Automated pericardial fat quantification from coronary magnetic resonance angiography: feasibility study

Ding, Xiaowei; Pang, Jianing; Ren, Zhou; Díaz-Zamudio, Mariana; Jiang, Chenfanfu; Fan, Zhaoyang; Berman, Daniel S.; Li, Debiao; Terzopoulos, Demetri; Slomka, Piotr J.; Dey, Damini

doi:10.1117/1.jmi.3.1.014002

Cited by 9 publications

(6 citation statements)

References 22 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…As standard protocols do not have zero slice gap (usually 5-8 mm slice gap), this approach, as it stands, is not suitable for application to standard-of-care CMR images. Ding et al (14) propose another approach for CMR PAT quantification; they present a limited study demonstrating feasibility of a fully automated pericardial fat quantification method from water/fat-resolved whole-heart non-contrast coronary magnetic resonance angiography. The very small sample size (n = 10) in this limited feasibility study precludes any meaningful assessment of model performance and the clinical validity of the proposed measurement is not known.…”

Section: Comparison With Existing Workmentioning

confidence: 99%

“…Cardiovascular magnetic resonance (CMR) is the reference imaging modality for assessment of cardiac structure and function and has been used in several large population studies, including the Multi-ethnic Study of Atherosclerosis ( 11 ), the Framingham Heart Study ( 12 ), and the UK Biobank (UKB) ( 13 ). Thus, CMR PAT quantification would have high utility for research, with potential for translation into clinical care; however, existing methods require dedicated acquisitions and, often, arduous manual image analysis ( 14 , 15 ), limiting their applicability to large datasets with standard sequence acquisitions.…”

Section: Introductionmentioning

confidence: 99%

See 1 more Smart Citation

Automated Quality-Controlled Cardiovascular Magnetic Resonance Pericardial Fat Quantification Using a Convolutional Neural Network in the UK Biobank

Bard

Raisi‐Estabragh

Ardissino

et al. 2021

Front. Cardiovasc. Med.

Self Cite

View full text Add to dashboard Cite

Background: Pericardial adipose tissue (PAT) may represent a novel risk marker for cardiovascular disease. However, absence of rapid radiation-free PAT quantification methods has precluded its examination in large cohorts.Objectives: We developed a fully automated quality-controlled tool for cardiovascular magnetic resonance (CMR) PAT quantification in the UK Biobank (UKB).Methods: Image analysis comprised contouring an en-bloc PAT area on four-chamber cine images. We created a ground truth manual analysis dataset randomly split into training and test sets. We built a neural network for automated segmentation using a Multi-residual U-net architecture with incorporation of permanently active dropout layers to facilitate quality control of the model's output using Monte Carlo sampling. We developed an in-built quality control feature, which presents predicted Dice scores. We evaluated model performance against the test set (n = 87), the whole UKB Imaging cohort (n = 45,519), and an external dataset (n = 103). In an independent dataset, we compared automated CMR and cardiac computed tomography (CCT) PAT quantification. Finally, we tested association of CMR PAT with diabetes in the UKB (n = 42,928).Results: Agreement between automated and manual segmentations in the test set was almost identical to inter-observer variability (mean Dice score = 0.8). The quality control method predicted individual Dice scores with Pearson r = 0.75. Model performance remained high in the whole UKB Imaging cohort and in the external dataset, with medium–good quality segmentation in 94.3% (mean Dice score = 0.77) and 94.4% (mean Dice score = 0.78), respectively. There was high correlation between CMR and CCT PAT measures (Pearson r = 0.72, p-value 5.3 ×10−18). Larger CMR PAT area was associated with significantly greater odds of diabetes independent of age, sex, and body mass index.Conclusions: We present a novel fully automated method for CMR PAT quantification with good model performance on independent and external datasets, high correlation with reference standard CCT PAT measurement, and expected clinical associations with diabetes.

show abstract

Section: Comparison With Existing Workmentioning

confidence: 99%

Section: Introductionmentioning

confidence: 99%

Automated Quality-Controlled Cardiovascular Magnetic Resonance Pericardial Fat Quantification Using a Convolutional Neural Network in the UK Biobank

Bard

Raisi‐Estabragh

Ardissino

et al. 2021

Front. Cardiovasc. Med.

