Identification of high-risk intracranial plaques with 3D high-resolution magnetic resonance imaging-based radiomics and machine learning

High-resolution magnetic resonance vessel wall imaging in ischemic stroke and carotid artery atherosclerotic stenosis: A review

Ischemic stroke is a significant burden on human health worldwide. Carotid Atherosclerosis stenosis plays an important role in the comprehensive assessment and prevention of ischemic stroke patients. High-resolution vessel wall magnetic resonance imaging has emerged as a successful technique for assessing carotid atherosclerosis stenosis. This advanced imaging modality has shown promise in effectively displaying a wide range of characteristics associated with the condition, leading to a comprehensive evaluation. High-resolution vessel wall magnetic resonance imaging not only enables a comprehensive evaluation of the instability of carotid atherosclerosis stenosis plaques but also provides valuable information for understanding the pathogenesis and predicting the prognosis of ischemic stroke patients. The purpose of this article is to review the application of high-resolution magnetic resonance imaging in ischemic stroke and carotid atherosclerotic stenosis.

Correlation Between Cognitive Impairment and Lenticulostriate Arteries: A Clinical and Radiomics Analysis

Lenticulostriate arteries (LSA) are potentially valuable for studying vascular cognitive impairment. This study aims to investigate correlations between cognitive impairment and LSA through clinical and radiomics features analysis. We retrospectively included 102 patients (mean age 62.5±10.3 years, 60 males), including 58 with mild cognitive impairment (MCI) and 44 with moderate or severe cognitive impairment (MSCI). The MRI images of these patients were subjected to z-score preprocessing, manual regions of interest (ROI) outlining, feature extraction (pyradiomics), feature selection [max-relevance and min-redundancy (mRMR), least absolute shrinkage and selection operator (LASSO), and univariate analysis], model construction (multivariate logistic regression), and evaluation [receiver operating characteristic curve (ROC), decision curve analysis (DCA), and calibration curves (CC)]. In the training dataset (71 patients, 44 MCI) and the test dataset (31 patients, 17 MCI), the area under curve (AUC) of the combined model (training 0.88 [95% CI 0.78, 0.97], test 0.76 [95% CI 0.6, 0.93]) was better than that of the clinical model and the radiomics model. The DCA results demonstrated the highest net yield of the combined model relative to the clinical and radiomics models. In addition, we found that LSA total vessel count (0.79 [95% CI 0.08, 1.59], P = 0.038) and wavelet.HLH_glcm_MCC (-1.2 [95% CI -2.2, -0.4], P = 0.008) were independent predictors of MCI. The model that combines clinical and radiomics features of LSA can predict MCI. Besides, LSA vascular parameters may serve as imaging biomarkers of cognitive impairment.

Radiomics Studies on Ischemic Stroke and Carotid Atherosclerotic Disease: A Reporting Quality Assessment

Objective: To assess the reporting quality of radiomics studies on ischemic stroke, intracranial and carotid atherosclerotic disease using the Image Biomarker Standardization Initiative (IBSI) reporting guidelines with the aim of finding avenues of improvement for future publications. Method: PubMed database was searched to identify relevant radiomics studies. Of 560 articles, 41 original research articles were included in this analysis. Based on IBSI radiomics reporting guidelines, checklists for CT-based and MRI-based studies were created to allow a structured and comprehensive evaluation of each study's adherence to these guidelines. Results: The main topics covered by the included radiomics studies were ischemic stroke, intracranial artery disease, and carotid atherosclerotic disease. The reporting checklist median score was 17/40 for the 20 CT-based radiomics studies and 22.5/50 for the 20 MRI-based studies. Basic items like imaging modality, region of interest, and image biomarker set utilized were included in all studies. However, details regarding image acquisition and reconstruction, post-acquisition image processing, and image biomarkers computation were inconsistently detailed across studies. Conclusion: The overall reporting quality of the included radiomics studies was suboptimal. These findings underscore a pressing need for improved reporting practices in radiomics research, to ensure validation and reproducibility of results. Our study provides insights into current reporting standards and highlights specific areas where adherence to IBSI guidelines could be significantly improved.

Initial experience with radiomics of carotid perivascular adipose tissue in identifying symptomatic plaque

Background

Carotid atherosclerotic ischemic stroke threatens human health and life. The aim of this study is to establish a radiomics model of perivascular adipose tissue (PVAT) around carotid plaque for evaluation of the association between Peri-carotid Adipose Tissue structural changes with stroke and transient ischemic attack.

