Automated Segmentation and Quantification of the Right Ventricle in 2-D Echocardiography

Chernyshov A, Grue JF, Nyberg J, Grenne B, Dalen H, Aase SA, Østvik A, Lovstakken L

In the work described we developed deep learning methods for automated segmentation and extraction of key clinical paremeters from the right ventricle. In particular, we explored a keypoint detection approach to segmentation that guards against erratic behavior often displayed by current segmentation models.

We used a data set of echo images focused on the right ventricle from 250 participants to train and evaluate several deep learning models. We proposed a compact architecture (U-Net KP) employing the keypoint approach, designed to balance high speed with accuracy and robustness. All featured models achieved segmentation accuracy close to the inter-observer variability. When computing the metrics of right ventricular systolic function from contour predictions of U-Net KP, we obtained the bias and 95% limits of agreement of 0.8 ± 10.8% for the right ventricular fractional area change measurements, –0.04 ± 0.54 cm for the tricuspid annular plane systolic excursion measurements and 0.2 ± 6.6% for the right ventricular free wall strain measurements. These results were also comparable to the semi-automatically derived inter-observer discrepancies of 0.4 ± 11.8%, –0.37 ± 0.58 cm and –1.0 ± 7.7% for the aforementioned metrics respectively.

In conclusion, given the appropriate data, automated segmentation and quantification of the right ventricle in 2-D echocardiography proved feasible with existing methods. Further, keypoint detection architectures may offer higher robustness and information density for the same computational cost.

Activity completed, link:
https://doi.org/10.1016/j.ultrasmedbio.2023.12.018