Dataset Information

A Radiomics Approach to Assess High Risk Carotid Plaques: A Non-invasive Imaging Biomarker, Retrospective Study.

ABSTRACT:

Objective

This study aimed to construct a radiomics-based MRI sequence from high-resolution magnetic resonance imaging (HRMRI), combined with clinical high-risk factors for non-invasive differentiation of the plaque of symptomatic patients from asyptomatic patients.

Methods

A total of 115 patients were retrospectively recruited. HRMRI was performed, and patients were diagnosed with symptomatic plaques (SPs) and asymptomatic plaques (ASPs). Patients were randomly divided into training and test groups in the ratio of 7:3. T2WI was used for segmentation and extraction of the texture features. Max-Relevance and Min-Redundancy (mRMR) and least absolute shrinkage and selection operator (LASSO) were employed for the optimized model. Radscore was applied to construct a diagnostic model considering the T2WI texture features and patient demography to assess the power in differentiating SPs and ASPs.

Results

SPs and ASPs were seen in 75 and 40 patients, respectively. Thirty texture features were selected by mRMR, and LASSO identified a radscore of 16 radiomics features as being related to plaque vulnerability. The radscore, consisting of eight texture features, showed a better diagnostic performance than clinical information, both in the training (area under the curve [AUC], 0.923 vs. 0.713) and test groups (AUC, 0.989 vs. 0.735). The combination model of texture and clinical information had the best performance in assessing lesion vulnerability in both the training (AUC, 0.926) and test groups (AUC, 0.898).

Conclusion

This study demonstrated that HRMRI texture features provide incremental value for carotid atherosclerotic risk assessment.

SUBMITTER: Chen S

PROVIDER: S-EPMC8957977 | biostudies-literature | 2022

REPOSITORIES: biostudies-literature

ACCESS DATA

Publications

A Radiomics Approach to Assess High Risk Carotid Plaques: A Non-invasive Imaging Biomarker, Retrospective Study.

Chen Sihan S Liu Changsheng C Chen Xixiang X Liu Weiyin Vivian WV Ma Ling L Zha Yunfei Y

Frontiers in neurology 20220308

<h4>Objective</h4>This study aimed to construct a radiomics-based MRI sequence from high-resolution magnetic resonance imaging (HRMRI), combined with clinical high-risk factors for non-invasive differentiation of the plaque of symptomatic patients from asyptomatic patients.<h4>Methods</h4>A total of 115 patients were retrospectively recruited. HRMRI was performed, and patients were diagnosed with symptomatic plaques (SPs) and asymptomatic plaques (ASPs). Patients were randomly divided into train ...[more]

PMID: 35350403

Similar Datasets

Project description:BackgroundCarotid plaques are major risk factors for stroke. Carotid ultrasound can help to assess the risk and incidence rate of stroke. However, large-scale carotid artery screening is time-consuming and laborious, the diagnostic results inevitably involve the subjectivity of the diagnostician to a certain extent. Deep learning demonstrates the ability to solve the aforementioned challenges. Thus, we attempted to develop an automated algorithm to provide a more consistent and objective diagnostic method and to identify the presence and stability of carotid plaques using deep learning.MethodsA total of 3,860 ultrasound images from 1,339 participants who underwent carotid plaque assessment between January 2021 and March 2023 at the Shanghai Eighth People's Hospital were divided into a 4:1 ratio for training and internal testing. The external test included 1,564 ultrasound images from 674 participants who underwent carotid plaque assessment between January 2022 and May 2023 at Xinhua Hospital affiliated with Dalian University. Deep learning algorithms, based on the fusion of a bilinear convolutional neural network with a residual neural network (BCNN-ResNet), were used for modeling to detect carotid plaques and assess plaque stability. We chose AUC as the main evaluation index, along with accuracy, sensitivity, and specificity as auxiliary evaluation indices.ResultsModeling for detecting carotid plaques involved training and internal testing on 1,291 ultrasound images, with 617 images showing plaques and 674 without plaques. The external test comprised 470 ultrasound images, including 321 images with plaques and 149 without. Modeling for assessing plaque stability involved training and internal testing on 764 ultrasound images, consisting of 494 images with unstable plaques and 270 with stable plaques. The external test was composed of 279 ultrasound images, including 197 images with unstable plaques and 82 with stable plaques. For the task of identifying the presence of carotid plaques, our model achieved an AUC of 0.989 (95% CI: 0.840, 0.998) with a sensitivity of 93.2% and a specificity of 99.21% on the internal test. On the external test, the AUC was 0.951 (95% CI: 0.962, 0.939) with a sensitivity of 95.3% and a specificity of 82.24%. For the task of identifying the stability of carotid plaques, our model achieved an AUC of 0.896 (95% CI: 0.865, 0.922) on the internal test with a sensitivity of 81.63% and a specificity of 87.27%. On the external test, the AUC was 0.854 (95% CI: 0.889, 0.830) with a sensitivity of 68.52% and a specificity of 89.49%.ConclusionDeep learning using BCNN-ResNet algorithms based on routine ultrasound images could be useful for detecting carotid plaques and assessing plaque instability.

