Interpretable Machine Learning for Automated Left Ventricular Scar Quantification in Hypertrophic Cardiomyopathy Patients
Zeinab Navidi, Jesse Sun, Raymond H. Chan, Kate Hanneman, Amna Al-Arnawoot, Alif Munim, Harry Rakowski, Martin S. Maron, Anna Woo, Bo Wang,Wendy Tsang
Scar quantification on cardiovascular magnetic resonance (CMR) late gadolinium enhancement (LGE) images is important in risk stratifying patients with hypertrophic cardiomyopathy (HCM) due to the importance of scar burden in predicting clinical outcomes. We aimed to develop a machine learning (ML) model that contours left ventricular (LV) endo- and epicardial borders and quantifies CMR LGE images from HCM patients.
Hypertrophic cardiomyopathy (HCM) is the most common inheritable cardiomyopathy with a reported prevalence as high as 1 in 200. Patients with HCM can develop myocardial fibrosis, which is associated with heart failure and sudden cardiac death. Late gadolinium enhancement (LGE) techniques on cardiovascular magnetic resonance (CMR) imaging allow for non-invasive detection and quantification of fibrosis in patients with HCM.
Materials and Methods:
The diagnosis of HCM was made clinically as per societal guidelines. Baseline demographics and clinical characteristics were obtained from the patient’s electronic medical record.
CMR imaging was performed using 1.5T or 3T scanners (Achieva, Philips, the Netherlands; or Avanto/Skyra_fit/Signa Excite/Verio, Siemens, Germany) using steady-state, free-precession breath-hold cines in sequential short-axis slices from the atrioventricular ring to the apex (6–8 mm slices with 0–2 mm inter-slice gap).
CMR Image Analysis
LV endo- and epicardial contouring and LGE scar quantification were performed using commercially available software packages (QMASS DSI version 7.4, Medis Medical Imaging, Leiden, Netherlands; CVi42 5.11.1, Circle Cardiovascular Imaging, Calgary, Canada) (S3 Table).
In this study, we have used multicenter CMR data to successfully develop and validate a fully automated deep learning algorithm that contours the LV endo- and epicardial borders and quantifies LGE in patients with HCM. Based on the experiments we performed, our pipeline provides more accurate and robust scar quantification as it was trained with data from different sites, vendors, readers, and analysis packages.
Citation: Navidi Z, Sun J, Chan RH, Hanneman K, Al-Arnawoot A, Munim A, et al. (2023) Interpretable machine learning for automated left ventricular scar quantification in hypertrophic cardiomyopathy patients. PLOS Digit Health 2(1): e0000159. https://doi.org/10.1371/journal.pdig.0000159
Editor: Rutwik Shah, UCSF: University of California San Francisco, UNITED STATES
Received: September 18, 2022; Accepted: November 9, 2022; Published: January 4, 2023.
Copyright: © 2023 Navidi et al. This is an open access article distributed under the terms of the Creative Commons Attribution License, which permits unrestricted use, distribution, and reproduction in any medium, provided the original author and source are credited.
Data Availability: Data cannot be shared publicly because of HIPAA requirements. For data requests, please contact the corresponding author at email@example.com. All code is available in a public link: https://drive.google.com/drive/folders/1197aHAFmLWqknuvrKAm51i7fH4q8c7Bo and will be shared on GitHub after publication.
Funding: Funding for this study was provided by the Peter Munk Cardiology Center Innovation Fund and the MSH-UHN AMO Innovation Fund. BW is partially supported by the CIFAR AI Chair Program. WT is supported by a Heart and Stroke Foundation of Canada National New Investigator Award. The funders had no role in study design, data collection and analysis, decision to publish, or preparation of the manuscript.
Competing interests: The authors declare that they have no competing interests.