Skip to main content

Thank you for visiting nature.com. You are using a browser version with limited support for CSS. To obtain the best experience, we recommend you use a more up to date browser (or turn off compatibility mode in Internet Explorer). In the meantime, to ensure continued support, we are displaying the site without styles and JavaScript.

Roadmap on the use of artificial intelligence for imaging of vulnerable atherosclerotic plaque in coronary arteries

Nature Reviews Cardiology (2023)Cite this article

Subjects

Abstract

Artificial intelligence (AI) is likely to revolutionize the way medical images are analysed and has the potential to improve the identification and analysis of vulnerable or high-risk atherosclerotic plaques in coronary arteries, leading to advances in the treatment of coronary artery disease. However, coronary plaque analysis is challenging owing to cardiac and respiratory motion, as well as the small size of cardiovascular structures. Moreover, the analysis of coronary imaging data is time-consuming, can be performed only by clinicians with dedicated cardiovascular imaging training, and is subject to considerable interreader and intrareader variability. AI has the potential to improve the assessment of images of vulnerable plaque in coronary arteries, but requires robust development, testing and validation. Combining human expertise with AI might facilitate the reliable and valid interpretation of images obtained using CT, MRI, PET, intravascular ultrasonography and optical coherence tomography. In this Roadmap, we review existing evidence on the application of AI to the imaging of vulnerable plaque in coronary arteries and provide consensus recommendations developed by an interdisciplinary group of experts on AI and non-invasive and invasive coronary imaging. We also outline future requirements of AI technology to address bias, uncertainty, explainability and generalizability, which are all essential for the acceptance of AI and its clinical utility in handling the anticipated growing volume of coronary imaging procedures.

Key points

  • Artificial intelligence (AI) might have the potential to transform the assessment of vulnerable or high-risk plaque in coronary arteries by improving the detection, quantification and prognostication of vulnerable plaque and integration with other imaging and clinical parameters.

  • The advantages of AI for the assessment of vulnerable plaque images include reducing observer variability, improving accuracy, enabling standardization, improving speed and facilitating the synthesis of diverse information.

  • The challenges for the development and implementation of AI include the presence of anatomical variations and imaging artefacts; the lack of reproducibility, generalizability and robustness across diverse imaging platforms; and the potential for the technology to introduce or worsen biases.

  • Clinical research has already been performed on AI tools for plaque assessment, but validated commercial solutions for clinical use are not yet available.

  • For AI to achieve its true potential for vulnerable plaque assessment in clinical practice, large and diverse studies are required, and AI tools must be trustworthy, explainable and interpretable.

This is a preview of subscription content, access via your institution

Relevant articles

Open Access articles citing this article.

Access options

Rent or buy this article

Prices vary by article type

from$1.95

to$39.95

Learn more

Prices may be subject to local taxes which are calculated during checkout

Fig. 1: Basics of artificial intelligence, machine learning and deep learning.
Fig. 2: The concept of vulnerable plaques and high-risk plaque features in CCTA, IVUS and OCT images.
Fig. 3: The interaction between tasks supported by AI tools for the assessment of vulnerable plaques in coronary arteries.
Fig. 4: Roadmap for AI in the imaging of vulnerable plaques.

References

  1. Roberts, J. Thinking machines: the search for artificial intelligence. Science History Institute https://www.sciencehistory.org/distillations/thinking-machines-the-search-for-artificial-intelligence (2016).

  2. Quer, G., Arnaout, R., Henne, M. & Arnaout, R. Machine learning and the future of cardiovascular care: JACC state-of-the-art review. J. Am. Coll. Cardiol. 77, 300–313 (2021).

    Article  PubMed  PubMed Central  Google Scholar 

  3. Al’Aref, S. J. et al. Clinical applications of machine learning in cardiovascular disease and its relevance to cardiac imaging. Eur. Heart J. 40, 1975–1986 (2019).

    Article  PubMed  Google Scholar 

  4. Shameer, K., Johnson, K. W., Glicksberg, B. S., Dudley, J. T. & Sengupta, P. P. Machine learning in cardiovascular medicine: are we there yet. Heart 104, 1156–1164 (2018).

    Article  PubMed  Google Scholar 

  5. Litjens, G. et al. State-of-the-art deep learning in cardiovascular image analysis. JACC Cardiovasc. Imaging 12, 1549–1565 (2019).

    Article  PubMed  Google Scholar 

  6. Friedrich, S. et al. Applications of artificial intelligence/machine learning approaches in cardiovascular medicine: a systematic review with recommendations. Eur. Heart J. Digit. Health 2, 424–436 (2021).

    Article  PubMed  PubMed Central  Google Scholar 

  7. Muller, J. E., Tofler, G. H. & Stone, P. H. Circadian variation and triggers of onset of acute cardiovascular disease. Circulation 79, 733–743 (1989).

    Article  CAS  PubMed  Google Scholar 

  8. Williams, M. C. et al. Coronary artery plaque characteristics associated with adverse outcomes in the SCOT-heart study. J. Am. Coll. Cardiol. 73, 291–301 (2019).

    Article  PubMed  PubMed Central  Google Scholar 

  9. Stone, G. W. et al. A prospective natural-history study of coronary atherosclerosis. N. Engl. J. Med. 364, 226–235 (2011).

    Article  CAS  PubMed  Google Scholar 

  10. Kedhi, E. et al. Thin-cap fibroatheroma predicts clinical events in diabetic patients with normal fractional flow reserve: the COMBINE OCT-FFR trial. Eur. Heart J. 42, 4671–4679 (2021).

