Fully Automated, Quality-Controlled Cardiac Analysis From CMR

TLDR

Cardiac magnetic resonance imaging is limited in clinical use by variable image quality, disease phenotype variability, and weaknesses in deep learning training, hindering automated ventricular function assessment. The study aimed to develop a fully automated, quality‑controlled framework for cardiac function analysis from CMR using deep learning. The framework includes a pre‑analysis DL image QC, a DL algorithm for biventricular segmentation in long‑axis and short‑axis views, myocardial feature‑tracking, and a post‑analysis QC, and was validated against manual analysis in 100 subjects and 700 QC evaluations. Automated DL analysis of CMR yielded left and right ventricular volumes, strain, and ejection/filling rates that correlated highly with manual measurements (r > 0.89) and showed negligible bias, while the QC detected erroneous outputs with 95 % sensitivity for volumes and 93 % for strain, enabling reference values from 2,029 exams.

Abstract

This study sought to develop a fully automated framework for cardiac function analysis from cardiac magnetic resonance (CMR), including comprehensive quality control (QC) algorithms to detect erroneous output.Analysis of cine CMR imaging using deep learning (DL) algorithms could automate ventricular function assessment. However, variable image quality, variability in phenotypes of disease, and unavoidable weaknesses in training of DL algorithms currently prevent their use in clinical practice.The framework consists of a pre-analysis DL image QC, followed by a DL algorithm for biventricular segmentation in long-axis and short-axis views, myocardial feature-tracking (FT), and a post-analysis QC to detect erroneous results. The study validated the framework in healthy subjects and cardiac patients by comparison against manual analysis (n = 100) and evaluation of the QC steps' ability to detect erroneous results (n = 700). Next, this method was used to obtain reference values for cardiac function metrics from the UK Biobank.Automated analysis correlated highly with manual analysis for left and right ventricular volumes (all r > 0.95), strain (circumferential r = 0.89, longitudinal r > 0.89), and filling and ejection rates (all r ≥ 0.93). There was no significant bias for cardiac volumes and filling and ejection rates, except for right ventricular end-systolic volume (bias +1.80 ml; p = 0.01). The bias for FT strain was <1.3%. The sensitivity of detection of erroneous output was 95% for volume-derived parameters and 93% for FT strain. Finally, reference values were automatically derived from 2,029 CMR exams in healthy subjects.The study demonstrates a DL-based framework for automated, quality-controlled characterization of cardiac function from cine CMR, without the need for direct clinician oversight.