毕鹏飞,霍黎明,聂文畅,刘健

• 1:北京大学人民医院心血管内科

摘要(Abstract)：

冠状动脉钙化（CAC）是冠状动脉粥样硬化性心脏病（冠心病）重要的病理表现之一。传统的CAC评估多依赖于心电门控CT和人工评分，因耗时长、准确性低等问题限制了其在临床中的应用。人工智能（AI）的发展为CAC评估带来了新的可能，AI在CAC的检测、量化及危险分层等方面表现出显著优势，并可以通过CAC的机会性筛查进行冠心病的早期干预，但仍面临图像质量和临床整合等方面的挑战。本文总结了不同影像技术中基于AI的CAC评估的现状、局限性及发展前景，为冠心病患者的危险分层和治疗决策提供依据。

关键词(KeyWords)： 冠状动脉钙化;人工智能;深度学习;影像学技术

Abstract:

Keywords:

基金项目(Foundation): 首都卫生发展科研专项项目（首发2024-2-4083）;; 首都临床特色诊疗技术研究及转化应用项目（Z221100007422096）;; 北京大学人民医院研究与发展基金项目（RDGS2022-08）

作者(Author): 毕鹏飞,霍黎明,聂文畅,刘健

参考文献(References)：

• [1]Onnis C,Virmani R, Kawai K, et al. Coronary artery calcification:current concepts and clinical implications[J].Circulation,2024,149(3):251-266. DOI:10.1161/circulationaha.123.065657.
• [2]Sakamoto A, Virmani R, Finn AV, et al. Calcifi ed nodule as the cause of acute coronary syndrome:connecting bench observations to the bedside[J]. Cardiology, 2018, 139(2):101-104. DOI:10.1159/000485119.
• [3]张礼潜，聂文畅，柏宝辰，等.冠状动脉钙化病理分类及相关分子机制研究进展[J].中国介入心脏病学杂志，2023, 31(10):764-769. DOI:10.3969/j.issn.1004-8812.2023.10.007.
• [4]Bell KJL, White S, Hassan O, et al. Evaluation of the incremental value of a coronary artery calcium score beyond traditional cardiovascular risk assessment:a systematic review and meta-analysis[J]. JAMA Intern Med, 2022, 182(6):634-642. DOI:10.1001/jamainternmed.2022.1262.
• [5]曹成富，马玉良，李琪，等.光学相干断层成像指导钙化病变介入治疗策略[J].中国介入心脏病学杂志，2021, 29(6):345-349. DOI:10.3969/j.issn.1004-8812.2021.06.011.
• [6]Mintz GS. Intravascular imaging of coronary calcifi cation and its clinical implications[J]. JACC Cardiovasc Imaging, 2015,8(4):461-471. DOI:10.1016/j.jcmg.2015.02.003.
• [7]Doris MK, Meah MN, Moss AJ, et al. Coronary(18)F-fl uoride uptake and progression of coronary artery calcifi cation[J]. Circ Cardiovasc Imaging, 2020, 13(12):e011438.DOI:10.1161/CIRCIMAGING.120.011438.
• [8]Isgum I, Rutten A, Prokop M, et al. Detection of coronary calcifi cations from computed tomography scans for automated risk assessment of coronary artery disease[J]. Med Phys, 2007,34(4):1450-1461. DOI:10.1118/1.2710548.
• [9]Brunner G, Chittajallu DR, Kurkure U, et al. Toward the automatic detection of coronary artery calcifi cation in non-contrast computed tomography data[J]. Int J Cardiovasc Imaging,2010, 26(7):829-838. DOI:10.1007/s10554-010-9608-1.
• [10]G??owacki J, Krysiński M, Czaja-Zió??kowska M, et al.Machine learning-based algorithm enables the exclusion of obstructive coronary artery disease in the patients who underwent coronary artery calcium scoring[J]. Acad Radiol, 2020, 27(10):1416-1421. DOI:10.1016/j.acra.2019.11.016.
• [11]Wang W, Wang H, Chen Q, et al. Coronary artery calcium score quantifi cation using a deep-learning algorithm[J]. Clin Radiol, 2020, 75(3):237.e211-237.e216. DOI:10.1016/j.crad.2019.10.012.
• [12]Gogin N, Viti M, Nicodème L, et al. Automatic coronary artery calcium scoring from unenhanced-ECG-gated CT using deep learning[J]. Diagn Interv Imaging, 2021, 102(11):683-690. DOI:10.1016/j.diii.2021.05.004.
• [13]Zeleznik R, Foldyna B, Eslami P, et al. Deep convolutional neural networks to predict cardiovascular risk from computed tomography[J]. Nat Commun, 2021, 12(1):715.DOI:10.1038/s41467-021-20966-2.
• [14]Winkel DJ, Suryanarayana VR, Ali AM, et al. Deep learning for vessel-specifi c coronary artery calcium scoring:validation on a multi-centre dataset[J]. Eur Heart J Cardiovasc Imaging,2022, 23(6):846-854. DOI:10.1093/ehjci/jeab119.
• [15]Williams MC, Shanbhag AD, Zhou J, et al. Automated vessel-specific coronary artery calcification quantification with deep learning in a large multi-centre registry[J]. Eur Heart J Cardiovasc Imaging, 2024, 25(7):976-985. DOI:10.1093/ehjci/jeae045.