Self Cite

View full text Add to dashboard Cite

show abstract

“…In this analysis, we took into account not only reported results but also the number of patients the method was validated on, as well as other potential ways the results might not be representative. The vast majority of papers attempt to segment EAT and PAT on CT images, with the notable exception of Ding et al [51], who use MRI images. The papers mentioned in this review use several evaluation methods and metrics to present their segmentation results including (among others): pixel-level accuracy, sensitivity, and specificity; the Sørensen-Dice coefficient (Dice coefficient, DSC); the Jaccard index (Intersection over Union, IoU); and the area under the receiver operating characteristic curve (AUC).…”

Section: Discussionmentioning

confidence: 99%

“…These methods can be made fully automatic by using atlas-based segmentation in place of manual initialization, as presented in Ding et al [51]. Their method works by first segmenting the heart using atlas-based segmentation.…”

Section: Traditional Image Processing Methodsmentioning

confidence: 99%

Recent Progress in Epicardial and Pericardial Adipose Tissue Segmentation and Quantification Based on Deep Learning: A Systematic Review

et al. 2022

View full text Add to dashboard Cite

Epicardial and pericardial adipose tissues (EAT and PAT), which are located around the heart, have been linked to coronary atherosclerosis, cardiomyopathy, coronary artery disease, and other cardiovascular diseases. Additionally, the volume and thickness of EAT are good predictors of CVD risk levels. Manual quantification of these tissues is a tedious and error-prone process. This paper presents a comprehensive and critical overview of research on the epicardial and pericardial adipose tissue segmentation and quantification methods, evaluates their effectiveness in terms of segmentation time and accuracy, provides a critical comparison of the methods, and presents ongoing and future challenges in the field. Described methods are classified into pericardial adipose tissue segmentation, direct epicardial adipose tissue segmentation, and epicardial adipose tissue segmentation via pericardium delineation. A comprehensive categorization of the underlying methods is conducted with insights into their evolution from traditional image processing methods to recent deep learning-based methods. The paper also provides an overview of the research on the clinical significance of epicardial and pericardial adipose tissues as well as the terminology and definitions used in the medical literature.

show abstract

“…This measure has been associated with all features of the metabolic syndrome 38 . MRI can volumetrically measure EAT volume 39 , but cardiac MRI is not performed as widely as CT and EAT quantification requires tedious manual tracing, although recently described automation tools may be promising 40 . CT -contrast or non-contrast- is considered to be the gold standard, due to its spatial resolution and volumetric acquisition.…”

Section: Imaging Perivascular and Epicardial Adipose Tissuementioning

confidence: 99%

State-of-the-art review article. Atherosclerosis affecting fat: What can we learn by imaging perivascular adipose tissue?

Antoniades

Kotanidis

Berman

2019

Journal of Cardiovascular Computed Tomography

Self Cite

View full text Add to dashboard Cite

Perivascular adipose tissue (PVAT) surrounding the human coronary arteries, secretes a wide range of adipocytokines affecting the biology of the adjacent vascular wall in a paracrine way. However, we have recently found that PVAT also behaves as a sensor of signals coming from the vascular wall, to which it reacts by changing its morphology and secretory profile. Indeed, vascular inflammation, a key feature of vascular disease pathogenesis, leads to the release of inflammatory signals that disseminate into local fat, inducing local lipolysis and inhibiting adipogenesis. This ability of PVAT to sense inflammatory signals from the vascular wall, can be used as a “thermometer” of the vascular wall, allowing for non-invasive detection of coronary inflammation. Vascular inflammation induces a shift of PVAT's composition from lipid to aqueous phase, resulting into increased computed tomography (CT) attenuation around the inflamed artery, forming a gradient with increasing attenuation closer to the inflamed coronary artery wall. These spatial changes in PVAT's attenuation are easily detected around culprit lesions during acute coronary syndromes. A new biomarker designed to captured these spatial changes in PVAT's attenuation around the human coronary arteries, the Fat Attenuation Index (FAI), has additional predictive value in stable patients for cardiac mortality and non-fatal heart attacks, above the prediction provided by the current state of the art that includes risk factors, calcium score and presence of high risk plaque features. The use of perivascular FAI in clinical practice may change the way we interpret cardiovascular CT angiography, as it is applicable to any coronary CT angiogram, and it offers dynamic information about the inflammatory burden of the coronary arteries, providing potential guidance for preventive measures and invasive treatments.

show abstract

Automated pericardial fat quantification from coronary magnetic resonance angiography: feasibility study

Cited by 9 publications

References 22 publications

Automated Quality-Controlled Cardiovascular Magnetic Resonance Pericardial Fat Quantification Using a Convolutional Neural Network in the UK Biobank

Automated Quality-Controlled Cardiovascular Magnetic Resonance Pericardial Fat Quantification Using a Convolutional Neural Network in the UK Biobank

Recent Progress in Epicardial and Pericardial Adipose Tissue Segmentation and Quantification Based on Deep Learning: A Systematic Review

State-of-the-art review article. Atherosclerosis affecting fat: What can we learn by imaging perivascular adipose tissue?

Contact Info

Product

Resources

About