Automated echocardiographic left ventricular strain measurements using deep learning
| Autor: | E Scheirlynck, Kristina H. Haugaa, Pål H. Brekke, Thor Edvardsen, Bernard Cosyns, S. Droogmans, C K Larsen, M Rogstadkjernet, Otto A. Smiseth, Lars Gunnar Klæboe, Sz Zha, Eigil Samset, John M Aalen |
|---|---|
| Rok vydání: | 2021 |
| Předmět: |
medicine.medical_specialty
Myocardial ischemia Longitudinal strain business.industry Deep learning General Medicine medicine.disease Heart failure Internal medicine Interobserver Variation medicine Cardiology Radiology Nuclear Medicine and imaging Artificial intelligence Systole Bland–Altman plot Cardiology and Cardiovascular Medicine business Left ventricular strain |
| Zdroj: | European Heart Journal - Cardiovascular Imaging. 22 |
| ISSN: | 2047-2412 2047-2404 |
| Popis: | Funding Acknowledgements Type of funding sources: Public grant(s) – National budget only. Main funding source(s): Research Council of Norway Background Speckle tracking echocardiography (STE) provides quantification of left ventricular (LV) deformation and is useful in the assessment of LV function. STE is increasingly being used clinically, and every effort to simplify and standardise STE is important. Manual outlining of regions of interest (ROIs) is labour intensive and may influence assessment of strain values. Purpose We hypothesised that ROIs from clinical echocardiographic exams could be used to train a deep learning (DL) model which could automate strain calculation by predicting ROIs with comparable fidelity to trained cardiologists. Methods Data consisted of still frames with cardiologist-defined ROIs from 435 clinical echocardiographic exams from a university hospital outpatient clinic. Exams included healthy subjects and patients with ischemic heart disease, heart failure, valvular disease and conduction abnormalities. Three frames surrounding mid-systole from standard apical views were paired with the mid-systolic ROI for training. Image quality was classified as high, medium or low by an experienced cardiologist prior to model training, and low quality images were excluded. The dataset was randomly split into 68%/17%/15% sets for training, validation and testing. A standard Unet architecture was used, with a combination of binary cross entropy and Dice loss functions. A total of 1025 images were used for final model training and testing, with augmentation used to extend the dataset. Predicted ROIs were reintroduced into commercially available echocardiographic analysis software to automatically calculate longitudinal strain (LS) values. Results The average absolute difference between manually measured and DL-assisted LS was 0.98 percentage points (95% confidence interval 0.82-1.13) for the final model. A Bland-Altman plot revealed very few outliers and no bias in the difference between manual and DL-assisted strain measurements. Conclusion The current study demonstrates that DL-assisted, automated strain measurement is feasible, and provides strain results within an acceptable range of intra- and interobserver variation. Employing DL in echocardiographic analysis could further facilitate adoption of STE parameters in clinical practice and research, and improve reproducibility. Abstract Figure. Bland-Altman plot. Manual and DL ROIs |
| Databáze: | OpenAIRE |
| Externí odkaz: |
|