A semi-automatic approach for epicardial adipose tissue segmentation and quantification on cardiac CT scans

Militello, Carmelo; Rundo, Leonardo; Toia, Patrizia; Conti, Vincenzo; Russo, Giorgio; Filorizzo, Clarissa; Maffei, Erica; Cademartiri, Filippo; Grutta, Ludovico La; Midiri, Massimo; Vitabile, Salvatore

doi:10.1016/j.compbiomed.2019.103424

Cited by 51 publications

(45 citation statements)

References 47 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Earlier cohort studies showing noncontrast CT-derived EAT volume to associate with MetS and cardiac events used manual or semi-automated methods for EAT quantification [9,12,25,26]. We recently reported that fully automated measurements of EAT volume and attenuation by DL software associate with MACE risk in asymptomatic individuals [14].…”

Section: Ai-based Eat Quantificationmentioning

confidence: 99%

Metabolic syndrome, fatty liver, and artificial intelligence-based epicardial adipose tissue measures predict long-term risk of cardiac events: a prospective study

Lin

Wong

Razipour

et al. 2021

Cardiovasc Diabetol

View full text Add to dashboard Cite

Background We sought to evaluate the association of metabolic syndrome (MetS) and computed tomography (CT)-derived cardiometabolic biomarkers (non-alcoholic fatty liver disease [NAFLD] and epicardial adipose tissue [EAT] measures) with long-term risk of major adverse cardiovascular events (MACE) in asymptomatic individuals. Methods This was a post-hoc analysis of the prospective EISNER (Early-Identification of Subclinical Atherosclerosis by Noninvasive Imaging Research) study of participants who underwent baseline coronary artery calcium (CAC) scoring CT and 14-year follow-up for MACE (myocardial infarction, late revascularization, or cardiac death). EAT volume (cm3) and attenuation (Hounsfield units [HU]) were quantified from CT using fully automated deep learning software (< 30 s per case). NAFLD was defined as liver-to-spleen attenuation ratio < 1.0 and/or average liver attenuation < 40 HU. Results In the final population of 2068 participants (59% males, 56 ± 9 years), those with MetS (n = 280;13.5%) had a greater prevalence of NAFLD (26.0% vs. 9.9%), higher EAT volume (114.1 cm3 vs. 73.7 cm3), and lower EAT attenuation (−76.9 HU vs. −73.4 HU; all p < 0.001) compared to those without MetS. At 14 ± 3 years, MACE occurred in 223 (10.8%) participants. In multivariable Cox regression, MetS was associated with increased risk of MACE (HR 1.58 [95% CI 1.10–2.27], p = 0.01) independently of CAC score; however, not after adjustment for EAT measures (p = 0.27). In a separate Cox analysis, NAFLD predicted MACE (HR 1.78 [95% CI 1.21–2.61], p = 0.003) independently of MetS, CAC score, and EAT measures. Addition of EAT volume to current risk assessment tools resulted in significant net reclassification improvement for MACE (22% over ASCVD risk score; 17% over ASCVD risk score plus CAC score). Conclusions MetS, NAFLD, and artificial intelligence-based EAT measures predict long-term MACE risk in asymptomatic individuals. Imaging biomarkers of cardiometabolic disease have the potential for integration into routine reporting of CAC scoring CT to enhance cardiovascular risk stratification. Trial registration NCT00927693.

show abstract

Section: Ai-based Eat Quantificationmentioning

confidence: 99%

Metabolic syndrome, fatty liver, and artificial intelligence-based epicardial adipose tissue measures predict long-term risk of cardiac events: a prospective study

Lin

Wong

Razipour

et al. 2021

Cardiovasc Diabetol

View full text Add to dashboard Cite

show abstract

“…Subjects were stratified by CAC and EAT as follows: low CAC <100 AU, high CAC ≥100 AU, low EAT 7 <113 cm 3 , high EAT ≥113 cm 3 . Risk of future major adverse cardiovascular events increased with increase in EAT volume and CAC and was highest in subjects with both high EAT and high CAC (reproduced with permission from Eisenberg et expedite this process [72,73]. Recently, a rapid and fully automated algorithm for EAT volume and attenuation quantification was described.…”

