Deep-Learning for Epicardial Adipose Tissue Assessment With Computed Tomography: Implications for Cardiovascular Risk Prediction

BACKGROUND

Epicardial adipose tissue (EAT) volume is a marker of visceral obesity that can be measured in coronary computed tomography angiograms (CCTA). The clinical value of integrating this measurement in routine CCTA interpretation has not been documented.

OBJECTIVES

This study sought to develop a deep-learning network for automated quantification of EAT volume from CCTA, test it in patients who are technically challenging, and validate its prognostic value in routine clinical care.

METHODS

The deep-learning network was trained and validated to autosegment EAT volume in 3,720 CCTA scans from the ORFAN (Oxford Risk Factors and Noninvasive Imaging Study) cohort. The model was tested in patients with challenging anatomy and scan artifacts and applied to a longitudinal cohort of 253 patients post-cardiac surgery and 1,558 patients from the SCOT-HEART (Scottish Computed Tomography of the Heart) Trial, to investigate its prognostic value.

RESULTS

External validation of the deep-learning network yielded a concordance correlation coefficient of 0.970 for machine vs human. EAT volume was associated with coronary artery disease (odds ratio [OR] per SD increase in EAT volume: 1.13 [95% CI: 1.04-1.30]; P = 0.01), and atrial fibrillation (OR: 1.25 [95% CI: 1.08-1.40]; P = 0.03), after correction for risk factors (including body mass index). EAT volume predicted all-cause mortality (HR per SD: 1.28 [95% CI: 1.10-1.37]; P = 0.02), myocardial infarction (HR: 1.26 [95% CI:1.09-1.38]; P = 0.001), and stroke (HR: 1.20 [95% CI: 1.09-1.38]; P = 0.02) independently of risk factors in SCOT-HEART (5-year follow-up). It also predicted in-hospital (HR: 2.67 [95% CI: 1.26-3.73]; P ≤ 0.01) and long-term post-cardiac surgery atrial fibrillation (7-year follow-up; HR: 2.14 [95% CI: 1.19-2.97]; P ≤ 0.01).

CONCLUSIONS

Automated assessment of EAT volume is possible in CCTA, including in patients who are technically challenging; it forms a powerful marker of metabolically unhealthy visceral obesity, which could be used for cardiovascular risk stratification.

Automated deep learning quantification of epicardial adiposity on cardiac CT predicts atrial fibrillation risk immediately following cardiac surgery and long-term

Introduction

Epicardial adipose tissue (EAT) is a visceral fat deposit within the pericardial sac which surrounds the heart myocardium and coronary arteries. The automated quantification of EAT volume is possible from routine CCTA scans via a deep-learning approach. The use of automated EAT quantification for the assessment of atrial fibrillation (AF) risk in the post-operative period, and longer-term, has not been previously investigated.

Purpose

To apply a deep-learning approach for automated segmentation of EAT from routine CCTA scans to assess the immediate post-operative and long-term risk of AF conveyed by EAT.

Methods

A deep-learning automated EAT segmentation tool using a 3D Residual-U-Net neural network architecture for 3D volumetric segmentation of CCTA data was created and trained on over 2800 consecutive CCTA performed as part of clinical care in patients with stable chest pain from 2015 onwards within the European arm of the Oxford Risk Factors And Non Invasive Imaging (ORFAN) Study. External validation in 817patients demonstrated excellent correlation between machine and human expert (CCC = 0.972). The prognostic value of deep-learning derived EAT volume was assessed in the AdipoRedOx Study (n=253; UK patients undergoing cardiac surgery) against both immediate in-hospital outcomes and longer-term outcomes from UK-wide NHS data, with adjustment for AF risk factors.

Results

There were 97 cases of new-onset AF in the immediate post-operative period (38.3%). EAT volume was found to be an independent predictor of post-operative AF regardless of body mass index. Utilising the median EAT volume as the cut point, the adjusted hazard ratio (HR [95% CI]) for risk of new-onset post-operative AF in-hospital was 1.56 [1.09–3.85], p<0.01 (Figure 1A). In receiver-operator characteristic analysis EAT volume added significant incremental prognostic power for the discrimination of in-hospital post-operative AF over a traditional risk factor model ΔAUC=0.101, p<0.01 (Figure 1B).

