Bayesian Optimization of 2D Echocardiography Segmentation
This work addresses hyperparameter tuning for echocardiography segmentation in cardiology, but it is incremental as it applies an existing optimization method to a known model.
The authors tackled the problem of optimizing hyperparameters for echocardiography segmentation using Bayesian Optimization, resulting in improved performance over a recent state-of-the-art model with mean Dice overlaps up to 0.96 and reduced errors in clinical indices such as LV end-diastolic volume (4.9mL vs. 6.7mL).
Bayesian Optimization (BO) is a well-studied hyperparameter tuning technique that is more efficient than grid search for high-cost, high-parameter machine learning problems. Echocardiography is a ubiquitous modality for evaluating heart structure and function in cardiology. In this work, we use BO to optimize the architectural and training-related hyperparameters of a previously published deep fully convolutional neural network model for multi-structure segmentation in echocardiography. In a fair comparison, the resulting model outperforms this recent state-of-the-art on the annotated CAMUS dataset in both apical two- and four-chamber echo views. We report mean Dice overlaps of 0.95, 0.96, and 0.93 on left ventricular (LV) endocardium, LV epicardium, and left atrium respectively. We also observe significant improvement in derived clinical indices, including smaller median absolute errors for LV end-diastolic volume (4.9mL vs. 6.7), end-systolic volume (3.1mL vs. 5.2), and ejection fraction (2.6% vs. 3.7); and much tighter limits of agreement, which were already within inter-rater variability for non-contrast echo. These results demonstrate the benefits of BO for echocardiography segmentation over a recent state-of-the-art framework, although validation using large-scale independent clinical data is required.