Skip to main page content
U.S. flag

An official website of the United States government

Dot gov

The .gov means it’s official.
Federal government websites often end in .gov or .mil. Before sharing sensitive information, make sure you’re on a federal government site.

Https

The site is secure.
The https:// ensures that you are connecting to the official website and that any information you provide is encrypted and transmitted securely.

Access keys NCBI Homepage MyNCBI Homepage Main Content Main Navigation
. 2024 May 4;16(5):e59647.
doi: 10.7759/cureus.59647. eCollection 2024 May.

Evaluating a Novel AI Tool for Automated Measurement of the Aortic Root and Valve in Cardiac Magnetic Resonance Imaging

Jack Parker  1   2   3 , James Coey  4   1   2 , Tarek Alambrouk  4 , Samuel M Lakey  5 , Thomas Green  5 , Alexander Brown  5 , Ian Maxwell  6 , David P Ripley  5   6
Affiliations

Evaluating a Novel AI Tool for Automated Measurement of the Aortic Root and Valve in Cardiac Magnetic Resonance Imaging

Jack Parker et al. Cureus. .

Abstract

Objective Evaluating an artificial intelligence (AI) tool (AIATELLA, version 1.0; AIATELLA Oy, Helsinki, Finland) in interpreting cardiac magnetic resonance (CMR) imaging to produce measurements of the aortic root and valve by comparison of accuracy and efficiency with that of three National Health Service (NHS) cardiologists. Methods AI-derived aortic root and valve measurements were recorded alongside manual measurements from three experienced NHS consultant cardiologists (CCs) over three separate sites in the northeast part of the United Kingdom. The study utilised a comprehensive dataset of CMR images, with the intraclass correlation coefficient (ICC) being the primary measure of concordance between the AI and the cardiologist assessments. Patient imaging was anonymised and blinded at the point of transfer to a secure data server. Results The study demonstrates a high level of concordance between AI assessment of the aortic root and valve with NHS cardiologists (ICC of 0.98). Notably, the AI delivered results in 2.6 seconds (+/- 0.532) compared to a mean of 334.5 seconds (+/- 61.9) by the cardiologists, a statistically significant improvement in efficiency without compromising accuracy. Conclusion AI's accuracy and speed of analysis suggest that it could be a valuable tool in cardiac diagnostics, addressing the challenges of time-consuming and variable clinician-based assessments. This research reinforces AI's role in optimising the patient journey and improving the efficiency of the diagnostic pathway.

Keywords: aortic root; aortic root dilation; aortic valve; aortic valve disease; artificial intelligence; artificial intelligence in radiology; cardiac magnetic resonance (cmr); cardiovascular radiology; interobserver variability; measurement accuracy.

PubMed Disclaimer

Conflict of interest statement

AIATELLA has filed for a patent related to the method utilised by the AI tool to determine key landmarks and produce measurements from medical imaging. Patent application 20235369 - Finland - Machine Learning Based Landmark or Segment Detection From Medical Image Data.. Jack Parker is the CEO and co-founder of AIATELLA. He holds a majority shareholding in the company. James Coey is an unpaid advisor to AIATELLA.

Figures

Figure 1
Figure 1. Anatomical cross-sections and measurements of the aortic root and valve
This figure provides a comprehensive view of the aortic root, highlighting the levels of the aortic annulus, sinuses of Valsalva (SoV) and sinotubular junction (STJ). The main figure (left) illustrates the overall structure and the specific levels where measurements were taken. The sub-figures (right) provide detailed cross-sectional views at the aortic annulus and SoV levels, indicating the exact points of measurement. LCC: left coronary cusp, NCC: non-coronary cusp, RCC: right coronary cusp, LRC: left-right coronary commissure, NRC: non-coronary-right commissure, NLC: non-coronary-left commissure Printed with permission from Sue Simon, MS, CMI © CC-BY-ND 2024
Figure 2
Figure 2. CMR imaging with AI-generated measurements and landmarks
This figure presents an example of the cardiovascular magnetic resonance (CMR) imaging used in this study, featuring AI-generated measurements. The left panel illustrates the diastolic phase of the cardiac cycle, showcasing AI-identified anatomical landmarks including the left coronary cusp (LCC), non-coronary cusp (NCC), right coronary cusp (RCC), left-right coronary commissure (LRC), non-coronary-right commissure (NRC), and non-coronary-left commissure (NLC). The right panel depicts the systolic phase of the cardiac cycle, highlighting both the AI-detected landmarks and the area measurement of the aortic valve lumen, represented in yellow.
See this image and copyright information in PMC

Similar articles

See all similar articles

References

    1. Post-stenotic aortic dilatation. Wilton E, Jahangiri M. J Cardiothorac Surg. 2006;1:7. - PMC - PubMed
    1. Outcomes of patients with asymptomatic aortic stenosis followed up in heart valve clinics. Lancellotti P, Magne J, Dulgheru R, et al. JAMA Cardiol. 2018;3:1060–1068. - PMC - PubMed
    1. Root dilatation is more malignant than ascending aortic dilation. Kalogerakos PD, Zafar MA, Li Y, Mukherjee SK, Ziganshin BA, Rizzo JA, Elefteriades JA. J Am Heart Assoc. 2021;10:0. - PMC - PubMed
    1. Impact of selected comorbidities on the presentation and management of aortic stenosis. Rudolph T K, Messika-Zeitoun D, Frey N, et al. OpenHeart. 2020;7:0. - PMC - PubMed
    1. Diagnosis and management of acute aortic syndromes: dissection, penetrating aortic ulcer, and intramural hematoma. Sorber R, Hicks CW. Curr Cardiol Rep. 2022;24:209–216. - PMC - PubMed

LinkOut - more resources

  NODES
twitter 2