Section: State-of-the-eat Assessment Using Cardiac Ctmentioning

confidence: 99%

Epicardial fat and coronary artery disease: Role of cardiac imaging

et al. 2021

View full text Add to dashboard Cite

Epicardial adipose tissue (EAT) represents the fat depot located between the myocardium and the visceral pericardial layer. Far from being an inert tissue, EAT has been recognized as secreting a large amount of bioactive molecules called adipokines, which have numerous exocrine and paracrine effects. Recent evidence demonstrates that pericoronary adipose tissue (PCAT) -the EAT directly surrounding the coronary arterieshas a complex bidirectional interaction with the underlying vascular wall. While in normal conditions this mutual cross-talk helps maintain the homeostasis of the vascular wall, dysfunctional PCAT produces deleterious proinflammatory adipokines involved in atherogenesis. Importantly, PCAT inflammation has been associated with coronary artery disease (CAD) and major cardiovascular events.This review aims to provide an overview of the imaging techniques used to assess EAT, with a specific focus on cardiac computed tomography (CCT), which has become the key modality in this field. In contrast to echocardiography and cardiac magnetic resonance (CMR), CCT is not only able to visualize and precisely quantify EAT, but also to assess the coronary arteries and the PCAT simultaneously. In recent years, several papers have shown the utility of using CCT-derived PCAT attenuation as a surrogate measure of coronary inflammation. This noninvasive imaging biomarker may potentially be used to monitor patient responses to new antinflammatory drugs for the treatment of CAD.

show abstract

“…Different from the classic segmentation method proposed by Militello et al [33], who introduced a user-friendly Graphical User Interface tool to support radiologists in epicardial adipose tissue (EAT) segmentation and quantification, Commandeur et al [34] exploited a convolutional neural network (CNN) for automated and fast EAT volume and density quantification. Moreno et al [35] employed two CNNs to develop a fully automatic LV segmentation method.…”

Section: Related Workmentioning

confidence: 99%

Edge-Sensitive Left Ventricle Segmentation Using Deep Reinforcement Learning

Xiong

Cheung

et al. 2021

Sensors

View full text Add to dashboard Cite

Deep reinforcement learning (DRL) has been utilized in numerous computer vision tasks, such as object detection, autonomous driving, etc. However, relatively few DRL methods have been proposed in the area of image segmentation, particularly in left ventricle segmentation. Reinforcement learning-based methods in earlier works often rely on learning proper thresholds to perform segmentation, and the segmentation results are inaccurate due to the sensitivity of the threshold. To tackle this problem, a novel DRL agent is designed to imitate the human process to perform LV segmentation. For this purpose, we formulate the segmentation problem as a Markov decision process and innovatively optimize it through DRL. The proposed DRL agent consists of two neural networks, i.e., First-P-Net and Next-P-Net. The First-P-Net locates the initial edge point, and the Next-P-Net locates the remaining edge points successively and ultimately obtains a closed segmentation result. The experimental results show that the proposed model has outperformed the previous reinforcement learning methods and achieved comparable performances compared with deep learning baselines on two widely used LV endocardium segmentation datasets, namely Automated Cardiac Diagnosis Challenge (ACDC) 2017 dataset, and Sunnybrook 2009 dataset. Moreover, the proposed model achieves higher F-measure accuracy compared with deep learning methods when training with a very limited number of samples.

show abstract

A semi-automatic approach for epicardial adipose tissue segmentation and quantification on cardiac CT scans

Cited by 51 publications

References 47 publications

Metabolic syndrome, fatty liver, and artificial intelligence-based epicardial adipose tissue measures predict long-term risk of cardiac events: a prospective study

Metabolic syndrome, fatty liver, and artificial intelligence-based epicardial adipose tissue measures predict long-term risk of cardiac events: a prospective study

Epicardial fat and coronary artery disease: Role of cardiac imaging

Edge-Sensitive Left Ventricle Segmentation Using Deep Reinforcement Learning

Contact Info

Product

Resources

About