139 Automated deep learning quantification of epicardial adiposity on cardiac ct predicts atrial fibrillation risk immediately following cardiac surgery and long-term. (6th June 2022)

• Record Type: Journal Article
• Authors: West, Henry; Siddique, Muhammad; Lyasheva, Maria; Volpe, Lucrezia; Desai, Ria; Dangas, Katerina; Tomlins, Pete; Mitchell, Andrew; Kardos, Attila; Casadei, Barbara; Channon, Keith M; Antoniades, Charalambos
• Is Part Of: Heart. Volume 108(2022)Supplement 1
• Page Start: A105
• Page End: A106
• Publication Date: 2022-06-06
• Subjects: Coronary computed tomography angiography -- Adipose tissue -- Deep-learning; Heart -- Diseases -- Treatment -- Periodicals; Cardiology -- Periodicals; 616.12
• DOI: 10.1136/heartjnl-2022-BCS.139
• Languages: English
• ISSNs: 1355-6037

Abstract

Abstract : 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 817 patients 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). Conclusion: 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. Conflict of Interest: None