    Article  CAS  PubMed  Google Scholar 

  11. Jonas, R. A. et al. Interobserver variability among expert readers quantifying plaque volume and plaque characteristics on coronary CT angiography: a CLARIFY trial sub-study. Clin. Imaging 91, 19–25 (2022).

    Article  PubMed  Google Scholar 

  12. Gruslova, A. et al. TCT-312 international OCT core labs can identify stable but not unstable coronary plaque. J. Am. Coll. Cardiol. 80, B125 (2022).

    Article  Google Scholar 

  13. Vázquez Mézquita, A. J. et al. Clinical quantitative coronary artery stenosis and coronary atherosclerosis imaging: a Consensus Statement from the Quantitative Cardiovascular Imaging Study Group. Nat Rev Cardiol. https://doi.org/10.1038/s41569-023-00880-4 (2023).

    Article  Google Scholar 

  14. Sihan, K. et al. Fully automatic three-dimensional quantitative analysis of intracoronary optical coherence tomography: method and validation. Catheter. Cardiovasc. Interv. 74, 1058–1065 (2009).

    Article  PubMed  Google Scholar 

  15. Chu, M. et al. Artificial intelligence and optical coherence tomography for the automatic characterisation of human atherosclerotic plaques. EuroIntervention 17, 41–50 (2021).

    Article  PubMed  PubMed Central  Google Scholar 

  16. Cho, H. et al. Intravascular ultrasound-based deep learning for plaque characterization in coronary artery disease. Atherosclerosis 324, 69–75 (2021).

    Article  CAS  PubMed  Google Scholar 

  17. Dewey, M. et al. Clinical quantitative cardiac imaging for the assessment of myocardial ischaemia. Nat. Rev. Cardiol. 17, 427–450 (2020).

    Article  PubMed  PubMed Central  Google Scholar 

  18. Sermesant, M., Delingette, H., Cochet, H., Jais, P. & Ayache, N. Applications of artificial intelligence in cardiovascular imaging. Nat. Rev. Cardiol. 18, 600–609 (2021).

    Article  PubMed  Google Scholar 

  19. de Villiers, M. R., de Villiers, P. J. & Kent, A. P. The Delphi technique in health sciences education research. Med. Teach. 27, 639–643 (2005).

    Article  PubMed  Google Scholar 

  20. Nasa, P., Jain, R. & Juneja, D. Delphi methodology in healthcare research: how to decide its appropriateness. World J. Methodol. 11, 116–129 (2021).

    Article  PubMed  PubMed Central  Google Scholar 

  21. Tastle, W. J. & Wierman, M. J. An information theoretic measure for the evaluation of ordinal scale data. Behav. Res. Methods 38, 487–494 (2006).

    Article  CAS  PubMed  Google Scholar 

  22. Finn, A. V., Nakano, M., Narula, J., Kolodgie, F. D. & Virmani, R. Concept of vulnerable/unstable plaque. Arterioscler. Thromb. Vasc. Biol. 30, 1282–1292 (2010).

    Article  CAS  PubMed  Google Scholar 

  23. Gaba, P., Gersh, B. J., Muller, J., Narula, J. & Stone, G. W. Evolving concepts of the vulnerable atherosclerotic plaque and the vulnerable patient: implications for patient care and future research. Nat. Rev. Cardiol. 20, 181–196 (2023).

    Article  PubMed  Google Scholar 

  24. Arbab-Zadeh, A. & Fuster, V. The myth of the “vulnerable plaque”: transitioning from a focus on individual lesions to atherosclerotic disease burden for coronary artery disease risk assessment. J. Am. Coll. Cardiol. 65, 846–855 (2015).

    Article  PubMed  PubMed Central  Google Scholar 

  25. Yamamoto, M. H. et al. 2-year outcomes after stenting of lipid-rich and nonrich coronary plaques. J. Am. Coll. Cardiol. 75, 1371–1382 (2020).

    Article  CAS  PubMed  Google Scholar 

  26. Joshi, N. V. et al. 18F-fluoride positron emission tomography for identification of ruptured and high-risk coronary atherosclerotic plaques: a prospective clinical trial. Lancet 383, 705–713 (2014).

    Article  PubMed  Google Scholar 

  27. Williams, M. C. et al. Low-attenuation noncalcified plaque on coronary computed tomography angiography predicts myocardial infarction: results from the multicenter SCOT-HEART trial (Scottish Computed Tomography of the HEART). Circulation 141, 1452–1462 (2020).

    Article  CAS  PubMed  PubMed Central  Google Scholar 

  28. Matsumoto, H. et al. Standardized volumetric plaque quantification and characterization from coronary CT angiography: a head-to-head comparison with invasive intravascular ultrasound. Eur. Radiol. 29, 6129–6139 (2019).

    Article  PubMed  PubMed Central  Google Scholar 

  29. Conte, E. et al. Plaque quantification by coronary computed tomography angiography using intravascular ultrasound as a reference standard: a comparison between standard and last generation computed tomography scanners. Eur. Heart J. Cardiovasc. Imaging 21, 191–201 (2020).

    PubMed  Google Scholar 

  30. Meah, M. N. et al. Plaque burden and 1-year outcomes in acute chest pain: results from the multicenter RAPID-CTCA trial. JACC Cardiovasc. Imaging 15, 1916–1925 (2022).

    Article  PubMed  Google Scholar 

  31. Ferencik, M. et al. Use of high-risk coronary atherosclerotic plaque detection for risk stratification of patients with stable chest pain: a secondary analysis of the PROMISE randomized clinical trial. JAMA Cardiol. 3, 144–152 (2018).