Over a median follow-up period of 89 months there were 48 unique cases (19%) of confirmed AF found in nation-wide NHS hospital episode statistics data for the AdipoRedOx cohort. EAT volume was found to be a significant independent predictor of long-term AF. Utilising the median EAT volume as the cut point, the adjusted HR for risk of new-onset long-term AF following cardiac surgery was 1.25 [1.08–3.17], p<0.01 (Figure 1C).

Conclusions

Automatically segmented EAT volume measured using a deep learning network predicts risk of both short-term new onset AF following cardiac surgery, and long-term risk of AF in the 7 years following the surgery independently of BMI and AF risk factors. This suggests that EAT is a potent mediator of AF risk in the post cardiac surgery setting.

Funding Acknowledgement

Type of funding sources: Foundation. Main funding source(s): British Heart Foundation - TG/19/2/34831EU Commission - 965286

Constructing custom-made radiotranscriptomic signatures of vascular inflammation from routine CT angiograms: a prospective outcomes validation study in COVID-19

BACKGROUND

Direct evaluation of vascular inflammation in patients with COVID-19 would facilitate more efficient trials of new treatments and identify patients at risk of long-term complications who might respond to treatment. We aimed to develop a novel artificial intelligence (AI)-assisted image analysis platform that quantifies cytokine-driven vascular inflammation from routine CT angiograms, and sought to validate its prognostic value in COVID-19.

METHODS

For this prospective outcomes validation study, we developed a radiotranscriptomic platform that uses RNA sequencing data from human internal mammary artery biopsies to develop novel radiomic signatures of vascular inflammation from CT angiography images. We then used this platform to train a radiotranscriptomic signature (C19-RS), derived from the perivascular space around the aorta and the internal mammary artery, to best describe cytokine-driven vascular inflammation. The prognostic value of C19-RS was validated externally in 435 patients (331 from study arm 3 and 104 from study arm 4) admitted to hospital with or without COVID-19, undergoing clinically indicated pulmonary CT angiography, in three UK National Health Service (NHS) trusts (Oxford, Leicester, and Bath). We evaluated the diagnostic and prognostic value of C19-RS for death in hospital due to COVID-19, did sensitivity analyses based on dexamethasone treatment, and investigated the correlation of C19-RS with systemic transcriptomic changes.

FINDINGS

Patients with COVID-19 had higher C19-RS than those without (adjusted odds ratio [OR] 2·97 [95% CI 1·43-6·27], p=0·0038), and those infected with the B.1.1.7 (alpha) SARS-CoV-2 variant had higher C19-RS values than those infected with the wild-type SARS-CoV-2 variant (adjusted OR 1·89 [95% CI 1·17-3·20] per SD, p=0·012). C19-RS had prognostic value for in-hospital mortality in COVID-19 in two testing cohorts (high [≥6·99] vs low [<6·99] C19-RS; hazard ratio [HR] 3·31 [95% CI 1·49-7·33], p=0·0033; and 2·58 [1·10-6·05], p=0·028), adjusted for clinical factors, biochemical biomarkers of inflammation and myocardial injury, and technical parameters. The adjusted HR for in-hospital mortality was 8·24 (95% CI 2·16-31·36, p=0·0019) in patients who received no dexamethasone treatment, but 2·27 (0·69-7·55, p=0·18) in those who received dexamethasone after the scan, suggesting that vascular inflammation might have been a therapeutic target of dexamethasone in COVID-19. Finally, C19-RS was strongly associated (r=0·61, p=0·00031) with a whole blood transcriptional module representing dysregulation of coagulation and platelet aggregation pathways.

INTERPRETATION

Radiotranscriptomic analysis of CT angiography scans introduces a potentially powerful new platform for the development of non-invasive imaging biomarkers. Application of this platform in routine CT pulmonary angiography scans done in patients with COVID-19 produced the radiotranscriptomic signature C19-RS, a marker of cytokine-driven inflammation driving systemic activation of coagulation and responsible for adverse clinical outcomes, which predicts in-hospital mortality and might allow targeted therapy.

