| Title: | Fully Automated, Quality-Controlled Cardiac Analysis From CMR Validation and Large-Scale Application to Characterize Cardiac Function |
| Journal: | JACC Cardiovascular Imaging |
| Published: | 17 Jul 2019 |
| Pubmed: | https://pubmed.ncbi.nlm.nih.gov/31326477/ |
| DOI: | https://doi.org/10.1016/j.jcmg.2019.05.030 |
Publication 2223
WARNING: the interactive features of this website use CSS3, which your browser does not support. To use the full features of this website, please update your browser.
Abstract
OBJECTIVES: 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.</p>
BACKGROUND: 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.</p>
METHODS: 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.</p>
RESULTS: 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.</p>
CONCLUSIONS: 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.</p>
18 Keywords
- Aged
- Automation
- Deep Learning
- Diagnosis, Computer-Assisted
- Female
- Heart Diseases
- Humans
- Image Interpretation, Computer-Assisted
- Magnetic Resonance Imaging, Cine
- Male
- Middle Aged
- Predictive Value of Tests
- Quality Control
- Quality Indicators, Health Care
- Reproducibility of Results
- Stroke Volume
- Ventricular Function, Left
- Ventricular Function, Right
8 Authors
- Bram Ruijsink
- Esther Puyol-Antón
- Ilkay Oksuz
- Matthew Sinclair
- Wenjia Bai
- Julia A. Schnabel
- Reza Razavi
- Andrew P. King
1 Application
| Application ID | Title |
|---|---|
| 17806 | Motion-based diagnosis and characterisation of heart disease |
Enabling scientific discoveries that improve human health