Automated coronary artery calcium scoring using nested U-Net and focal loss

Hong, Jia‐Sheng; Tzeng, Yun-Hsuan; Yin, Wei‐Hsian; Wu, Kuan-Ting; Hsu, Huan-Yu; Lu, Chia‐Feng; Liu, Ho-Ren; Wu, Yu‐Te

doi:10.1016/j.csbj.2022.03.025

Cited by 11 publications

(10 citation statements)

References 36 publications

Supporting

Mentioning

Contrasting

Unclassified

Order By: Relevance

“…этот метод не является рутинным, однако в последние годы увеличивается количество исследований с использованием оценки кальциевого скоринга некоронарных артерий. в публикациях, посвящённых изучению кальцификации грудной аорты у больных с аг в сравнении с общей популяцией, выявлены больший объём поражения [19] и связь с развитием гипертрофии миокарда лж, повышенным риском сердечнососудистых осложнений [20] [21]. обнаружена более выраженная кальцификация грудной аорты у пациентов с резистентной аг при недостижении целевого уровня артериального давления, что подтверждает связь структурных изменений сосудистой стенки с тяжестью течения аг.…”

Section: Discussionunclassified

The relationship of fibroblast growth factor 23 with calcification of the thoracic aorta according to the results of multislice computed tomography in patients with resistant arterial hypertension

Litvinova

Хаишева

Шлык

2022

jour

View full text Add to dashboard Cite

Objective: to evaluate the incidence and severity of thoracic aortic calcification, the relationship with endothelial dysfunction and fibroblast growth factor in patients with resistant arterial hypertension.Materials and methods: the study involved 92 patients with resistant hypertension. Daily monitoring of blood pressure (ABPM) was performed, the functional state of the endothelium was assessed in a sample with reactive hyperemia, the calcium index (CI) of the thoracic aorta was determined using MSCT, and the serum level of FGF-23 was determined using enzyme immunoassay.Results: based on ABPM, patients were divided into groups 1st-controlled (n=44) and 2nd-uncontrolled (n=48) resistant AH. In the 2nd group, a more pronounced dysfunction of the endothelium was revealed in the sample with reactive hyperemia and changes in the velocity parameters of blood flow. FGF23 levels and CI were higher in individuals with uncontrolled resistant hypertension. According to the results of correlation-regression analysis, CI was associated with the value of pulse pressure (r=0.49, p=0.007), the duration of hypertension (r=0.68, p=0.04) and the duration of regular antihypertensive therapy (r = −0 .33, p=0.02). FGF- 23 was found to be associated with PA hemodynamic parameters: with Ved (r=0.42, p=0.003), PI (r=0.43, p=0.041) and RI (r=0.46, p=0.025), as well as with CI (r=0.76, p=0.006).Conclusion: patients with uncontrolled resistant hypertension showed a more pronounced decrease in brachial artery EVR and an increase in vascular resistance indices in the test with reactive hyperemia, which was statistically significantly associated with the level of FGF23. In patients with resistant hypertension, excessive calcification of the thoracic aorta was found according to the results of MSCT. Calcium index values are higher in patients with high pulse BP, longer duration of hypertension and high levels of FGF23.

show abstract

Section: Discussionunclassified

The relationship of fibroblast growth factor 23 with calcification of the thoracic aorta according to the results of multislice computed tomography in patients with resistant arterial hypertension

Litvinova

Хаишева

Шлык

2022

jour

View full text Add to dashboard Cite

show abstract

“…Interestingly, the availability of additional datasets rather than adopting multiple models (in the same dataset) improved the AI-based accuracy [ 89 ]. While these results already proved the potential of AI, the adoption of U-net++, an ameliorated version of U-net [ 90 ], reduced the CACS error from 5.5 to 0.48, indicating a bright future for this application [ 91 ]. On non-gated images, ICC values of 0.99 and 0.90 were reported using chest CT scans [ 92 ] and low-dose chest CT scans acquired for LC screening [ 93 ], respectively.…”

Section: Translating Ai Concepts Into Cacsmentioning

confidence: 99%

Artificial intelligence in coronary artery calcium score: rationale, different approaches, and outcomes

Gennari,

Rossi,

De Cecco

et al. 2024

Int J Cardiovasc Imaging

View full text Add to dashboard Cite

Almost 35 years after its introduction, coronary artery calcium score (CACS) not only survived technological advances but became one of the cornerstones of contemporary cardiovascular imaging. Its simplicity and quantitative nature established it as one of the most robust approaches for atherosclerotic cardiovascular disease risk stratification in primary prevention and a powerful tool to guide therapeutic choices. Groundbreaking advances in computational models and computer power translated into a surge of artificial intelligence (AI)-based approaches directly or indirectly linked to CACS analysis. This review aims to provide essential knowledge on the AI-based techniques currently applied to CACS, setting the stage for a holistic analysis of the use of these techniques in coronary artery calcium imaging. While the focus of the review will be detailing the evidence, strengths, and limitations of end-to-end CACS algorithms in electrocardiography-gated and non-gated scans, the current role of deep-learning image reconstructions, segmentation techniques, and combined applications such as simultaneous coronary artery calcium and pulmonary nodule segmentation, will also be discussed.

show abstract

“…Examples include semiautomated segmentation of right ventricle from short-axis CMR, 68 endocardial contouring for left ventricular volume and ejection fraction estimation from 3-dimensional transthoracic echocardiography, 69 and lumen vessel segmentation from contrast-enhanced imaging modalities for atherosclerotic plaque detection. 70 Deep learning model architectures like U-Net can perform tasks like CAC scoring 71 and left ventricle function estimation from CMR. Chen et al 72 provided a detailed survey of the latest segmentation techniques applied to CMR, CT, and echocardiography.…”

Section: Automated Data Extraction For Fusion Inputmentioning

confidence: 99%

Fusion Modeling: Combining Clinical and Imaging Data to Advance Cardiac Care

van Assen,

Tariq,

Razavi

et al. 2023

Circ: Cardiovascular Imaging

View full text Add to dashboard Cite

In addition to the traditional clinical risk factors, an increasing amount of imaging biomarkers have shown value for cardiovascular risk prediction. Clinical and imaging data are captured from a variety of data sources during multiple patient encounters and are often analyzed independently. Initial studies showed that fusion of both clinical and imaging features results in superior prognostic performance compared with traditional scores. There are different approaches to fusion modeling, combining multiple data resources to optimize predictions, each with its own advantages and disadvantages. However, manual extraction of clinical and imaging data is time and labor intensive and often not feasible in clinical practice. An automated approach for clinical and imaging data extraction is highly desirable. Convolutional neural networks and natural language processing can be utilized for the extraction of electronic medical record data, imaging studies, and free-text data. This review outlines the current status of cardiovascular risk prediction and fusion modeling; and in addition gives an overview of different artificial intelligence approaches to automatically extract data from images and electronic medical records for this purpose.

show abstract

Automated coronary artery calcium scoring using nested U-Net and focal loss

Cited by 11 publications

References 36 publications

The relationship of fibroblast growth factor 23 with calcification of the thoracic aorta according to the results of multislice computed tomography in patients with resistant arterial hypertension

The relationship of fibroblast growth factor 23 with calcification of the thoracic aorta according to the results of multislice computed tomography in patients with resistant arterial hypertension

Artificial intelligence in coronary artery calcium score: rationale, different approaches, and outcomes

Fusion Modeling: Combining Clinical and Imaging Data to Advance Cardiac Care

Contact Info

Product

Resources

About