[Skip to Content]

Claim CME

Health Informatics

Deep Learning for Cardiovascular ImagingA Review

To identify the key insights or developments described in this article

1 Credit CME

JAMA Cardiology

Published Online: September 20, 2023

Review

Article Information and Disclosures

Ramsey M. Wehbe, MD, MSAI^1,2;

Aggelos K. Katsaggelos, PhD³;

Kristian J. Hammond, PhD⁴;

Ha Hong, PhD⁵;

Faraz S. Ahmad, MD, MS^2,6,9;

David Ouyang, MD⁷;

Sanjiv J. Shah, MD^2,9;

Patrick M. McCarthy, MD^8,9;

James D. Thomas, MD^2,9

Author Affiliations

¹Division of Cardiology, Department of Medicine & Biomedical Informatics Center, Medical University of South Carolina, Charleston
²Division of Cardiology, Department of Medicine, Northwestern University Feinberg School of Medicine, Chicago, Illinois
³Department of Computer and Electrical Engineering, Northwestern University, Evanston, Illinois
⁴Department of Computer Science, Northwestern University, Evanston, Illinois
⁵Medtronic, Minneapolis, Minnesota
⁶Center for Health Information Partnerships, Institute for Public Health and Medicine, Northwestern University Feinberg School of Medicine, Chicago, Illinois
⁷Division of Cardiology, Department of Medicine, Cedars-Sinai Medical Center, Los Angeles, California
⁸Division of Cardiac Surgery, Department of Surgery, Northwestern University Feinberg School of Medicine, Chicago, Illinois
⁹Center for Artificial Intelligence, Northwestern Medicine Bluhm Cardiovascular Institute, Chicago, Illinois

Read article on JAMA Network

Read Article Claim CME

Abstract

Importance Artificial intelligence (AI), driven by advances in deep learning (DL), has the potential to reshape the field of cardiovascular imaging (CVI). While DL for CVI is still in its infancy, research is accelerating to aid in the acquisition, processing, and/or interpretation of CVI across various modalities, with several commercial products already in clinical use. It is imperative that cardiovascular imagers are familiar with DL systems, including a basic understanding of how they work, their relative strengths compared with other automated systems, and possible pitfalls in their implementation. The goal of this article is to review the methodology and application of DL to CVI in a simple, digestible fashion toward demystifying this emerging technology.

Observations At its core, DL is simply the application of a series of tunable mathematical operations that translate input data into a desired output. Based on artificial neural networks that are inspired by the human nervous system, there are several types of DL architectures suited to different tasks; convolutional neural networks are particularly adept at extracting valuable information from CVI data. We survey some of the notable applications of DL to tasks across the spectrum of CVI modalities. We also discuss challenges in the development and implementation of DL systems, including avoiding overfitting, preventing systematic bias, improving explainability, and fostering a human-machine partnership. Finally, we conclude with a vision of the future of DL for CVI.

Conclusions and Relevance Deep learning has the potential to meaningfully affect the field of CVI. Rather than a threat, DL could be seen as a partner to cardiovascular imagers in reducing technical burden and improving efficiency and quality of care. High-quality prospective evidence is still needed to demonstrate how the benefits of DL CVI systems may outweigh the risks.

Claim CME

Sign in to take quiz and track your certificates

Buy This Activity

Article Information

Accepted for Publication: July 27, 2023.

Published Online: September 20, 2023. doi:10.1001/jamacardio.2023.3142

Correction: This article was corrected on November 8, 2023, to fix an author’s misspelled surname.

Corresponding Author: Ramsey M. Wehbe, MD, MSAI, Division of Cardiology & Biomedical Informatics Center, Medical University of South Carolina, 22 WestEdge St, Ste 200, Room WG213E, Charleston, SC 29403 (wehbe@musc.edu).

