心外膜脂肪影像分割量化方法及其临床应用的研究进展

doi:10.3969/j.issn.1006-7795.2025.01.016

摘要/Abstract

摘要： 心外膜脂肪（epicardial adipose tissue，EAT）是紧邻冠状动脉和心肌的脂肪组织，通过自分泌或旁分泌活性因子对机体造成生理和病理性的改变。EAT被认为是心血管疾病的诊断标志物和潜在的治疗靶点，分割量化EAT具有重要意义。本文从传统影像、图谱及人工智能三个方面介绍EAT分割量化方法的演变过程，并对自动量化的EAT指标在心血管疾病诊疗中的研究进展进行综述。

关键词: 心外膜脂肪, 分割及量化, 深度学习, 临床应用

Abstract: Epicardial adipose tissue (EAT) is a type of fat tissue that is closely adjacent to the coronary arteries and myocardium, and it caused physiological and pathological changes to the body through the secretion of autocrine and paracrine active factors. EAT is regarded as a diagnostic marker and a potential therapeutic target for cardiovascular diseases, and it is of great significance to segment and quantify EAT. This article introduced the evolution of the EAT segmentation and quantification methods from the aspects of traditional imaging, atlas, and artificial intelligence. Furthermore, it reviewed the research progresses on automatically quantified EAT indices in the diagnosis and treatment of cardiovascular diseases.

Key words: epicardial adipose tissue, segmentation and quantification, deep learning, clinical application

中图分类号:

R318
TP18

屈俊达, 杨敏福, 李春林, 孙立伟, 高赫, 张旭. 心外膜脂肪影像分割量化方法及其临床应用的研究进展[J]. 首都医科大学学报, 2025, 46(1): 99-105.

Qu Junda, Yang Minfu, Li Chunlin, Sun Liwei, Gao He, Zhang Xu. Research progress on imaging segmentation and quantification methods for epicardial adipose tissue and its clinical applications[J]. Journal of Capital Medical University, 2025, 46(1): 99-105.

