Deep learning for automated exclusion of cardiac CT examinations negative for coronary artery calcium

Oever, L B van den; Cornelissen, Ludo J.; Vonder, Marleen; Xia, Congying; Bolhuis, Jurjen N. van; Vliegenthart, Rozemarijn; Veldhuis, Raymond; Bock, Geertruida H. de; Oudkerk, Matthijs; Ooijen, Peter M. A. van

doi:10.1016/j.ejrad.2020.109114

Cited by 18 publications

(21 citation statements)

References 25 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Alternatively, the identification of CCTA without coronary artery calcification can be used to help prioritize work lists, by identifying scans that can be reviewed less urgently [ 66 ]. These techniques can also be used to expand the capabilities of CCTA, for example, to identify lesion-specific ischemia from conventional anatomical images [ 53 ].…”

Section: Ai In Cardiovascular Ctmentioning

confidence: 99%

Position paper of the EACVI and EANM on artificial intelligence applications in multimodality cardiovascular imaging using SPECT/CT, PET/CT, and cardiac CT

Slart

Williams

Juárez-Orozco

et al. 2021

Eur J Nucl Med Mol Imaging

View full text Add to dashboard Cite

In daily clinical practice, clinicians integrate available data to ascertain the diagnostic and prognostic probability of a disease or clinical outcome for their patients. For patients with suspected or known cardiovascular disease, several anatomical and functional imaging techniques are commonly performed to aid this endeavor, including coronary computed tomography angiography (CCTA) and nuclear cardiology imaging. Continuous improvement in positron emission tomography (PET), single-photon emission computed tomography (SPECT), and CT hardware and software has resulted in improved diagnostic performance and wide implementation of these imaging techniques in daily clinical practice. However, the human ability to interpret, quantify, and integrate these data sets is limited. The identification of novel markers and application of machine learning (ML) algorithms, including deep learning (DL) to cardiovascular imaging techniques will further improve diagnosis and prognostication for patients with cardiovascular diseases. The goal of this position paper of the European Association of Nuclear Medicine (EANM) and the European Association of Cardiovascular Imaging (EACVI) is to provide an overview of the general concepts behind modern machine learning-based artificial intelligence, highlights currently prefered methods, practices, and computational models, and proposes new strategies to support the clinical application of ML in the field of cardiovascular imaging using nuclear cardiology (hybrid) and CT techniques.

show abstract

Section: Ai In Cardiovascular Ctmentioning

confidence: 99%

Position paper of the EACVI and EANM on artificial intelligence applications in multimodality cardiovascular imaging using SPECT/CT, PET/CT, and cardiac CT

Slart

Williams

Juárez-Orozco

et al. 2021

Eur J Nucl Med Mol Imaging

View full text Add to dashboard Cite

show abstract

“…Subsequently, only candidate lesions in the vicinity of the coronary arteries were classified using a neural network that combines spatial coordinate features with features from the segmentation CNN. Van den Oever et al [20] proposed an approach that employs a CNN to segment CAC by analyzing image slices in three orthogonal directions and thereafter, combines them to obtain the final segmentation. The evaluation showed that due to the absence of false negative predictions, the method could be used to exclude scans without CAC to relieve the workload of radiologist.…”

Section: Coronary Calcium Scoring In Cardiac Ctmentioning

confidence: 99%

AI for Calcium Scoring

van Velzen,

Hampe,

de Vos

et al. 2021

Preprint

View full text Add to dashboard Cite

Calcium scoring, a process in which arterial calcifications are detected and quantified in CT, is valuable in estimating the risk of cardiovascular disease events. Especially when used to quantify the extent of calcification in the coronary arteries, it is a strong and independent predictor of coronary heart disease events. Advances in artificial intelligence (AI)-based image analysis have produced a multitude of automatic calcium scoring methods. While most early methods closely follow standard calcium scoring accepted in clinic, recent approaches extend this procedure to enable faster or more reproducible calcium scoring. This chapter provides an introduction to AI for calcium scoring, and an overview of the developed methods and their applications. We conclude with a discussion on AI methods in calcium scoring and propose potential directions for future research.

show abstract

“…The identification of calcified plaque on CT using deep learning has been widely studied, particularly on non-contrast images, but the automatic identification of non-calcified and high-risk plaque subtypes is more challenging [59]. Recently, a deep learning algorithm that identified CCTA without calcification has been proposed as a method to help prioritize work lists [60]. Further advancements in machine learning to automate plaque analysis will reduce the time to perform this analysis and increase its application in clinical practice.…”

Section: Future Developments -Radiomics and Machine Learningmentioning

confidence: 99%

Clinical Relevance of Coronary Computed Tomography Angiography Beyond Coronary Artery Stenosis

Meah

Williams

2021

Rofo

View full text Add to dashboard Cite

Background The capabilities of coronary computed tomography angiography (CCTA) have advanced significantly in the past decade. Its capacity to detect stenotic coronary arteries safely and consistently has led to a marked decline in invasive diagnostic angiography. However, CCTA can do much more than identify coronary artery stenoses. Method This review discusses applications of CCTA beyond coronary stenosis assessment, focusing in particular on the visual and quantitative analysis of atherosclerotic plaque. Results Established signs of visually assessed high-risk plaque on CT include positive remodeling, low-attenuation plaque, spotty calcification, and the napkin-ring sign, which correlate with the histological thin-cap fibroatheroma. Recently, quantification of plaque subtypes has further improved the assessment of coronary plaque on CT. Quantitatively assessed low-attenuation plaque, which correlates with the necrotic core of the thin-cap fibroatheroma, has demonstrated superiority over stenosis severity and coronary calcium score in predicting subsequent myocardial infarction. Current research aims to use radiomic and machine learning methods to further improve our understanding of high-risk atherosclerotic plaque subtypes identified on CCTA. Conclusion Despite rapid technological advances in the field of coronary computed tomography angiography, there remains a significant lag in routine clinical practice where use is often limited to lumenography. We summarize some of the most promising techniques that significantly improve the diagnostic and prognostic potential of CCTA. Key Points: Citation Format

show abstract

Deep learning for automated exclusion of cardiac CT examinations negative for coronary artery calcium

Abstract: Take-down policy If you believe that this document breaches copyright please contact us providing details, and we will remove access to the work immediately and investigate your claim.

Cited by 18 publications

References 25 publications

Position paper of the EACVI and EANM on artificial intelligence applications in multimodality cardiovascular imaging using SPECT/CT, PET/CT, and cardiac CT

Position paper of the EACVI and EANM on artificial intelligence applications in multimodality cardiovascular imaging using SPECT/CT, PET/CT, and cardiac CT

AI for Calcium Scoring

Clinical Relevance of Coronary Computed Tomography Angiography Beyond Coronary Artery Stenosis

Contact Info

Product

Resources

About