Conflict of Interest Disclosures: Dr Wehbe reported grants from the American Society of Nuclear Cardiology (ASNC Young Investigator Award in Cardiac Amyloidosis) and Pfizer (Global Medical Grants Program for Research in ATTR-Cardiac Amyloidosis); patents pending for AI-based extraction of digital waveforms from temporal strain analysis on echocardiography (No. 63/278,708) and DL-augmented interpretation of cardiac scintigraphy for ATTR-cardiac amyloidosis (No. 63/250,784); consultant fees from GE Healthcare; and investments in Microsoft Corporation. Dr Hammond reported being a co-founder of Narrative Science, with multiple patents related to the company, outside of the submitted work. Dr Hong reported personal fees from Caption Health as a former employee during the drafting of this manuscript and outside the submitted work; patents US20180153505A1 and US20200245970A1 pending; and patents US10631791B2, US10470677B2, and US10726548B2 issued. Dr Ahmad reported consulting fees from Amgen, Teladoc Livongo, and Pfizer outside the submitted work. Dr Ouyang reported research support from the National Institutes of Health (grant R00-HL157421); consulting for InVision, EchoIQ, Ultromics, Pfizer, AstraZeneca, and Alexion outside the submitted work; and having a patent pending for EchoNet-LVH. Dr Shah reported research grants from the National Institutes of Health (R01 HL107577, R01 HL127028, R01 HL140731, R01 HL149423), Actelion, AstraZeneca, Corvia, Novartis, and Pfizer and consulting fees from Abbott, Actelion, AstraZeneca, Amgen, Aria CV, Axon Therapies, Bayer, Boehringer Ingelheim, Boston Scientific, Bristol Myers Squibb, Cardiora, CVRx, Cytokinetics, Edwards Lifesciences, Eidos, Eisai, Imara, Impulse Dynamics, Intellia, Ionis, Ironwood, Lilly, Merck, MyoKardia, Novartis, Novo Nordisk, Pfizer, Prothena, Regeneron, Rivus, Sanofi, Shifamed, Tenax, Tenaya, and United Therapeutics. Dr McCarthy reported personal fees and royalties from Edwards Lifesciences, speaker fees or honoraria from Atricure and Medtronic, serving on an advisory board for Egnite, and serving as a principal investigator for a trial with Abbott Vascular outside the submitted work. Dr Thomas reported partial salary support from the Irene D. Pritzker Foundation during the conduct of the study; grants from Abbott Vascular and GE; personal fees from Caption Health, GE, Egnite, Edwards, Shire, and EchoIQ outside the submitted work; and spouse employment with Caption Health. No other disclosures were reported.

Funding/Support: Dr Wehbe is supported by the American Society of Nuclear Cardiology/Pfizer Young Investigator in Cardiac Amyloidosis Research Award and a separate grant from Pfizer’s Global Medical Grants Competitive Grant Program in Transthyretin Amyloid Cardiomyopathy Research. Dr Ahmad is supported by grants from the Agency for Healthcare Research and Quality (K12HS026385), National Institutes of Health (NIH) National Heart, Lung, and Blood Institute (K23HL155970), and American Heart Association (No. 856917). Dr Ouyang receives research support from the NIH (grant R00-HL157421). Dr Thomas is supported by a grant from the Irene D. Pritzker Foundation.

Role of the Funder/Sponsor: The funders had no role in the preparation, review, or approval of the manuscript or decision to submit the manuscript for publication.

Additional Information: Figures 1 and 2 and eFigures 4 and 7A in the Supplement were created with BioRender scientific image and illustration software.

AMA CME Accreditation Information

Credit Designation Statement: The American Medical Association designates this Journal-based CME activity activity for a maximum of 1.00  AMA PRA Category 1 Credit(s)™. Physicians should claim only the credit commensurate with the extent of their participation in the activity.

Successful completion of this CME activity, which includes participation in the evaluation component, enables the participant to earn up to:

1.00 Medical Knowledge MOC points in the American Board of Internal Medicine's (ABIM) Maintenance of Certification (MOC) program;;
1.00 Self-Assessment points in the American Board of Otolaryngology – Head and Neck Surgery’s (ABOHNS) Continuing Certification program;
1.00 MOC points in the American Board of Pediatrics’ (ABP) Maintenance of Certification (MOC) program;
1.00 Lifelong Learning points in the American Board of Pathology’s (ABPath) Continuing Certification program; and
1.00 credit toward the CME of the American Board of Surgery’s Continuous Certification program

It is the CME activity provider's responsibility to submit participant completion information to ACCME for the purpose of granting MOC credit.