参考文献

［1］ Vaduganathan M, Mensah G A, Turco J V, et al. The global burden of cardiovascular diseases and risk: a compass for future health［J］. J Am Coll Cardiol, 2022, 80(25): 2361-2371.
［2］ World Health Organization. Monitoring health for the sustainable development goals (SDGs)［M］. Geneva: World Health Organization, 2016.
［3］ World Health Organization. Monitoring health for the SDGs, sustainable development goals［M］. Geneva: World Health Organization, 2023: 130.
［4］ Tarsitano M G, Pandozzi C, Muscogiuri G, et al. Epicardial adipose tissue: a novel potential imaging marker of comorbidities caused by chronic inflammation［J］. Nutrients, 2022, 14(14): 2926.
［5］ Fang W, Xie S, Deng W. Epicardial adipose tissue: a potential therapeutic target for cardiovascular diseases［J］. J Cardiovasc Transl Res, 2023, 17(2): 322-333.
［6］ Monti C B, Codari M, De Cecco C N, et al. Novel imaging biomarkers: epicardial adipose tissue evaluation［J］. Br J Radiol, 2020, 93(1113): 20190770.
［7］ Commandeur F, Goeller M, Betancur J, et al. Deep learning for quantification of epicardial and thoracic adipose tissue from non-contrast CT［J］. IEEE Trans Med Imaging, 2018, 37(8): 1835-1846.
［8］ Abdulkareem M, Brahier M S, Zou F W, et al. Quantification of epicardial adipose tissue volume and attenuation for cardiac CT scans using deep learning in a single multi-task framework［J］. Rev Cardiovasc Med, 2022, 23(12): 412.
［9］ He X X, Guo B J, Lei Y, et al. Automatic segmentation and quantification of epicardial adipose tissue from coronary computed tomography angiography［J］. Phys Med Biol, 2020, 65(9): 095012.
［10］ Zhang Q, Zhou J H, Zhang B, et al. Automatic epicardial fat segmentation and quantification of CT scans using dual U-nets with a morphological processing layer［J］. IEEE Access, 2020, 8: 128032-128041.
［11］ Li Y F, Song S N, Sun Y, et al. Segmentation and volume quantification of epicardial adipose tissue in computed tomography images［J］. Med Phys, 2022, 49(10): 6477-6490.
［12］ Hoori A, Hu T, Lee J, et al. Deep learning segmentation and quantification method for assessing epicardial adipose tissue in CT calcium score scans［J］. Sci Rep, 2022, 12(1): 2276.
［13］ Iacobellis G, Assael F, Ribaudo M C, et al. Epicardial fat from echocardiography: a new method for visceral adipose tissue prediction［J］. Obes Res, 2003, 11(2): 304-310.
［14］周茜洋, 唐春香, 杨桂芬, 等. 心包脂肪影像学的研究进展［J］. 国际医学放射学杂志, 2020, 43(4): 447-451.
［15］ Iacobellis G. Epicardial adipose tissue in contemporary cardiology［J］. Nat Rev Cardiol, 2022, 19(9): 593-606.
［16］ Priya C, Sudha S. Adaptive fruitfly based modified region growing algorithm for cardiac fat segmentation using optimal neural network［J］. J Med Syst, 2019, 43(5): 104.
［17］ Rodrigues É O, Morais F F, Morais N A, et al. A novel approach for the automated segmentation and volume quantification of cardiac fats on computed tomography［J］. Comput Methods Programs Biomed, 2016,123:109-128.
［18］ Zlokolica V, Krstanovic L, Velicki L, et al. Semiautomatic epicardial fat segmentation based on fuzzy c-means clustering and geometric ellipse fitting［J］. J Healthc Eng, 2017, 2017: 5817970.
［19］ Dey D, Suzuki Y, Suzuki S, et al. Automated quantitation of pericardiac fat from noncontrast CT［J］. Invest Radiol, 2008, 43(2): 145-153.
［20］ Coppini G, Favilla R, Marraccini P, et al. Quantification of epicardial fat by cardiac CT imaging［J］. Open Med Inform J, 2010, 4:126-135.
［21］ Gauβ S, Klinghammer L, Jahn D, et al. Epicardial fat and coronary artery calcification in patients on long-term hemodialysis［J］. J Comput Assist Tomogr, 2014, 38(5): 768-772.
［22］ Zheng Y F, Vega-Higuera F, Zhou S K, et al. Fast and automatic heart isolation in 3D CT volumes: optimal shape initialization［C］//International workshop on machine learning in medical imaging. Heidelberg: Springer, 2010: 84-91.
［23］ Militello C, Rundo L, Toia P, et al. A semi-automatic approach for epicardial adipose tissue segmentation and quantification on cardiac CT scans［J］. Comput Biol Med, 2019, 114: 103424.
［24］ Barbosa J G, Figueiredo B, Bettencourt N, et al. Towards automatic quantification of the epicardial fat in non-contrasted CT images［J］. Comput Methods Biomech Biomed Engin, 2011, 14(10): 905-914.
［25］ Rebelo A F, Ferreira A M, Fonseca J M. Automatic epicardial fat segmentation and volume quantification on non-contrast cardiac computed tomography［J］. Comput Methods Programs Biomed Update, 2022, 2: 100079.
［26］ Benc∨evic′ M, Galic′ I, Habijan M, et al. Recent progress in epicardial and pericardial adipose tissue segmentation and quantification based on deep learning: a systematic review［J］. Appl Sci, 2022, 12(10): 5217.
［27］ Ding X W, Terzopoulos D, Diaz-Zamudio M, et al. Automated pericardium delineation and epicardial fat volume quantification from noncontrast CT［J］. Med Phys, 2015, 42(9): 5015-5026.
［28］ Norlén A, Alvén J, Molnar D, et al. Automatic pericardium segmentation and quantification of epicardial fat from computed tomography angiography［J］. J Med Imaging (Bellingham), 2016, 3(3): 034003.