FUNDING

Engineering and Physical Sciences Research Council, British Heart Foundation, Oxford BHF Centre of Research Excellence, Innovate UK, NIHR Oxford Biomedical Research Centre, Wellcome Trust, Onassis Foundation.

Predicting Survival in Patients with Brain Tumors: Current State-of-the-Art of AI Methods Applied to MRI

Given growing clinical needs, in recent years Artificial Intelligence (AI) techniques have increasingly been used to define the best approaches for survival assessment and prediction in patients with brain tumors. Advances in computational resources, and the collection of (mainly) public databases, have promoted this rapid development. This narrative review of the current state-of-the-art aimed to survey current applications of AI in predicting survival in patients with brain tumors, with a focus on Magnetic Resonance Imaging (MRI). An extensive search was performed on PubMed and Google Scholar using a Boolean research query based on MeSH terms and restricting the search to the period between 2012 and 2022. Fifty studies were selected, mainly based on Machine Learning (ML), Deep Learning (DL), radiomics-based methods, and methods that exploit traditional imaging techniques for survival assessment. In addition, we focused on two distinct tasks related to survival assessment: the first on the classification of subjects into survival classes (short and long-term or eventually short, mid and long-term) to stratify patients in distinct groups. The second focused on quantification, in days or months, of the individual survival interval. Our survey showed excellent state-of-the-art methods for the first, with accuracy up to ∼98%. The latter task appears to be the most challenging, but state-of-the-art techniques showed promising results, albeit with limitations, with C-Index up to ∼0.91. In conclusion, according to the specific task, the available computational methods perform differently, and the choice of the best one to use is non-univocal and dependent on many aspects. Unequivocally, the use of features derived from quantitative imaging has been shown to be advantageous for AI applications, including survival prediction. This evidence from the literature motivates further research in the field of AI-powered methods for survival prediction in patients with brain tumors, in particular, using the wealth of information provided by quantitative MRI techniques.

Automated quantification of epicardial adipose tissue on CCTA via deep-learning detection of the pericardium: clinical implications

Background

Epicardial adipose tissue (EAT) is a visceral fat deposit within the pericardial sac which surrounds the heart myocardium and coronary arteries. EAT volume has been demonstrated to be strongly associated with the development and prognosis of cardiovascular diseases, but its measurement is subjective and challenging in practice.

Purpose

To develop a deep-learning approach for automated segmentation of EAT from routine CCTA scans, that could assist clinical interpretation of CCTA.

Methods

A deep-learning method using a 3D Residual-U-Net neural network architecture for 3D volumetric segmentation of CCTA data was created. The network was trained on a diverse sample of 1900 CCTAs, each manually segmented by a single expert, drawn from the UK sites of the Oxford Risk Factors And Non-invasive imaging (ORFAN) Study. Three iterations of feedback learning were used to fine tune the algorithm for the segmentation of the whole heart within the bounds of the pericardium. In each iteration, the machine analysed sets of 100–250 unannotated CCTAs unseen by the machine which were then corrected by experts. EAT volumes were calculated by automated thresholding of adipose tissue (−190HU through −30HU) from within the bound of the pericardial segment (Figure 1). The network was then applied to 817 unseen CCTAs from US sites of the ORFAN Study. These scans were also segmented for ground truth by two experts blind to all other data. Comparisons between machine vs expert total pericardial volume and EAT volume were made using Lin's concordance correlation coefficient (CCC). The algorithm was then applied externally in 1588 CCTAs from the SCOTHEART trial (UK), and the EAT volume was automatically calculated for each case. Cross-sectional associations between standardised EAT volumes and prevalent AF and CAD were performed.

Results

Within both the internal (UK ORFAN sites) and external (USA ORFAN sites) validation cohorts correlation between human and machine segmented total pericardium and EAT was excellent, with CCC of 0.97 for both volumes (external validation cohort shown in Figure 2A). Utilising SCOTHEART CCTAs with automatically segmented EAT volumes, a multivariable-adjusted logistic regression model accounting for risk factors of age, sex, BMI, hypertension, diabetes mellitus, valvular disease, and previous heart surgery found that EAT volumes were significantly associated with prevalent AF, with odds ratio (OR) per 1 SD increase of EAT volume of 1.20 (95% CI, 1.06 to 1.44; P=0.03). A similar model for prevalent CAD, adjusted for age, sex, BMI, hypertension, non-HDL cholesterol, diabetes mellitus, and coronary artery calcium score resulted in an OR per 1 SD increase of EAT volume of 1.26 (95% CI, 1.10 to 1.45; P=0.001) (Figure 2B).