    Article  PubMed  PubMed Central  Google Scholar 

  32. Aguirre, A. D., Arbab-Zadeh, A., Soeda, T., Fuster, V. & Jang, I. K. Optical coherence tomography of plaque vulnerability and rupture: JACC focus seminar Part 1/3. J. Am. Coll. Cardiol. 78, 1257–1265 (2021).

    Article  PubMed  PubMed Central  Google Scholar 

  33. Mintz, G. S. & Guagliumi, G. Intravascular imaging in coronary artery disease. Lancet 390, 793–809 (2017).

    Article  PubMed  Google Scholar 

  34. Maehara, A., Matsumura, M., Ali, Z. A., Mintz, G. S. & Stone, G. W. IVUS-guided versus OCT-guided coronary stent implantation: a critical appraisal. JACC Cardiovasc. Imaging 10, 1487–1503 (2017).

    Article  PubMed  Google Scholar 

  35. Raber, L. et al. Changes in coronary plaque composition in patients with acute myocardial infarction treated with high-intensity statin therapy (IBIS-4): a serial optical coherence tomography study. JACC Cardiovasc. Imaging 12, 1518–1528 (2019).

    Article  PubMed  Google Scholar 

  36. Guagliumi, G. et al. Temporal course of vascular healing and neoatherosclerosis after implantation of durable- or biodegradable-polymer drug-eluting stents. Eur. Heart J. 39, 2448–2456 (2018).

    Article  CAS  PubMed  Google Scholar 

  37. Cheng, J. M. et al. In vivo detection of high-risk coronary plaques by radiofrequency intravascular ultrasound and cardiovascular outcome: results of the ATHEROREMO-IVUS study. Eur. Heart J. 35, 639–647 (2014).

    Article  PubMed  Google Scholar 

  38. Calvert, P. A. et al. Association between IVUS findings and adverse outcomes in patients with coronary artery disease: the VIVA (VH-IVUS in Vulnerable Atherosclerosis) study. JACC Cardiovasc. Imaging 4, 894–901 (2011).

    Article  PubMed  Google Scholar 

  39. Prati, F. et al. Relationship between coronary plaque morphology of the left anterior descending artery and 12 months clinical outcome: the CLIMA study. Eur. Heart J. 41, 383–391 (2020).

    Article  PubMed  Google Scholar 

  40. Motoyama, S. et al. Plaque characterization by coronary computed tomography angiography and the likelihood of acute coronary events in mid-term follow-up. J. Am. Coll. Cardiol. 66, 337–346 (2015).

    Article  PubMed  Google Scholar 

  41. Ferencik, M. et al. Computed tomography-based high-risk coronary plaque score to predict acute coronary syndrome among patients with acute chest pain–results from the ROMICAT II trial. J. Cardiovasc. Comput. Tomogr. 9, 538–545 (2015).

    Article  PubMed  PubMed Central  Google Scholar 

  42. Min, J. K. et al. Whole-heart quantification and characterization of coronary atherosclerotic burden and risk of major adverse cardiovascular events: the ischemia trial [abstract 17195]. Circulation 144(25), e575–e576 (2021).

    Google Scholar 

  43. Arbab-Zadeh, A. & Fuster, V. From detecting the vulnerable plaque to managing the vulnerable patient: JACC state-of-the-art review. J. Am. Coll. Cardiol. 74, 1582–1593 (2019).

    Article  PubMed  Google Scholar 

  44. Williams, M. C., Earls, J. P. & Hecht, H. Quantitative assessment of atherosclerotic plaque, recent progress and current limitations. J. Cardiovasc. Comput. Tomogr. 16, 124–137 (2022).

    Article  PubMed  Google Scholar 

  45. Hosny, A., Parmar, C., Quackenbush, J., Schwartz, L. H. & Aerts, H. Artificial intelligence in radiology. Nat. Rev. Cancer 18, 500–510 (2018).

    Article  CAS  PubMed  PubMed Central  Google Scholar 

  46. Hampe, N., Wolterink, J. M., van Velzen, S. G. M., Leiner, T. & Išgum, I. Machine learning for assessment of coronary artery disease in cardiac CT: a survey. Front. Cardiovasc. Med. 6, 172 (2019).

    Article  PubMed  PubMed Central  Google Scholar 

  47. Lin, A. et al. Deep learning-enabled coronary CT angiography for plaque and stenosis quantification and cardiac risk prediction: an international multicentre study. Lancet Digit. Health 4, e256–e265 (2022).

    Article  CAS  PubMed  PubMed Central  Google Scholar 

  48. Lin, A. et al. Artificial intelligence in cardiovascular imaging for risk stratification in coronary artery disease. Radiol. Cardiothorac. Imaging 3, e200512 (2021).

    Article  PubMed  PubMed Central  Google Scholar 

  49. Hampe, N. et al. Deep learning-based detection of functionally significant stenosis in coronary CT angiography. Front. Cardiovasc. Med. 9, 964355 (2022).

    Article  CAS  PubMed  PubMed Central  Google Scholar 

  50. Chen, Q. et al. A coronary CT angiography radiomics model to identify vulnerable plaque and predict cardiovascular events. Radiology 307, 221693 (2023).

    Article  Google Scholar 

  51. Chang, H. J. et al. Coronary atherosclerotic precursors of acute coronary syndromes. J. Am. Coll. Cardiol. 71, 2511–2522 (2018).

    Article  PubMed  PubMed Central  Google Scholar 

  52. Group, D. T. et al. CT or invasive coronary angiography in stable chest pain. N. Engl. J. Med. 386, 1591–1602 (2022).