Methods

A total of 203 patients underwent head and neck computed tomography angiography examination in our hospital. All patients were divided into a symptomatic group (71 cases) and an asymptomatic group (132 cases) according to whether they had acute/subacute stroke or transient ischemic attack. The radiomic signature (RS) of carotid plaque PVAT was extracted, and the minimum redundancy maximum correlation, recursive feature elimination, and linear discriminant analysis algorithms were used for feature screening and dimensionality reduction.

Results

It was found that the RS model achieved the best diagnostic performance in the Bagging Decision Tree algorithm, and the training set (AUC, 0.837; 95%CI: 0.775, 0.899), testing set (AUC, 0.834; 95%CI: 0.685, 0.982). Compared with the traditional feature model, the RS model significantly improved the diagnostic efficacy for identifying symptomatic plaques in the testing set (AUC: 0.834 vs. 0.593; Z = 2.114, p = 0.0345).

Conclusion

The RS model of PVAT of carotid plaque can be used as an objective indicator to evaluate the risk of plaque and provide a basis for risk stratification of carotid atherosclerotic disease.

Risk prediction of CISS classification in endovascular treatment of basilar artery stenosis

Objective

To investigate the incidence of ischemic stroke complications after endovascular treatment for basilar artery stenosis used preoperative high-resolution magnetic resonance vascular wall imaging (HRMR/VWI) and diffusion-weighted imaging (DWI).

Methods

The clinical data of 47 patients with severe symptomatic basilar artery stenosis (stenosis rate ≥70 %) treated with endovascular therapy at the Neuro-interventional Center from December 2017 to December 2021 were retrospectively analyzed. High-resolution magnetic resonance angiography (HRMR VWI) and DWI were used to evaluate the location of atherosclerotic plaque at basilar artery stenosis and the distribution of cerebral infarction lesions in all patients before surgery.According to the CISS classification system for ischemic stroke, patients were divided into a perforation group and a hypoperfusion group, and the general situation, plaque distribution, and incidence of ischemic stroke complications 7 days after endovascular treatment in the two groups were analyzed.

Results

There was no significant difference in baseline data between the two groups. After 7 days of intravascular treatment, the incidence of ischemic stroke was higher in the perforation group (20.0 %) than in the hypoperfusion group (0.0 %), and the difference was statistically significant (P = 0.027). A significant association was found between the perforation group and the hypoperfusion group for the incidence of ischemic stroke at 7 days (P = 0.003, OR = 2.347; 95 % CI = 2.056-4.268). There were a higher proportion of ventral plaques (74.1 %) and a lower proportion of dorsal plaques (33.3 %) in the hypoperfusion group, which were 15.0 % and 90.0 % in the perforation group, respectively (χ2 = 16.045, P < 0.001; χ2 = 15.092, P < 0.001). There was no significant difference in the proportion of left and right plaques between the two groups.

Conclusions

The risk of ischemic stroke is greater in patients with perforator artery obstruction undergoing endovascular therapy, and lower in patients with hypoperfusion/embolus removal.

PET Radiotracers in Atherosclerosis: A Review

Traditional atherosclerosis imaging modalities are limited to late stages of disease, prior to which patients are frequently asymptomatic. Positron emission tomography (PET) imaging allows for the visualization of metabolic processes underscoring disease progression via radioactive tracer, allowing earlier-stage disease to be identified. 2-deoxy-2-[fluorine-18]fluoro-D-glucose (18F-FDG) uptake largely reflects the metabolic activity of macrophages, but is unspecific and limited in its utility. By detecting areas of microcalcification, 18F-Sodium Fluoride (18F-NaF) uptake also provides insight into atherosclerosis pathogenesis. Gallium-68 DOTA-0-Tyr3-Octreotate (68Ga-DOTATATE) PET has also shown potential in identifying vulnerable atherosclerotic plaques with high somatostatin receptor expression. Finally, 11-carbon (11C)-choline and 18F-fluoromethylcholine (FMCH) tracers may identify high-risk atherosclerotic plaques by detecting increased choline metabolism. Together, these radiotracers quantify disease burden, assess treatment efficacy, and stratify risk for adverse cardiac events.

The Value of Applying Machine Learning in Predicting the Time of Symptom Onset in Stroke Patients: Systematic Review and Meta-Analysis

BACKGROUND

Machine learning is a potentially effective method for identifying and predicting the time of the onset of stroke. However, the value of applying machine learning in this field remains controversial and debatable.

OBJECTIVE

We aimed to assess the value of applying machine learning in predicting the time of stroke onset.

METHODS

PubMed, Web of Science, Embase, and Cochrane were comprehensively searched. The C index and sensitivity with 95% CI were used as effect sizes. The risk of bias was evaluated using PROBAST (Prediction Model Risk of Bias Assessment Tool), and meta-analysis was conducted using R (version 4.2.0; R Core Team).