• [16]Ahn Y, Jeong GJ, Lee D, et al. Automatic identifi cation of coronary stent in coronary calcium scoring CT using deep learning[J]. Sci Rep, 2024, 14(1):25730. DOI:10.1038/s41598-024-76092-8.
• [17]Chamberlin J, Kocher MR, Waltz J, et al. Automated detection of lung nodules and coronary artery calcium using artificial intelligence on low-dose CT scans for lung cancer screening:accuracy and prognostic value[J]. BMC Med,2021, 19(1):55. DOI:10.1186/s12916-021-01928-3.
• [18]Atkins KM, Weiss J, Zeleznik R, et al. Elevated coronary artery calcium quantified by a validated deep learning model from lung cancer radiotherapy planning scans predicts mortality[J]. JCO Clin Cancer Inform, 2022, 6:e2100095. DOI:10.1200/cci.21.00095.
• [19]Gernaat SAM, van Velzen SGM, Koh V, et al. Automatic quantifi cation of calcifi cations in the coronary arteries and thoracic aorta on radiotherapy planning CT scans of Western and Asian breast cancer patients[J]. Radiother Oncol, 2018, 127(3):487-492. DOI:10.1016/j.radonc.2018.04.011.
• [20]Shen H, Lian Y, Yin J, et al. Cardiovascular risk stratifi cation by automatic coronary artery calcium scoring on pretreatment chest computed tomography in diffuse large b-cell lymphoma receiving anthracycline-based chemotherapy:a multicenter study[J]. Circ Cardiovasc Imaging, 2023, 16(2):e014829.DOI:10.1161/CIRCIMAGING.122.014829.
• [21]Luo Y, Hanuska D, Xu J, et al. Quantifi cation of coronary artery calcification in systemic sclerosis using visual ordinal and deep learning scoring:association with systemic sclerosis clinical features[J]. Semin Arthritis Rheum, 2025, 70:152598. DOI:10.1016/j.semarthrit.2024.152598.
• [22]Sandhu AT, Rodriguez F, Ngo S, et al. Incidental coronary artery calcium:opportunistic screening of previous nongated chest computed tomography scans to improve statin rates(NOTIFY-1 Project)[J]. Circulation, 2023, 147(9):703-714. DOI:10.1161/CIRCULATIONAHA.122.062746.
• [23]Wolterink JM, Leiner T, de Vos BD, et al. Automatic coronary artery calcium scoring in cardiac CT angiography using paired convolutional neural networks[J]. Med Image Anal,2016, 34:123-136. DOI:10.1016/j.media.2016.04.004.
• [24]Mu D, Bai J, Chen W, et al. Calcium scoring at coronary CT angiography using deep learning[J]. Radiology, 2022, 302(2):309-316. DOI:10.1148/radiol.2021211483.
• [25]Cho SG,Lee JE,Cho KH, et al. Coronary artery calcium measurement on attenuation correction computed tomography using artificial intelligence:correlation with coronary flow capacity and prognosis[J]. Eur J Nucl Med Mol Imaging,2025, 52(3):1050-1059. DOI:10.1007/s00259-024-06948-8.
• [26]Miller RJH, Pieszko K, Shanbhag A, et al. Deep learning coronary artery calcium scores from SPECT/CT attenuation maps improve prediction of major adverse cardiac events[J].J Nucl Med, 2023, 64(4):652-658. DOI:10.2967/jnumed.122.264423.
• [27]Li C, Jia H, Tian J, et al. Comprehensive assessment of coronary calcification in intravascular OCT using a spatialtemporal encoder-decoder network[J]. IEEE Trans Med Imaging, 2022, 41(4):857-868. DOI:10.1109/tmi.2021.3125061.
• [28]Liu S, Neleman T, Hartman EMJ, et al. Automated quantitative assessment of coronary calcification using intravascular ultrasound[J]. Ultrasound Med Biol, 2020, 46(10):2801-2809. DOI:10.1016/j.ultrasmedbio.2020.04.032.
• [29]Gao Z, Guo W, Liu X, et al. Automated detection framework of the calcifi ed plaque with acoustic shadowing in IVUS images[J]. PLoS One,2014,9(11):e109997. DOI:10.1371/journal.pone.0109997.