    Article  Google Scholar 

  53. Motwani, M. et al. Machine learning for prediction of all-cause mortality in patients with suspected coronary artery disease: a 5-year multicentre prospective registry analysis. Eur. Heart J. 38, 500–507 (2017).

    PubMed  Google Scholar 

  54. van Velzen, S. G. M. et al. Deep learning for automatic calcium scoring in CT: validation using multiple cardiac CT and chest CT protocols. Radiology 295, 66–79 (2020).

    Article  PubMed  Google Scholar 

  55. Wolterink, J. M. et al. Automatic coronary artery calcium scoring in cardiac CT angiography using paired convolutional neural networks. Med. Image Anal. 34, 123–136 (2016).

    Article  PubMed  Google Scholar 

  56. Follmer, B. et al. Active multitask learning with uncertainty-weighted loss for coronary calcium scoring. Med. Phys. 49, 7262–7277 (2022).

    Article  PubMed  Google Scholar 

  57. Jia, D. & Zhuang, X. Learning-based algorithms for vessel tracking: a review. Comput. Med. Imaging Graph. 89, 101840 (2021).

    Article  PubMed  Google Scholar 

  58. Kolossváry, M. et al. Radiomic features are superior to conventional quantitative computed tomographic metrics to identify coronary plaques with napkin-ring sign. Circ. Cardiovasc. Imaging 10, e006843 (2017).

    Article  PubMed  PubMed Central  Google Scholar 

  59. Murgia, A. et al. Cardiac computed tomography radiomics: an emerging tool for the non-invasive assessment of coronary atherosclerosis. Cardiovasc. Diagn. Ther. 10, 2005–2017 (2020).

    Article  PubMed  PubMed Central  Google Scholar 

  60. Lin, A. et al. Radiomics-based precision phenotyping identifies unstable coronary plaques from computed tomography angiography. JACC Cardiovasc. Imaging 15, 859–871 (2022).

    Article  PubMed  PubMed Central  Google Scholar 

  61. Al’Aref, S. J. et al. A boosted ensemble algorithm for determination of plaque stability in high-risk patients on coronary CTA. JACC Cardiovasc. Imaging 13, 2162–2173 (2020).

    Article  PubMed  Google Scholar 

  62. Diaz-Zamudio, M. et al. Automated quantitative plaque burden from coronary CT angiography noninvasively predicts hemodynamic significance by using fractional flow reserve in intermediate coronary lesions. Radiology 276, 408–415 (2015).

    Article  PubMed  Google Scholar 

  63. Yang, S. et al. CT angiographic and plaque predictors of functionally significant coronary disease and outcome using machine learning. JACC Cardiovasc. Imaging 14, 629–641 (2021).

    Article  PubMed  Google Scholar 

  64. von Knebel Doeberitz, P. L. et al. Coronary CT angiography-derived plaque quantification with artificial intelligence CT fractional flow reserve for the identification of lesion-specific ischemia. Eur. Radiol. 29, 2378–2387 (2019).

    Article  Google Scholar 

  65. Coenen, A. et al. Diagnostic accuracy of a machine-learning approach to coronary computed tomographic angiography-based fractional flow reserve: result from the MACHINE consortium. Circ. Cardiovasc. Imaging 11, e007217 (2018).

    Article  PubMed  Google Scholar 

  66. Dey, D. et al. Integrated prediction of lesion-specific ischaemia from quantitative coronary CT angiography using machine learning: a multicentre study. Eur. Radiol. 28, 2655–2664 (2018).

    Article  PubMed  PubMed Central  Google Scholar 

  67. Dey, D. et al. Artificial intelligence in cardiovascular imaging: JACC state-of-the-art review. J. Am. Coll. Cardiol. 73, 1317–1335 (2019).

    Article  PubMed  PubMed Central  Google Scholar 

  68. Kwiecinski, J. et al. Machine learning with 18F-sodium fluoride PET and quantitative plaque analysis on CT angiography for the future risk of myocardial infarction. J. Nucl. Med. 63, 158–165 (2022).

    Article  CAS  PubMed  PubMed Central  Google Scholar 

  69. Canan, A. et al. CAD-RADS: pushing the limits. Radiographics 40, 629–652 (2020).

    Article  PubMed  Google Scholar 

  70. Lee, J. et al. Fully automated plaque characterization in intravascular OCT images using hybrid convolutional and lumen morphology features. Sci. Rep. 10, 2596 (2020).

    Article  CAS  PubMed  PubMed Central  Google Scholar 

  71. Lee, J. et al. Automatic A-line coronary plaque classification using combined deep learning and textural features in intravascular OCT images. Proc. SPIE Int. Soc. Opt. Eng. 11315, 1131513 (2020).

    PubMed  PubMed Central  Google Scholar 

  72. Cheimariotis, G.-A. et al. Automatic classification of A-lines in intravascular OCT images using deep learning and estimation of attenuation coefficients. Appl. Sci. 11, 7412 (2021).

    Article  CAS  Google Scholar 

  73. Lee, J. et al. Automated analysis of fibrous cap in intravascular optical coherence tomography images of coronary arteries. Sci. Rep. 12, 21454 (2022).

    Article  CAS  PubMed  PubMed Central  Google Scholar 

  74. Lee, J. et al. Automated plaque characterization using deep learning on coronary intravascular optical coherence tomographic images. Biomed. Opt. Express 10, 6497–6515 (2019).

    Article  PubMed  PubMed Central  Google Scholar 

  75. Min, H. S. et al. Detection of optical coherence tomography-defined thin-cap fibroatheroma in the coronary artery using deep learning. EuroIntervention 16, 404–412 (2020).