RESULTS

Thirteen eligible studies were included in the meta-analysis involving 55 machine learning models with 41 models in the training set and 14 in the validation set. The overall C index was 0.800 (95% CI 0.773-0.826) in the training set and 0.781 (95% CI 0.709-0.852) in the validation set. The sensitivity and specificity were 0.76 (95% CI 0.73-0.80) and 0.79 (95% CI 0.74-0.82) in the training set and 0.81 (95% CI 0.68-0.90) and 0.83 (95% CI 0.73-0.89) in the validation set, respectively. Subgroup analysis revealed that the accuracy of machine learning in predicting the time of stroke onset within 4.5 hours was optimal (training: 0.80, 95% CI 0.77-0.83; validation: 0.79, 95% CI 0.71-0.86).

CONCLUSIONS

Machine learning has ideal performance in identifying the time of stroke onset. More reasonable image segmentation and texture extraction methods in radiomics should be used to promote the value of applying machine learning in diverse ethnic backgrounds.

TRIAL REGISTRATION

PROSPERO CRD42022358898; https://www.crd.york.ac.uk/Prospero/display_record.php?RecordID=358898.

Radiomics and artificial neural networks modelling for identification of high-risk carotid plaques

Objective

In this study, we aimed to investigate the classification of symptomatic plaques by evaluating the models generated via two different approaches, a radiomics-based machine learning (ML) approach, and an end-to-end learning approach which utilized deep learning (DL) techniques with several representative model frameworks.

Methods

We collected high-resolution magnetic resonance imaging (HRMRI) data from 104 patients with carotid artery stenosis, who were diagnosed with either symptomatic plaques (SPs) or asymptomatic plaques (ASPs), in two medical centers. 74 patients were diagnosed with SPs and 30 patients were ASPs. Sampling Perfection with Application-optimized Contrasts (SPACE) by using different flip angle Evolutions was used for MRI imaging. Repeated stratified five-fold cross-validation was used to evaluate the accuracy and receiver operating characteristic (ROC) of the trained classifier. The two proposed approaches were investigated to train the models separately. The difference in the model performance of the two proposed methods was quantitatively evaluated to find a better model to differentiate between SPs and ASPs.

Results

3D-SE-Densenet-121 model showed the best performance among all prediction models (AUC, accuracy, precision, sensitivity, and F1-score of 0.9300, 0.9308, 0.9008, 0.8588, and 0.8614, respectively), which were 0.0689, 0.1119, 0.1043, 0.0805, and 0.1089 higher than the best radiomics-based ML model (MLP). Decision curve analysis showed that the 3D-SE-Densenet-121 model delivered more net benefit than the best radiomics-based ML model (MLP) with a wider threshold probability.

Conclusion

The DL models were able to accurately differentiate between symptomatic and asymptomatic carotid plaques with limited data, which outperformed radiomics-based ML models in identifying symptomatic plaques.

Identifying vulnerable plaques: A 3D carotid plaque radiomics model based on HRMRI

Background

Identification of vulnerable carotid plaque is important for the treatment and prevention of stroke. In previous studies, plaque vulnerability was assessed qualitatively. We aimed to develop a 3D carotid plaque radiomics model based on high-resolution magnetic resonance imaging (HRMRI) to quantitatively identify vulnerable plaques.

Methods

Ninety patients with carotid atherosclerosis who underwent HRMRI were randomized into training and test cohorts. Using the radiological characteristics of carotid plaques, a traditional model was constructed. A 3D carotid plaque radiomics model was constructed using the radiomics features of 3D T₁-SPACE and its contrast-enhanced sequences. A combined model was constructed using radiological and radiomics characteristics. Nomogram was generated based on the combined models, and ROC curves were utilized to assess the performance of each model.

Results

48 patients (53.33%) were symptomatic and 42 (46.67%) were asymptomatic. The traditional model was constructed using intraplaque hemorrhage, plaque enhancement, wall remodeling pattern, and lumen stenosis, and it provided an area under the curve (AUC) of 0.816 vs. 0.778 in the training and testing sets. In the two cohorts, the 3D carotid plaque radiomics model and the combined model had an AUC of 0.915 vs. 0.835 and 0.957 vs. 0.864, respectively. In the training set, both the radiomics model and the combination model outperformed the traditional model, but there was no significant difference between the radiomics model and the combined model.

Conclusions

HRMRI-based 3D carotid radiomics models can improve the precision of detecting vulnerable carotid plaques, consequently improving risk classification and clinical decision-making in patients with carotid stenosis.