Deep-Learning for Epicardial Adipose Tissue Assessment With Computed Tomography

West, Henry W.; Siddique, Muhammad; Williams, Michelle; Volpe, Lucrezia della; Desai, Ria; Lyasheva, Maria; Thomas, Sheena; Dangas, Katerina; Kotanidis, Christos; Tomlins, Peter H.; Mahon, Caroline; Kardos, Attila; Adlam, David; Graby, John; Rodrigues, Jonathan; Shirodaria, C; Deanfield, John; Mehta, Nehal N.; Neubauer, Stefan; Channon, K M; Desai, Milind Y.; Nicol, Edward; Newby, David E.; Antoniades, Charalambos

doi:10.1016/j.jcmg.2022.11.018

Cited by 36 publications

(11 citation statements)

References 15 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…This was trained on 2800 consecutive CTCA performed as part of usual care in patients with stable chest pain from 2015 onwards. External validation in 817 patients demonstrated excellent correlation between machine and human expert (CCC = 0.972) 3 . EAT was automatically quantified in <12 s per scan.…”

Section: Methodsmentioning

confidence: 91%

“…Methods: AcceSS and Equity in Transplantation (ASSET), a health-linked data platform, was used to include people commencing KRT in Aotearoa from 2006 to 2019. 3 Residential domicile was categorised into the 20 former DHB jurisdictions. The Geographic Classification for Health was used for rurality scoring and the NZDep2018 Index for socioeconomic status.…”

Section: Discussionmentioning

confidence: 99%

“…It is known that epicardial adipose tissue (EAT) contributes to the risk of patients going into AF through inflammatory and fibrotic disruption of the atrial myocardium 2 . The use of deep-learning methods has allowed the automated quantification of EAT volume on computed tomography (CT) images of the heart 3 . EAT volume quantification for assessing post-cardiac surgery atrial fibrillation (AF) risk, both in-hospital and longer-term, has not been previously investigated or compared to pre-existing risk stratification tools.…”

mentioning

confidence: 99%

See 2 more Smart Citations

Adult Medicine—New South Wales, Australian Capital Territory

2024

Internal Medicine Journal

View full text Add to dashboard Cite

Section: Methodsmentioning

confidence: 91%

Section: Discussionmentioning

confidence: 99%

mentioning

confidence: 99%

See 1 more Smart Citation

Adult Medicine—New South Wales, Australian Capital Territory

2024

Internal Medicine Journal

View full text Add to dashboard Cite

“…43 Similar work is ongoing for advanced measures such as myocardial strain on echocardiography and cardiac MRI, vascular caliber and flow on CT, and microvascular perfusion on positron emission tomography. [44][45][46][47] Because conventional imaging measures and biomarkers may not fully capture disease heterogeneity across all patients, particularly those who have been under-represented, the automated processing of novel imaging phenotypes would allow for broadened investigations of disease phenotypes in understudied populations (Figure 3; Sections 1.2.2.1 and 1.2.2.2).…”

Section: Automating and Standardizing Measurement Of Conventional Ima...mentioning

confidence: 99%

Machine Learning and Bias in Medical Imaging: Opportunities and Challenges

Vrudhula,

Kwan,

Ouyang

et al. 2024

Circ: Cardiovascular Imaging

View full text Add to dashboard Cite

Bias in health care has been well documented and results in disparate and worsened outcomes for at-risk groups. Medical imaging plays a critical role in facilitating patient diagnoses but involves multiple sources of bias including factors related to access to imaging modalities, acquisition of images, and assessment (ie, interpretation) of imaging data. Machine learning (ML) applied to diagnostic imaging has demonstrated the potential to improve the quality of imaging-based diagnosis and the precision of measuring imaging-based traits. Algorithms can leverage subtle information not visible to the human eye to detect underdiagnosed conditions or derive new disease phenotypes by linking imaging features with clinical outcomes, all while mitigating cognitive bias in interpretation. Importantly, however, the application of ML to diagnostic imaging has the potential to either reduce or propagate bias. Understanding the potential gain as well as the potential risks requires an understanding of how and what ML models learn. Common risks of propagating bias can arise from unbalanced training, suboptimal architecture design or selection, and uneven application of models. Notwithstanding these risks, ML may yet be applied to improve gain from imaging across all 3A’s (access, acquisition, and assessment) for all patients. In this review, we present a framework for understanding the balance of opportunities and challenges for minimizing bias in medical imaging, how ML may improve current approaches to imaging, and what specific design considerations should be made as part of efforts to maximize the quality of health care for all.

show abstract

“…Adipose tissue is recognized as a key regulator of cardiovascular health and disease, exerting both protective and deleterious effects on the cardiovascular system. 83 Epicardial and peri-coronary adipose tissue are markers of visceral obesity and inflammation features evaluated by CCTA that have proven to be associated with coronary atherosclerosis and cardiovascular events. 84 An increase in vessel inflammation represented by perivascular adipose tissue density is independently associated with the progression of the lipid component of coronary atherosclerotic plaques, as shown by Lee et al .…”

Section: Quantification Of Epicardial and Peri-coronary Adipose Tissuementioning

confidence: 99%

Use of coronary artery calcium score and coronary CT angiography to guide cardiovascular prevention and treatment

Lima,

Lopes,

Ferreira

2024

Therapeutic Advances in Cardiovascular Disease

View full text Add to dashboard Cite

Currently, cardiovascular risk stratification to guide preventive therapy relies on clinical scores based on cardiovascular risk factors. However, the discriminative power of these scores is relatively modest. The use of coronary artery calcium score (CACS) and coronary CT angiography (CCTA) has surfaced as methods for enhancing the estimation of risk and potentially providing insights for personalized treatment in individual patients. CACS improves overall cardiovascular risk prediction and may be used to improve the yield of statin therapy in primary prevention, and possibly identify patients with a favorable risk/benefit relationship for antiplatelet therapies. CCTA holds promise to guide anti-atherosclerotic therapies and to monitor individual response to these treatments by assessing individual plaque features, quantifying total plaque volume and composition, and assessing peri-coronary adipose tissue. In this review, we aim to summarize current evidence regarding the use of CACS and CCTA for guiding lipid-lowering and antiplatelet therapy and discuss the possibility of using plaque burden and plaque phenotyping to monitor response to anti-atherosclerotic therapies.

show abstract

Deep-Learning for Epicardial Adipose Tissue Assessment With Computed Tomography

Cited by 36 publications

References 15 publications

Adult Medicine—New South Wales, Australian Capital Territory

Adult Medicine—New South Wales, Australian Capital Territory

Machine Learning and Bias in Medical Imaging: Opportunities and Challenges

Use of coronary artery calcium score and coronary CT angiography to guide cardiovascular prevention and treatment

Contact Info

Product

Resources

About