    Article  PubMed  Google Scholar 

  76. Niioka, H. et al. Automated diagnosis of optical coherence tomography imaging on plaque vulnerability and its relation to clinical outcomes in coronary artery disease. Sci. Rep. 12, 14067 (2022).

    Article  CAS  PubMed  PubMed Central  Google Scholar 

  77. Holmberg, O. et al. Histopathology-based deep-learning predicts atherosclerotic lesions in intravascular imaging. Front. Cardiovasc. Med. 8, 779807 (2021).

    Article  PubMed  PubMed Central  Google Scholar 

  78. Jun, T. J. et al. Automated detection of vulnerable plaque in intravascular ultrasound images. Med. Biol. Eng. Comput. 57, 863–876 (2019).

    Article  PubMed  Google Scholar 

  79. Nicol, E. D. Machine learning assessment of CAD: a giant leap or a small step for coronary CTA? JACC Cardiovasc. Imaging 16, 206–208 (2023).

    Article  PubMed  Google Scholar 

  80. Nicol, E. D., Weir-McCall, J. R., Shaw, L. J. & Williamson, E. Great debates in cardiac computed tomography: OPINION: “artificial intelligence and the future of cardiovascular CT – Managing expectation and challenging hype”. J. Cardiovasc. Comput. Tomogr. https://doi.org/10.1016/j.jcct.2022.07.005 (2022).

    Article  PubMed  Google Scholar 

  81. US Food and Drug Administration. Artificial intelligence and machine learning (AI/ML)-enabled medical devices. FDA https://www.fda.gov/medical-devices/software-medical-device-samd/artificial-intelligence-and-machine-learning-aiml-enabled-medical-devices (2022).

  82. Muehlematter, U. J., Daniore, P. & Vokinger, K. N. Approval of artificial intelligence and machine learning-based medical devices in the USA and Europe (2015-20): a comparative analysis. Lancet Digit. Health 3, e195–e203 (2021).

    Article  CAS  PubMed  Google Scholar 

  83. Wu, E. et al. How medical AI devices are evaluated: limitations and recommendations from an analysis of FDA approvals. Nat. Med. 27, 582–584 (2021).

    Article  CAS  PubMed  Google Scholar 

  84. The Medical Futurist. FDA-approved A.I.-based algorithms. TMF https://medicalfuturist.com/fda-approved-ai-based-algorithms/ (2023).

  85. ACR Data Science Institute. Radiology SaMD dashboard. AI Central https://aicentral.acrdsi.org/ (2023).

  86. Radboud University Medical Center. Products. AI for Radiology https://grand-challenge.org/aiforradiology/ (2023).

  87. US Food and Drug Administration. Autoplaque: 510(k) premarket notification. FDA https://www.accessdata.fda.gov/scripts/cdrh/cfdocs/cfpmn/pmn.cfm?ID=K212758 (2023).

  88. Zhou, Q., Chen, Z. H., Cao, Y. H. & Peng, S. Clinical impact and quality of randomized controlled trials involving interventions evaluating artificial intelligence prediction tools: a systematic review. NPJ Digit. Med. 4, 154 (2021).

    Article  PubMed  PubMed Central  Google Scholar 

  89. Plana, D. et al. Randomized clinical trials of machine learning interventions in health care: a systematic review. JAMA Netw. Open. 5, e2233946 (2022).

    Article  PubMed  PubMed Central  Google Scholar 

  90. European Commission. Ethics guidelines for trustworthy AI. European Commission https://digital-strategy.ec.europa.eu/en/library/ethics-guidelines-trustworthy-ai (2019).

  91. Sounderajah, V. et al. Developing a reporting guideline for artificial intelligence-centred diagnostic test accuracy studies: the STARD-AI protocol. BMJ Open. 11, e047709 (2021).

    Article  PubMed  PubMed Central  Google Scholar 

  92. Vasey, B. et al. Reporting guideline for the early-stage clinical evaluation of decision support systems driven by artificial intelligence: DECIDE-AI. Nat. Med. 28, 924–933 (2022).

    Article  CAS  PubMed  Google Scholar 

  93. Liu, X. et al. Reporting guidelines for clinical trial reports for interventions involving artificial intelligence: the CONSORT-AI extension. Nat. Med. 26, 1364–1374 (2020).

    Article  CAS  PubMed  PubMed Central  Google Scholar 

  94. World Health Organization. Ethics and Governance of Artificial Intelligence for Health: WHO Guidance (WHO, 2021).

  95. Ugurlu, D. et al. in Statistical Atlases and Computational Models of the Heart. Multi-Disease, Multi-View, and Multi-Center Right Ventricular Segmentation in Cardiac MRI Challenge (eds Antón, E. P. et al.) 57–65 (Springer, 2022).

  96. Adamson, A. S. & Smith, A. Machine learning and health care disparities in dermatology. JAMA Dermatol. 154, 1247–1248 (2018).

    Article  PubMed  Google Scholar 

  97. Obermeyer, Z., Powers, B., Vogeli, C. & Mullainathan, S. Dissecting racial bias in an algorithm used to manage the health of populations. Science 366, 447–453 (2019).

    Article  CAS  PubMed  Google Scholar 

  98. Seyyed-Kalantari, L., Zhang, H., McDermott, M. B. A., Chen, I. Y. & Ghassemi, M. Underdiagnosis bias of artificial intelligence algorithms applied to chest radiographs in under-served patient populations. Nat. Med. 27, 2176–2182 (2021).

    Article  CAS  PubMed  PubMed Central  Google Scholar 

  99. Bavli, I. & Jones, D. S. Race correction and the X-ray machine – the controversy over increased radiation doses for black Americans in 1968. N. Engl. J. Med. 387, 947–952 (2022).

