regression tree analysis (CART). All models were cross-validated using 5-fold cross validation. Class-specific accuracy, precision, recall and F-measure evaluation metrics were used to quantify classifier output quality.Results: A total of 230 radiomics features were extracted from each plaque. Pairwise Spearman correlation between features reported a high level of correlations, with more than 80% correlating with at least one other feature at |ρ| > 0.8. After a stepwise backward elimination procedure, the entropy and volume features were found to be the most significantly associated with the two plaque groups (p< 0.001), with AUCs of 0.92 and 0.96, respectively. The best performance was registered by the SVM classifier with the RBF kernel, with accuracy, precision, recall and F-score equal to 86.7, 92.9, 81.3 and 86.7%, respectively. The CART classification tree model for the entropy and volume features model achieved 86.7% well-classified plaques and an AUC of 0.987.Conclusion: This pilot study highlighted the potential of CTA-based radiomics and machine learning to discriminate plaque composition. This new approach has the potential to provide a reliable method to improve risk stratification in patients with carotid atherosclerosis.

show abstract

“…Lowrisk plaques were defined as follows: (1) HRVW imaging: did not show potentially high-risk plaque components and did not show enhancement. (2) No obvious lesion was identified in the ipsilateral brain parenchyma on DWI (Figure 2; Adamson et al, 2015;Zhang R. Y. et al, 2020).…”

Section: Subjectsmentioning

confidence: 99%

Differences in Wall Shear Stress Between High-Risk and Low-Risk Plaques in Patients With Moderate Carotid Artery Stenosis: A 4D Flow MRI Study

Zhang

Qin

et al. 2021

Front. Neurosci.

View full text Add to dashboard Cite

This study aimed to evaluate the difference in wall shear stress (WSS) (axial, circumferential, and 3D) between high-risk and low-risk plaques in patients with moderate carotid artery stenosis and to identify which time points and directions play the dominant roles in determining the risk associated with plaques. Forty carotid arteries in 30 patients were examined in this study. All patients underwent high-resolution vessel wall (HRVW) imaging, diffusion-weighted imaging (DWI), and 4D flow MRI; HRVW imaging and DWI were used to separate low- and high-risk plaque. Twenty-four high-risk plaques and 16 low-risk plaques were enrolled. An independent-sample t-test was used to compare WSS between low- and high-risk plaques in the whole cardiac cycle and at 20 different time points in the cardiac cycle. The study found that patients with high-risk plaques had higher WSS than those with low-risk plaques throughout the entire cardiac cycle (p < 0.05), but the changes varied at the 20 different time points. The number of non-significant differences (p > 0.05) was less in diastole than in systole across different time points. The axial WSS values were higher than the circumferential WSS values; the difference in axial WSS values between high- and low-risk plaques was more significant than the difference in circumferential WSS, whereas 3D WSS values best reflected the difference between high-risk and low-risk plaques because they showed significant differences at every time point. In conclusion, increased WSS, especially during the diastolic period and in the axial direction, may be a signal of a high-risk plaque and may cause cerebrovascular events in patients with moderate carotid artery stenosis. Additionally, WSS can provide hemodynamic information and help clinicians make more appropriate decisions for patients with plaques.

show abstract

Identification of high-risk carotid plaque with MRI-based radiomics and machine learning

Cited by 64 publications

References 25 publications

Anomalous Origin of the Right Vertebral Artery

Anomalous Origin of the Right Vertebral Artery

CT Angiography-Based Radiomics as a Tool for Carotid Plaque Characterization and Surgery Patient Selection: A Pilot Study

Differences in Wall Shear Stress Between High-Risk and Low-Risk Plaques in Patients With Moderate Carotid Artery Stenosis: A 4D Flow MRI Study

Contact Info

Product

Resources

About