Proceedings of the NHLBI Workshop on Artificial Intelligence in Cardiovascular Imaging: Translation to Patient Care.

Artificial intelligence (AI) promises to revolutionize many fields, but its clinical implementation in cardiovascular imaging is still rare despite increasing research. We sought to facilitate discussion across several fields and across the lifecycle of research, development, validation, and implementation to identify challenges and opportunities to further translation of AI in cardiovascular imaging. Furthermore, it seemed apparent that a multidisciplinary effort across institutions would be essential to overcome these challenges. This paper summarizes the proceedings of the National Heart, Lung, and Blood Institute-led workshop, creating consensus around needs and opportunities for institutions at several levels to support and advance research in this field and support future translation.

[1]  R. Arnaout,et al.  ENRICHing medical imaging training sets enables more efficient machine learning , 2023, J. Am. Medical Informatics Assoc..

[2]  R. Arnaout,et al.  Label-free segmentation from cardiac ultrasound using self-supervised learning , 2022, ArXiv.

[3]  D. Dey,et al.  Deep Learning–Based Attenuation Correction Improves Diagnostic Accuracy of Cardiac SPECT , 2022, The Journal of Nuclear Medicine.

[4]  D. Dey,et al.  Deep Learning for Explainable Estimation of Mortality Risk From Myocardial Positron Emission Tomography Images , 2022, Circulation. Cardiovascular imaging.

[5]  D. Dey,et al.  Deep Learning of Coronary Calcium Scores From PET/CT Attenuation Maps Accurately Predicts Adverse Cardiovascular Events. , 2022, JACC. Cardiovascular imaging.

[6]  D. Dey,et al.  Automated nonlinear registration of coronary PET to CT angiography using pseudo-CT generated from PET with generative adversarial networks , 2022, Journal of Nuclear Cardiology.

[7]  P. Hert,et al.  Transparency of AI in Healthcare as a Multilayered System of Accountabilities: Between Legal Requirements and Technical Limitations , 2022, Frontiers in Artificial Intelligence.

[8]  D. Dey,et al.  Explainable Deep Learning Improves Physician Interpretation of Myocardial Perfusion Imaging , 2022, The Journal of Nuclear Medicine.

[9]  D. Dey,et al.  Deep learning-enabled coronary CT angiography for plaque and stenosis quantification and cardiac risk prediction: an international multicentre study , 2022, The Lancet. Digital health.

[10]  Matthew B. A. McDermott,et al.  Underdiagnosis bias of artificial intelligence algorithms applied to chest radiographs in under-served patient populations , 2021, Nature Medicine.

[11]  A. Moran,et al.  Spending on Cardiovascular Disease and Cardiovascular Risk Factors in the United States: 1996 to 2016 , 2021, Circulation.

[12]  E. V. van Beek,et al.  Machine Learning with 18F-Sodium Fluoride PET and Quantitative Plaque Analysis on CT Angiography for the Future Risk of Myocardial Infarction , 2021, The Journal of Nuclear Medicine.

[13]  D. Dey,et al.  Metabolic syndrome, fatty liver, and artificial intelligence-based epicardial adipose tissue measures predict long-term risk of cardiac events: a prospective study , 2021, Cardiovascular Diabetology.

[14]  P. Parizel,et al.  Epicardial and pericardial fat analysis on CT images and artificial intelligence: a literature review. , 2021, Quantitative imaging in medicine and surgery.

[15]  Gary S Collins,et al.  Reporting guidelines for clinical trial reports for interventions involving artificial intelligence: the CONSORT-AI Extension , 2020, BMJ.

[16]  Kipp W. Johnson,et al.  Proposed Requirements for Cardiovascular Imaging-Related Machine Learning Evaluation (PRIME): A Checklist: Reviewed by the American College of Cardiology Healthcare Innovation Council. , 2020, JACC. Cardiovascular imaging.

[17]  Gary S Collins,et al.  Guidelines for clinical trial protocols for interventions involving artificial intelligence: the SPIRIT-AI Extension , 2020, Nature Medicine.

[18]  Angelica I. Avilés-Rivero,et al.  Common pitfalls and recommendations for using machine learning to detect and prognosticate for COVID-19 using chest radiographs and CT scans , 2020, Nature Machine Intelligence.

[19]  Lauren Wilcox,et al.  A Human-Centered Evaluation of a Deep Learning System Deployed in Clinics for the Detection of Diabetic Retinopathy , 2020, CHI.

[20]  Curtis P. Langlotz,et al.  Video-based AI for beat-to-beat assessment of cardiac function , 2020, Nature.

[21]  P Hendrik Pretorius,et al.  Improving Diagnostic Accuracy in Low-Dose SPECT Myocardial Perfusion Imaging With Convolutional Denoising Networks , 2020, IEEE Transactions on Medical Imaging.

[22]  P. Kellman,et al.  The Prognostic Significance of Quantitative Myocardial Perfusion , 2020, Circulation.

[23]  P. Kellman,et al.  Automated Inline Analysis of Myocardial Perfusion MRI with Deep Learning , 2019, Radiology. Artificial intelligence.

[24]  Tim Leiner,et al.  Artificial Intelligence Will Transform Cardiac Imaging—Opportunities and Challenges , 2019, Front. Cardiovasc. Med..

[25]  Erik Schultes,et al.  The FAIR Guiding Principles for scientific data management and stewardship , 2016, Scientific Data.

[26]  Deepak L. Bhatt,et al.  ACC/AHA/STS Statement on the Future of Registries and the Performance Measurement Enterprise: A Report of the American College of Cardiology/American Heart Association Task Force on Performance Measures and The Society of Thoracic Surgeons. , 2015, Journal of the American College of Cardiology.

[27]  J. West,et al.  Disruptive Innovation , 2015 .

[28]  Albert de Roos,et al.  Cardiac radiology: centenary review. , 2014, Radiology.

[29]  Majnu John,et al.  Facial Recognition Software Success Rates for the Identification of 3D Surface Reconstructed Facial Images: Implications for Patient Privacy and Security , 2012, Journal of Digital Imaging.

[30]  Andrew Y. Ng,et al.  Retrieval-Based Chest X-Ray Report Generation Using a Pre-trained Contrastive Language-Image Model , 2021, ML4H@NeurIPS.

[31]  Rohit Gupta,et al.  Super-Resolution using GANs for Medical Imaging , 2020 .