    Article  PubMed  Google Scholar 

  100. Bernhardt, M., Jones, C. & Glocker, B. Potential sources of dataset bias complicate investigation of underdiagnosis by machine learning algorithms. Nat. Med. 28, 1157–1158 (2022).

    Article  CAS  PubMed  Google Scholar 

  101. Suresh, H. & Guttag, J. A framework for understanding sources of harm throughout the machine learning life cycle. ACM Digital Library https://dl.acm.org/doi/pdf/10.1145/3465416.3483305 (2021).

  102. Dewey, M. & Wilkens, U. The Bionic Radiologist: avoiding blurry pictures and providing greater insights. NPJ Digit. Med. 2, 65 (2019).

    Article  PubMed  PubMed Central  Google Scholar 

  103. US Food and Drug Administration. vascuCAP: 510(k) premarket notification. FDA https://www.accessdata.fda.gov/cdrh_docs/pdf18/K183012.pdf (2018).

  104. Buckler, A. J. et al. Virtual transcriptomics: noninvasive phenotyping of atherosclerosis by decoding plaque biology from computed tomography angiography imaging. Arterioscler. Thromb. Vasc. Biol. 41, 1738–1750 (2021).

    Article  CAS  PubMed  PubMed Central  Google Scholar 

  105. Endovascular Today. CRISP consortium study evaluates Elucid Bio’s vascuCAP AI software to predict stroke. Endovascular Today https://evtoday.com/news/crisp-consortium-study-evaluates-elucid-bios-vascucap-ai-software-to-predict-stroke (2020).

  106. US Food and Drug Administration. cvi42: 510(k) premarket notification. FDA https://www.accessdata.fda.gov/cdrh_docs/pdf14/K141480.pdf (2014).

  107. US Food and Drug Administration. Syngo.CT CaScoring: 510(k) premarket notification. FDA https://www.accessdata.fda.gov/cdrh_docs/pdf20/K201034.pdf (2020).

  108. US Food and Drug Administration. iNtuition-Structural Heart Module: 510(k) premarket notification. FDA https://www.accessdata.fda.gov/cdrh_docs/pdf19/K191585.pdf (2019).

  109. US Food and Drug Administration. AI-Rad Companion (Cardiovascular): 510(k) premarket notification. FDA https://www.accessdata.fda.gov/cdrh_docs/pdf18/K183268.pdf (2019).

  110. US Food and Drug Administration. AVIEW: 510(k) premarket notification. FDA https://www.accessdata.fda.gov/cdrh_docs/pdf20/K200714.pdf (2020).

  111. Radboud University Medical Center. AVIEW CAC: Coreline Soft. AI for Radiology https://grand-challenge.org/aiforradiology/product/coreline-soft-aview-cac/ (2022).

  112. US Food and Drug Administration. Cleerly Labs v2.0: 510(k) premarket notification. FDA https://www.accessdata.fda.gov/cdrh_docs/pdf20/K202280.pdf (2020).

  113. US Food and Drug Administration. Cleerly Labs: 510(k) premarket notification. FDA https://www.accessdata.fda.gov/cdrh_docs/pdf19/K190868.pdf (2019).

  114. US Food and Drug Administration. HealthCCSng: 510(k) premarket notification. FDA https://www.accessdata.fda.gov/cdrh_docs/pdf21/K210085.pdf (2021).

  115. Business Wire. Nanox announces issuance of American Medical Association New Category III CPT® code for its coronary artery calcium population health solution. businesswire https://www.businesswire.com/news/home/20220111005789/en/Nanox-Announces-Issuance-of-American-Medical-Association-New-Category-III-CPT%C2%AE-Code-for-Its-Coronary-Artery-Calcium-Population-Health-Solution (2022).

  116. US Food and Drug Administration. HeartFlow Analysis: 510(k) premarket notification. FDA https://www.accessdata.fda.gov/cdrh_docs/pdf21/K213857.pdf (2022).

  117. Radboud University Medical Center. HeartFlow FFRCT Analysis: HeartFlow. AI for Radiology https://grand-challenge.org/aiforradiology/product/heartflow-ffrct-analysis/ (2022).

  118. US Food and Drug Administration. OPTIS™ Mobile Next Imaging System, OPTIS™ Integrated Next Imaging System with Ultreon™ Software 1.0: 510(k) premarket notification. FDA https://www.accessdata.fda.gov/cdrh_docs/pdf21/K210458.pdf (2021).

  119. Abbott. Abbott receives FDA clearance for its imaging technology using artificial intelligence for vessels in the heart. Abbott https://abbott.mediaroom.com/2021-08-03-Abbott-Receives-FDA-Clearance-for-its-Imaging-Technology-Using-Artificial-Intelligence-for-Vessels-in-the-Heart (2021).

  120. Cury, R. C. et al. CAD-RADS 2.0 - 2022 Coronary Artery Disease-Reporting and Data System: an expert consensus document of the Society of Cardiovascular Computed Tomography (SCCT), the American College of Cardiology (ACC), the American College of Radiology (ACR), and the North America Society of Cardiovascular Imaging (NASCI). J. Cardiovasc. Comput. Tomogr. 16, 536–557 (2022).

