Radiomics-based machine learning atherosclerotic carotid artery disease in ultrasound: systematic review with
Sebastiano Vacca1,2,3, Roberta Scicolone4, Francesco Pisu5
1School of Medicine and Surgery, University of Cagliari, 09042, Cagliari, Italy.
Insights
Radiomics and machine learning show promise in assessing carotid artery disease using ultrasound, achieving high accuracy. However, further high-quality research is needed to confirm these findings due to current study limitations.
Area of Science:
- Medical Imaging
- Artificial Intelligence
- Cardiovascular Disease
Background:
- Stroke is a major cause of death and disability, often linked to carotid artery disease.
- Differentiating symptomatic from asymptomatic carotid artery disease is critical for treatment.
- Radiomics and machine learning (ML) offer potential advancements in ultrasound (US) imaging for lesion screening.
Purpose of the Study:
- To systematically review and meta-analyze the diagnostic performance of radiomics-based ML models in assessing carotid plaque vulnerability using US.
- To evaluate the methodological quality and risk of bias in existing studies.
Main Methods:
- A comprehensive literature search was conducted across PubMed, Web of Science, and Scopus (January 2005 - May 2023).
- Radiomics Quality Score (RQS) and Quality Assessment of Diagnostic Accuracy Studies (QUADAS-2) were used for quality and bias assessment.
- Meta-analyses of sensitivity, specificity, and logarithmic diagnostic odds ratio (logDOR) were performed.
Main Results:
- Methodological quality assessed by RQS was generally low.
- QUADAS-2 indicated a low risk of bias overall, with exceptions in two studies.
- Radiomics-ML models demonstrated satisfactory performance for predicting culprit plaques on US, with sensitivity=0.84, specificity=0.82, AUC=0.887, and pooled logDOR=3.54.
Conclusions:
- Radiomics combined with ML show potential for high sensitivity and low false positive rates in carotid plaque vulnerability assessment via US.
- Current evidence is limited by low study quality and high heterogeneity.
- High-quality, prospective studies are necessary to validate these promising techniques.
Background:
Stroke, a leading global cause of mortality and neurological disability, is often associated with atherosclerotic carotid artery disease. Distinguishing between symptomatic and asymptomatic carotid artery disease is crucial for appropriate treatment decisions. Radiomics, a quantitative image analysis technique, and machine learning (ML) have emerged as promising tools in Ultrasound (US) imaging, potentially providing a helpful tool in the screening of such lesions.
Methods:
Pubmed, Web of Science and Scopus databases were searched for relevant studies published from January 2005 to May 2023. The Radiomics Quality Score (RQS) was used to assess methodological quality of studies included in the review. The Quality Assessment of Diagnostic Accuracy Studies (QUADAS-2) assessed the risk of bias. Sensitivity, specificity, and logarithmic diagnostic odds ratio (logDOR) meta-analyses have been conducted, alongside an influence analysis.
Results:
RQS assessed methodological quality, revealing an overall low score and consistent findings with other radiology domains. QUADAS-2 indicated an overall low risk, except for two studies with high bias. The meta-analysis demonstrated that radiomics-based ML models for predicting culprit plaques on US had a satisfactory performance, with a sensitivity of 0.84 and specificity of 0.82. The logDOR analysis confirmed the positive results, yielding a pooled logDOR of 3.54. The summary ROC curve provided an AUC of 0.887.
Conclusion:
Radiomics combined with ML provide high sensitivity and low false positive rate for carotid plaque vulnerability assessment on US. However, current evidence is not definitive, given the low overall study quality and high inter-study heterogeneity. High quality, prospective studies are needed to confirm the potential of these promising techniques.
Related Concept Videos
01:25Imaging Studies for Cardiovascular System VI: Calcium -Scoring CT
01:21Imaging Studies for Cardiovascular System IV: CMRI
01:20Imaging Studies for Cardiovascular System III: X-Ray
Definition and Purpose
An X-ray, or radiograph, is a non-invasive method that uses ionizing radiation to take images of internal structures. It is mainly used in cardiac imaging to examine the heart, lungs, and major blood vessels, aiming to identify abnormalities in the heart's size, shape, and position, such as heart failure, congenital defects, and vascular...
01:28Imaging Studies for Cardiovascular System V: CT