• [30]Tian J, Li C, Qin Z, et al. Coronary artery calcifi cation and cardiovascular outcome as assessed by intravascular OCT and artificial intelligence[J]. Biomed Opt Express, 2024, 15(8):4438-4452. DOI:10.1364/BOE.524946.
• [31]Yuan N, Kwan AC, Duff y G, et al. Prediction of coronary artery calcium using deep learning of echocardiograms[J].J Am Soc Echocardiogr, 2023, 36(5):474-481.e473.DOI:10.1016/j.echo.2022.12.014.
• [32]Jeong H, Park HB, Hong J, et al. Identifying coronary artery calcifi cation using chest X-ray radiographs and machine learning:the role of the radiomics score[J]. J Thorac Imaging, 2024,39(2):119-126. DOI:10.1097/rti.0000000000000757.
• [33]Rim TH, Lee CJ, Tham YC, et al. Deep-learning-based cardiovascular risk stratification using coronary artery calcium scores predicted from retinal photographs[J]. Lancet Digit Health, 2021, 3(5):e306-e316. DOI:10.1016/s2589-7500(21)00043-1.
• [34]Klug M, Shemesh J, Green M, et al. A deep-learning method for the denoising of ultra-low dose chest CT in coronary artery calcium score evaluation[J]. Clin Radiol, 2022, 77(7):e509-e517. DOI:10.1016/j.crad.2022.03.005.
• [35]Zhang Y, van der Werf NR, Jiang B, et al. Motion-corrected coronary calcium scores by a convolutional neural network:a robotic simulating study[J]. Eur Radiol, 2020, 30(2):1285-1294. DOI:10.1007/s00330-019-06447-7.
• [36]Dobrolińska M,van der Werf N,Greuter M,et al. Classification of moving coronary calcified plaques based on motion artifacts using convolutional neural networks:a robotic simulating study on infl uential factors[J]. BMC Med Imaging, 2021, 21(1):151. DOI:10.1186/s12880-021-00680-7.
• [37]Willemink MJ, Leiner T, de Jong PA, et al. Iterative reconstruction techniques for computed tomography part 2:initial results in dose reduction and image quality[J]. Eur Radiol, 2013, 23(6):1632-1642. DOI:10.1007/s00330-012-2764-z.
• [38]Otgonbaatar C,Jeon PH, Ryu JK, et al. Coronary artery calcium quantification:comparison between filtered-back projection, hybrid iterative reconstruction, and deep learning reconstruction techniques[J]. Acta Radiol, 2023, 64(8):2393-2400. DOI:10.1177/02841851231174463.
• [39]Rossi A, Gennari AG, Etter D, et al. Impact of deep learning image reconstructions(DLIR)on coronary artery calcium quantification[J]. Eur Radiol, 2023, 33(6):3832-3838. DOI:10.1007/s00330-022-09287-0.
• [40]Klemenz AC, Beckert L, Manzke M, et al. Infl uence of deep learning based image reconstruction on quantitative results of coronary artery calcium scoring[J]. Acad Radiol, 2024, 31(6):2259-2267. DOI:10.1016/j.acra.2024.03.020.
• [41]van Velzen SGM, Lessmann N, Velthuis BK, et al. Deep learning for automatic calcium scoring in CT:validation using multiple cardiac CT and chest CT protocols[J]. Radiology,2020, 295(1):66-79. DOI:10.1148/radiol.2020191621.
• [42]Hagopian R, Strebel T, Bernatz S, et al. AI opportunistic coronary calcium screening at veterans affairs hospitals[J]. NEJM AI, 2025, 2(6). DOI:10.1056/aioa2400937.
• [43]Park D, Ng J, Zhong Y, et al. Evaluating the generalizability of an automated coronary artery calcium segmentation and scoring algorithm using multi-vendor dataset[J]. Sci Rep, 2025, 15(1):21744. DOI:10.1038/s41598-025-05785-5.
• [44]Kamel PI, Yi PH, Sair HI, et al. Prediction of coronary artery calcium and cardiovascular risk on chest radiographs using deep learning[J]. Radiol Cardiothorac Imaging, 2021, 3(3):e200486. DOI:10.1148/ryct.2021200486.