    Article  PubMed  Google Scholar 

Download references

Acknowledgements

We thank the German Research Foundation (grant number DE 1361/22-1) for funding the second Quantitative Cardiovascular Imaging meeting. M.C.W. is supported by the British Heart Foundation (FS/ICRF/20/26002). D.D. has received software royalties from Cedars–Sinai Medical Center and grant support from NIH/NHLBI. D.R. is supported by the ERC Advanced Grant Deep4MI, as well as by grants from the British Heart Foundation, Bundesministerium für Bildung und Forschung, Deutsche Forschungsgemeinschaft, EU Horizon 2020, Engineering and Physical Sciences Research Council and InnovateUK. He is a recipient of the Alexander Humboldt Professorship for AI. J.A.S. is supported by a Helmholtz Distinguished Professorship and a TUM Liesel Beckmann Professorship, as well as by grants from the British Heart Foundation, Bundesministerium für Gesundheit, Cancer Research UK, Engineering and Physical Sciences Research Council, InnovateUK, The Royal Society and The Wellcome Trust. D.E.N. has received research funding from the British Heart Foundation, Chest Heart Stroke Scotland, Chief Scientist Office, Medical Research Council and The Wellcome Trust. M.R.D. is supported by the British Heart Foundation (FS/SCRF/21/32010) and is the recipient of the Sir Jules Thorn Award for Biomedical Research 2015 (15/JTA). M.D. has received grant support from the FP7 Programme of the European Commission for the DISCHARGE trial (EC-GA 603266 in HEALTH.2013.2.4.2-2), and has also received grant support from the German Research Foundation in the Heisenberg Programme (DE 1361/14-1, DFG project 213705389), the graduate programme on quantitative biomedical imaging (BIOQIC, GRK 2260/1, DFG project 289347353) and for fractal analysis of myocardial perfusion (DE 1361/18-1, DFG project 392304398), the DFG Priority Programme Radiomics (DFG project 402688427) for the investigation of coronary plaque and coronary flow (DE 1361/19-1 (DFG project 428222922) and DE 1361/20-1 (DFG project 428223139) in SPP 2177/1), the GUIDE-IT project on data sharing of medical imaging trials (DE 1361/24-1 (DFG project 495697118)), the Quantitative Cardiovascular Imaging meeting (DE 1361/22-1) and the Future of Medical Imaging meeting (DE 1361/28-1). He has also received funding from the Berlin University Alliance (GC_SC_PC 27) and from the Digital Health Accelerator of the Berlin Institute of Health.

Author information

Author notes

  1. These authors contributed equally: Bernhard Föllmer, Michelle C. Williams.

  2. These authors jointly supervised this work: Ivana Išgum, Marc Dewey.

Authors and Affiliations

  1. Department of Radiology, Charité – Universitätsmedizin Berlin, Berlin, Germany

    Bernhard Föllmer, Aldo J. Vázquez Mézquita, Federico Biavati & Marc Dewey

  2. Centre for Cardiovascular Science, University of Edinburgh, Edinburgh, UK

    Michelle C. Williams, David E. Newby & Marc R. Dweck

  3. Biomedical Imaging Research Institute and Department of Imaging, Medicine and Biomedical Sciences, Cedars–Sinai Medical Center, Los Angeles, CA, USA

    Damini Dey

  4. Division of Cardiology, Department of Medicine, The Johns Hopkins University School of Medicine, Baltimore, MD, USA

    Armin Arbab-Zadeh

  5. Department of Radiology, Medical Imaging Center, Semmelweis University, Budapest, Hungary

    Pál Maurovich-Horvat

  6. Department of Cardiology, Radboud University Medical Center, Nijmegen, Netherlands

    Rick H. J. A. Volleberg

  7. Artificial Intelligence in Medicine and Healthcare, Technical University of Munich, Munich, Germany

    Daniel Rueckert

  8. Department of Computing, Imperial College London, London, UK

    Daniel Rueckert

  9. School of Biomedical Imaging and Imaging Sciences, King’s College London, London, UK

    Julia A. Schnabel

  10. Institute of Machine Learning in Biomedical Imaging, Helmholtz Munich, Neuherberg, Germany

    Julia A. Schnabel

  11. School of Computation, Information and Technology, Technical University of Munich, Munich, Germany

    Julia A. Schnabel

  12. Division of Cardiology, IRCCS Galeazzi Sant’Ambrogio Hospital, Milan, Italy

    Giulio Guagliumi

  13. Department of Cardiothoracic and Vascular Surgery, Deutsches Herzzentrum der Charité, Charité Universitätsmedizin, Berlin, Germany

    Volkmar Falk

  14. Department of Health Science and Technology, ETH Zurich, Zurich, Switzerland

    Volkmar Falk

  15. Berlin Institute of Health at Charité and DZHK (German Centre for Cardiovascular Research), Partner Site, Berlin, Germany

    Volkmar Falk

  16. Department of Biomedical Engineering and Physics, Amsterdam University Medical Center, University of Amsterdam, Amsterdam, Netherlands

    Ivana Išgum

  17. Department of Radiology and Nuclear Medicine, Amsterdam UMC, University of Amsterdam, Amsterdam, Netherlands

    Ivana Išgum

  18. Informatics Institute, Faculty of Science, University of Amsterdam, Amsterdam, Netherlands

    Ivana Išgum

  19. Berlin Institute of Health, Campus Charité Mitte, Berlin, Germany

    Marc Dewey

  20. DZHK (German Centre for Cardiovascular Research), Partner Site Berlin and Deutsches Herzzentrum der Charité (DHZC), Charité – Universitätsmedizin Berlin, Berlin, Germany