Conclusion

Highly accurate, reproducible, and instantaneous EAT volume quantification is possible utilising deep-learning detection of the whole human heart within the pericardial sac.

Funding Acknowledgement

Type of funding sources: Public Institution(s). Main funding source(s): British Heart FoundationNational Institute for Health Research - Oxford University Hospitals Biomedical Research Centre Figure 1Figure 2

Pericoronary fat radiomic profile (FRP) predicts long-term cardiac risk in individuals with calcium score below 100 on coronary computed tomography angiography

Background

Coronary computed tomography angiography (CCTA) provides useful information regarding cardiovascular risk assessment. Key aspects of coronary biology induce changes in perivascular adipose tissue composition, detectable by the pericoronary Fat Radiomic Profile (FRP) index.

Purpose

We assessed the ability of FRP to further stratify cardiac risk in patients with Coronary Artery Calcium (CAC) scoring below 100 following routine CCTA.

Methods

The study population consisted of 1,575 participants from the CCTA arm of the SCOT-HEART trial (NCT01149590) with images available and eligible for analysis. Pericoronary FRP mapping was performed in perivascular adipose tissue segmentations around the proximal sites of the right and left coronary arteries, as previously validated. The prognostic potential of FRP was initially tested in a sub-cohort, consisting of patients with Coronary Artery Calcium (CAC) score lower than 100. Further analysis was performed after sub-grouping based on the absence of high risk plaque (HRP) features and obstructive coronary artery disease (CAD). The association with future incidence of major adverse cardiac events (MACE: cardiac mortality or non-fatal myocardial infarction) or a composite endpoint of MACE ± late revascularization (MACE-ReVasc) was assessed using adjusted Cox regression models [adjusted for age, sex, systolic blood pressure (SBP), diabetes mellitus (DM), body mass index (BMI), smoking, CAD (≥50% stenosis), total cholesterol, high-density lipoprotein (HDL), and HRP features].

Results

Two-thirds (66%) of the study population were at low-risk according to the CAC score (CAC&lt;100). Over a mean follow-up of 4.87±1.06 years, 12 MACE and 47 MACE-ReVasc were recorded. In this sub-cohort, high FRP was associated with a 14.4-fold (95% CI: 3.80–54.78, p&lt;0.001) higher adjusted risk of MACE and a 2.8-fold (95% CI: 1.49–5.36, p=0.001) higher adjusted risk of MACE-ReVasc. Adding high FRP to a baseline model consisting of traditional risk factors (age, sex, systolic blood pressure, diabetes mellitus, BMI, smoking, CAD (≥50% stenosis), total cholesterol, HDL, HRP) significantly enhanced (deltaAUC at 5 years:0.15, p=0.03) the model's performance (A) and reclassified individuals (NRI=0.59, p=0.02). Interestingly, following further filtering of the population by the absence of HRP features and obstructive CAD, high FRP remained an independent predictor of MACE (B).

Conclusion

The Fat Radiomic Profile biormarker significantly improves risk prediction for adverse clinical events beyond the current state-of-the-art in individuals with low CAC scores. Non-invasive profiling of pericoronary adipose tissue using CCTA-derived FRP captures irreversible changes in perivascular adipose tissue composition associated with chronic vascular inflammation and atherosclerotic disease, and can improve risk stratification and clinical decision making in low-risk populations.

Funding Acknowledgement

Type of funding source: Foundation. Main funding source(s): British Heart Foundation, National Institute of Health Research, Oxford Biomedical Research Centre

A novel machine learning-derived radiotranscriptomic signature of perivascular fat improves cardiac risk prediction using coronary CT angiography

BACKGROUND

Coronary inflammation induces dynamic changes in the balance between water and lipid content in perivascular adipose tissue (PVAT), as captured by perivascular Fat Attenuation Index (FAI) in standard coronary CT angiography (CCTA). However, inflammation is not the only process involved in atherogenesis and we hypothesized that additional radiomic signatures of adverse fibrotic and microvascular PVAT remodelling, may further improve cardiac risk prediction.