［29］ Shahzad R, Bos D, Metz C, et al. Automatic quantification of epicardial fat volume on non-enhanced cardiac CT scans using a multi-atlas segmentation approach［J］. Med Phys, 2013, 40(9): 091910.
［30］ Ding X W, Terzopoulos D, Diaz-Zamudio M, et al. Automated epicardial fat volume quantification from non-contrast CT［C］//SPIE medical imaging. San Diego: SPIE, 2014: 90340I.
［31］ Rodrigues É O, Cordeiro de Morais F F, Conci A. On the automated segmentation of epicardial and mediastinal cardiac adipose tissues using classification algorithms［J］. Stud Health Technol Inform, 2015, 216: 726-730.
［32］ Cao J, Zhao A, Zhang Z. Automatic image annotation method based on a convolutional neural network with threshold optimization［J］. PLoS One, 2020, 15(9): e0238956.
［33］ Commandeur F, Goeller M, Razipour A, et al. Fully automated CT quantification of epicardial adipose tissue by deep learning: a multicenter study［J］. Radiol Artif Intell, 2019, 1(6): e190045.
［34］ Ronneberger O, Fischer P, Brox T. U-net: convolutional networks for biomedical image segmentation［C］//Medical image computing and computer-assisted intervention – MICCAI 2015. Cham: Springer International Publishing, 2015: 234-241.
［35］ Eisenberg E, McElhinney P A, Commandeur F, et al. Deep learning-based quantification of epicardial adipose tissue volume and attenuation predicts major adverse cardiovascular events in asymptomatic subjects［J］. Circ Cardiovasc Imaging, 2020, 13(2): e009829.
［36］ Commandeur F, Slomka P J, Goeller M, et al. Machine learning to predict the long-term risk of myocardial infarction and cardiac death based on clinical risk, coronary calcium, and epicardial adipose tissue: a prospective study［J］. Cardiovasc Res, 2020, 116(14): 2216-2225.
［37］ Tamarappoo B K, Lin A, Commandeur F, et al. Machine learning integration of circulating and imaging biomarkers for explainable patient-specific prediction of cardiac events: a prospective study［J］. Atherosclerosis, 2021, 318: 76-82.
［38］ Lin A, Wong N D, Razipour A, et al. Metabolic syndrome, fatty liver, and artificial intelligence-based epicardial adipose tissue measures predict long-term risk of cardiac events: a prospective study［J］. Cardiovasc Diabetol, 2021, 20(1): 27.
［39］ Slipczuk L, Castagna F, Schonberger A, et al. Coronary artery calcification and epicardial adipose tissue as independent predictors of mortality in COVID-19［J］. Int J Cardiovasc Imaging, 2021, 37(10): 3093-3100.
［40］ Slipczuk L, Castagna F, Schonberger A, et al. Incidence of new-onset atrial fibrillation in COVID-19 is associated with increased epicardial adipose tissue［J］. J Interv Card Electrophysiol, 2022, 64(2): 383-391.
［41］ Bartoli A, Fournel J, Ait-Yahia L, et al. Automatic deep-learning segmentation of epicardial adipose tissue from low-dose chest CT and prognosis impact on COVID-19［J］. Cells, 2022, 11(6): 1034.
［42］ Molnar D, Bjrnson E, Larsson M, et al. Pre-diabetes is associated with attenuation rather than volume of epicardial adipose tissue on computed tomography［J］. Sci Rep, 2023, 13(1): 1623.
［43］ Kroll L, Nassenstein K, Jochims M, et al. Assessing the role of pericardial fat as a biomarker connected to coronary calcification-a deep learning based approach using fully automated body composition analysis［J］. J Clin Med, 2021, 10(2): 356.
［44］ Wang Z G, Zhang J H, Zhang A X A, et al. The role of epicardial and pericoronary adipose tissue radiomics in identifying patients with non-ST-segment elevation myocardial infarction from unstable angina［J］. Heliyon, 2023, 9(5): e15738.
［45］ You H R, Zhang R R, Hu J S, et al. Performance of radiomics models based on coronary computed tomography angiography in predicting the risk of major adverse cardiovascular events within 3 years: a comparison between the pericoronary adipose tissue model and the epicardial adipose tissue model［J］. Acad Radiol, 2023, 30(3): 390-401.
［46］ Zhang L, Xu Z, Jiang B, et al. Machine-learning-based radiomics identifies atrial fibrillation on the epicardial fat in contrast-enhanced and non-enhanced chest CT［J］. Br J Radiol, 2022, 95(1135): 20211274.
［47］ Ilyushenkova J, Sazonova S, Popov E, et al. Radiomic phenotype of epicardial adipose tissue in the prognosis of atrial fibrillation recurrence after catheter ablation in patients with lone atrial fibrillation［J］. J Arrhythm, 2022, 38(5): 682-693.
［48］ Yang M, Cao Q, Xu Z, et al. Development and validation of a machine learning-based radiomics model on cardiac computed tomography of epicardial adipose tissue in predicting characteristics and recurrence of atrial fibrillation［J］. Front Cardiovasc Med, 2022, 9: 813085.
［49］ Deng Y S, Liu Z, Wang X M, et al. Radiomics signature of epicardial adipose tissue for predicting postoperative atrial fibrillation after off-pump coronary artery bypass surgery［J］. Rev Cardiovasc Med, 2023, 24(11): 327.
［50］ Liu Z, Deng Y, Wang X, et al. Radiomics signature of epicardial adipose tissue for predicting postoperative atrial fibrillation after pulmonary endarterectomy［J］. Front Cardiovasc Med, 2023, 9: 1046931.
［51］仝珊, 吉庆伟, 李伟, 等. 不同冠心病患者心外膜脂肪CT测量指标的变化及其意义［J］.心肺血管病杂志, 2021, 40 (1): 16-20.