    Marc Dewey

Authors
  1. Bernhard Föllmer
    View author publications

    You can also search for this author in PubMed Google Scholar

  2. Michelle C. Williams
    View author publications

    You can also search for this author in PubMed Google Scholar

  3. Damini Dey
    View author publications

    You can also search for this author in PubMed Google Scholar

  4. Armin Arbab-Zadeh
    View author publications

    You can also search for this author in PubMed Google Scholar

  5. Pál Maurovich-Horvat
    View author publications

    You can also search for this author in PubMed Google Scholar

  6. Rick H. J. A. Volleberg
    View author publications

    You can also search for this author in PubMed Google Scholar

  7. Daniel Rueckert
    View author publications

    You can also search for this author in PubMed Google Scholar

  8. Julia A. Schnabel
    View author publications

    You can also search for this author in PubMed Google Scholar

  9. David E. Newby
    View author publications

    You can also search for this author in PubMed Google Scholar

  10. Marc R. Dweck
    View author publications

    You can also search for this author in PubMed Google Scholar

  11. Giulio Guagliumi
    View author publications

    You can also search for this author in PubMed Google Scholar

  12. Volkmar Falk
    View author publications

    You can also search for this author in PubMed Google Scholar

  13. Aldo J. Vázquez Mézquita
    View author publications

    You can also search for this author in PubMed Google Scholar

  14. Federico Biavati
    View author publications

    You can also search for this author in PubMed Google Scholar

  15. Ivana Išgum
    View author publications

    You can also search for this author in PubMed Google Scholar

  16. Marc Dewey
    View author publications

    You can also search for this author in PubMed Google Scholar

Contributions

B.F. and M.D. researched data for the article. B.F., M.C.W. and M.D. contributed to the discussion of content. B.F., M.C.W., D.D., A.A.-Z., P.M.-H., R.H.J.A.V., D.R. J.A.S., D.E.N., M.R.D., G.G., V.F., A.J.V.M., F.B., I.I. and M.D. wrote the manuscript. All authors contributed to reviewing and editing the manuscript before submission.

Corresponding authors

Correspondence to Bernhard Föllmer or Marc Dewey.

Ethics declarations

Competing interests

M.C.W. has given talks for Canon Medical Systems, Novartis and Siemens Healthineers. A.A.-Z. has received research support from Canon Medical Systems. P.M.-H. is a shareholder of Neumann Medical. D.R. has received consultancy fees from Heartflow and IXICO. D.E.N. receives grants, acts as a consultant and has clinical trial contracts with Abbott, Amgen, AstraZeneca, Autoplaque, BMS, Boehringer Ingelheim, Eli Lilly, GE HealthCare, GSK, Janssen, Life Molecular Imaging, MSD, Novartis, Pfizer, Philips, Roche, Sanofi, Siemens, Silence, SOFIE, Toshiba, UCB, Vifor, Wyeth and Zealand. He collaborates with the publications chair from the BMJ Group and Elsevier. He is the chief investigator of the SCOT-HEART and PRE18FFIR trials. M.R.D. has received speaker fees from Edwards, Novartis and Pfizer and consultancy fees from Beren, Jupiter Bioventures, Novartis and Silence Therapeutics. G.G. has a consultant agreement with Abbott Vascular, Gentuity, Infraredx and Panovision, and has received a research grant in the past 36 months from Abbott Vascular, Amgen and Infraredx. V.F. has received educational grants, fees for lectures and speeches, fees for professional consultation, as well as research and study funds from Abbott, Abiomed, Berlin Heart, Biotronik, Boston Scientific, Edwards Lifesciences, JOTEC/CryoLife, LivaNova, Medtronic, Novartis and Zurich Heart. I.I. has received institutional research grants by Esaote and Pie Medical Imaging and received an institutional research grant funded by Dutch Technology Foundation with the participation of Pie Medical Imaging and Philips Healthcare. She is also a co-inventor on several patents (US 10,176,575 B2; US 10,395,366 B2; US 11,004,198 B2; US 10,699,407 B2) and patent applications (17317746, 16911323) on the detection of functionally significant coronary stenosis. M.D. is the publications chair of the European Society of Radiology (ESR; 2022–2025); the opinions expressed in this article are the author’s own and do not represent the view of the ESR. He is also the editor of Cardiac CT (published by Springer Nature) and has institutional master research agreements with Canon, General Electric, Philips and Siemens, the arrangements of which are managed by Charité – Universitätsmedizin Berlin. He also holds a joint approved patent on dynamic perfusion analysis using fractal analysis (EPO 2022 EP3350773A1 and USPTO 2021 10,991,109). The other authors declare no competing interests.

Peer review

Peer review information

Nature Reviews Cardiology thanks Carlo de Cecco; Joseph Schoepf, who co-reviewed with Daniel Pinos Sanchez; and Christian Tesche for their contribution to the peer review of this work.

Additional information

Publisher’s note Springer Nature remains neutral with regard to jurisdictional claims in published maps and institutional affiliations.

Supplementary information

Rights and permissions

Springer Nature or its licensor (e.g. a society or other partner) holds exclusive rights to this article under a publishing agreement with the author(s) or other rightsholder(s); author self-archiving of the accepted manuscript version of this article is solely governed by the terms of such publishing agreement and applicable law.

Reprints and Permissions

About this article

Check for updates. Verify currency and authenticity via CrossMark

Cite this article

Föllmer, B., Williams, M.C., Dey, D. et al. Roadmap on the use of artificial intelligence for imaging of vulnerable atherosclerotic plaque in coronary arteries. Nat Rev Cardiol (2023). https://doi.org/10.1038/s41569-023-00900-3

Download citation

  • Accepted:

  • Published:

  • DOI: https://doi.org/10.1038/s41569-023-00900-3

This article is cited by

Search

Advanced search

Quick links

Nature Briefing

Sign up for the Nature Briefing newsletter — what matters in science, free to your inbox daily.

Get the most important science stories of the day, free in your inbox. Sign up for Nature Briefing