Project description:Background and purposeParameters other than luminal narrowing are needed to predict the risk of stroke more reliably, particularly in patients with <70% stenosis. The goal of our study was to identify clinical risk factors and CT features of carotid atherosclerotic plaques, in a retrospective cohort of patients free of stroke at baseline, that are independent predictors of incident stroke on follow-up.Materials and methodsWe identified a retrospective cohort of patients admitted to our emergency department with suspected stroke between 2001-2007 who underwent a stroke work-up including a CTA of the carotid arteries that was subsequently negative for acute stroke. All patients also had to receive a follow-up brain study at least 2 weeks later. From a random sample, we reviewed charts and imaging studies of patients with subsequent new stroke on follow-up as well as those who remained stroke-free. All patients were classified either as "new carotid infarct patients" or "no-new carotid infarct patients" based on the Causative Classification for Stroke. Independently, the baseline CTA studies were processed using a custom, CT-based automated computer classifier algorithm that quantitatively assesses a set of carotid CT features (wall thickness, plaque ulcerations, fibrous cap thickness, lipid-rich necrotic core, and calcifications). Univariate and multivariate statistical analyses were used to identify any significant differences in CT features between the patient groups in the sample. Subsequent ROC analysis allowed comparison to the classic NASCET stenosis rule in identifying patients with incident stroke on follow-up.ResultsWe identified a total of 315 patients without a new carotid stroke between baseline and follow-up, and 14 with a new carotid stroke between baseline and follow-up, creating the main comparison groups for the study. Statistical analysis showed age and use of antihypertensive drugs to be the most significant clinical variables, and maximal carotid wall thickness was the most relevant imaging variable. The use of age ≥ 75 years, antihypertensive medication use, and a maximal carotid wall thickness of at least 4 mm was able to successfully identify 10 of the 14 patients who developed a new incident infarct on follow-up. ROC analysis showed an area under the ROC curve of 0.706 for prediction of new stroke with this new model.ConclusionsOur new paradigm of using age ≥ 75 years, history of hypertension, and carotid maximal wall thickness of >4 mm identified most of the patients with subsequent new carotid stroke in our study. It is simple and may help clinicians choose the patients at greatest risk of developing a carotid infarct, warranting validation with a prospective observational study.

Project description:ObjectiveIn this study, serum markers of acute ischemic stroke (AICS) with carotid artery plaque were retrospectively evaluated to establish a basis for discovering serological indicators for early warning of acute ischemic stroke (AICS).MethodsA total of 248 patients with AICS were enrolled in Lanzhou University Second Hospital from January 2019 to December 2020. The study population included 136 males and 112 females, 64 ± 11 years of age. Of these, there were 90 patients with a transient ischemic attack (TIA), including 60 males and 30 females, aged 64 ± 8 years old. Patients with AICS were stratified by carotid ultrasound into a plaque group (n = 154) and a non-plaque group (n = 94). A total of 160 healthy subjects were selected as the control group. Serum lipoprotein-associated phospholipase A2 (Lp-PLA2), amyloid A (SAA), immunoglobulin E (IgE), D-dimer (D-D), total cholesterol (TC), triglyceride (TG), and low-density lipoprotein cholesterol (LDL-C) were collected from all subjects. Multivariate logistic regression was used to analyze the risk factors of AICS with carotid plaque. ROC curve was used to analyze the diagnostic efficacy of AICS with carotid plaque.ResultsThe IgE, Lp-PLA2, SAA, LDL-C, TC, TG, and D-D levels in the AICS group were higher than those in the TIA group and healthy control group (P < 0.05). The IgE level was significantly higher than that in the healthy control group and TIA group. The IgE level in the AICS plaque group was significantly higher than that in the AICS non-plaque group (P < 0.01), and the Lp-PLA2 level was also different (P < 0.05). The incidence of AICS was positively correlated with Lp-PLA2, TC, IgE, TG, D-D, SAA and LDL-C (r = 0.611, 0.499, 0.478, 0.431, 0.386, 0.332, 0.280, all P < 0.05). The incidence of AICS with plaque was only positively correlated with IgE and Lp-PLA2 (r = 0.588, 0.246, P < 0.05). Logistic regression analysis showed that IgE and Lp-PLA2 were independent risk factors for predicting the occurrence of AICS with carotid plaque (P < 0.05). ROC curve analysis showed that the AUC of IgE (0.849) was significantly higher than other indicators; its sensitivity and specificity were also the highest, indicating that IgE can improve the diagnostic efficiency of AICS with carotid plaque.ConclusionIgE is a serum laboratory indicator used to diagnose AICS disease with carotid plaque, which lays a foundation for further research on potential early warning indicators of AICS disease.

Dataset Information

A Radiomics Approach to Assess High Risk Carotid Plaques: A Non-invasive Imaging Biomarker, Retrospective Study.

Objective

Methods

Results

Conclusion

Publications

A Radiomics Approach to Assess High Risk Carotid Plaques: A Non-invasive Imaging Biomarker, Retrospective Study.

Similar Datasets

OmicsDI is part of the ELIXIR infrastructure

Tweets