METHODS AND RESULTS

We present a new artificial intelligence-powered method to predict cardiac risk by analysing the radiomic profile of coronary PVAT, developed and validated in patient cohorts acquired in three different studies. In Study 1, adipose tissue biopsies were obtained from 167 patients undergoing cardiac surgery, and the expression of genes representing inflammation, fibrosis and vascularity was linked with the radiomic features extracted from tissue CT images. Adipose tissue wavelet-transformed mean attenuation (captured by FAI) was the most sensitive radiomic feature in describing tissue inflammation (TNFA expression), while features of radiomic texture were related to adipose tissue fibrosis (COL1A1 expression) and vascularity (CD31 expression). In Study 2, we analysed 1391 coronary PVAT radiomic features in 101 patients who experienced major adverse cardiac events (MACE) within 5 years of having a CCTA and 101 matched controls, training and validating a machine learning (random forest) algorithm (fat radiomic profile, FRP) to discriminate cases from controls (C-statistic 0.77 [95%CI: 0.62-0.93] in the external validation set). The coronary FRP signature was then tested in 1575 consecutive eligible participants in the SCOT-HEART trial, where it significantly improved MACE prediction beyond traditional risk stratification that included risk factors, coronary calcium score, coronary stenosis, and high-risk plaque features on CCTA (Δ[C-statistic] = 0.126, P < 0.001). In Study 3, FRP was significantly higher in 44 patients presenting with acute myocardial infarction compared with 44 matched controls, but unlike FAI, remained unchanged 6 months after the index event, confirming that FRP detects persistent PVAT changes not captured by FAI.

CONCLUSION

The CCTA-based radiomic profiling of coronary artery PVAT detects perivascular structural remodelling associated with coronary artery disease, beyond inflammation. A new artificial intelligence (AI)-powered imaging biomarker (FRP) leads to a striking improvement of cardiac risk prediction over and above the current state-of-the-art.

Synergistic application of pulmonary 18F-FDG PET/HRCT and computer-based CT analysis with conventional severity measures to refine current risk stratification in idiopathic pulmonary fibrosis (IPF)

INTRODUCTION

To investigate the combined performance of quantitative CT (qCT) following a computer algorithm analysis (IMBIO) and ¹⁸F-FDG PET/CT to assess survival in patients with idiopathic pulmonary fibrosis (IPF).

METHODS

A total of 113 IPF patients (age 70 ± 9 years) prospectively and consecutively underwent ¹⁸F-FDG PET/CT and high-resolution CT (HRCT) at our institution. During a mean follow-up of 29.6 ± 26 months, 44 (48%) patients died. As part of the qCT analysis, pattern evaluation of HRCT (using IMBIO software) included the total extent (percentage) of the following features: normal-appearing lung, hyperlucent lung, parenchymal damage (comprising ground-glass opacification, reticular pattern and honeycombing), and the pulmonary vessels. The maximum (SUV_max) and minimum (SUV_min) standardized uptake value (SUV) for ¹⁸F-FDG uptake in the lungs, and the target-to-background (SUV_max/SUV_min) ratio (TBR) were quantified using routine region-of-interest (ROI) analysis. Pulmonary functional tests (PFTs) were acquired within 14 days of the PET/CT/HRCT scan. Kaplan-Meier (KM) survival analysis was used to identify associations with mortality.

RESULTS

Data from 91 patients were available for comparative analysis. The average ± SD GAP [gender, age, physiology] score was 4.2 ± 1.7 (range 0-8). The average ± SD SUV_max, SUV_min, and TBR were 3.4 ± 1.4, 0.7 ± 0.2, and 5.6 ± 2.8, respectively. In all patients, qCT analysis demonstrated a predominantly reticular lung pattern (14.9 ± 12.4%). KM analysis showed that TBR (p = 0.018) and parenchymal damage assessed by qCT (p = 0.0002) were the best predictors of survival. Adding TBR and qCT to the GAP score significantly increased the ability to differentiate between high and low risk (p < 0.0001).

CONCLUSION

¹⁸F-FDG PET and qCT are independent and synergistic in predicting mortality in patients with IPF.