Uncertainty Propagation for Echocardiography Clinical Metric Estimation via Contour Sampling

TL;DR

The paper addresses the challenge of propagating uncertainty from echocardiography images to clinically useful metrics. It introduces CASUS, a contour-based uncertainty framework that predicts per-point contour uncertainty, samples plausible contours via a posterior shape model with PCA, and propagates these samples to clinical metrics using Monte Carlo methods. The approach yields interpretable uncertainty for both contours and derived metrics (Area, FAC, Volume, EF) and demonstrates improved calibration on CAMUS and a private dataset, outperforming pixel-wise and some other baselines. The work provides an end-to-end, temporally-consistent pipeline for uncertainty-aware automated echocardiography metric estimation, with public code available for reproducibility.

Abstract

Echocardiography plays a fundamental role in the extraction of important clinical parameters (e.g. left ventricular volume and ejection fraction) required to determine the presence and severity of heart-related conditions. When deploying automated techniques for computing these parameters, uncertainty estimation is crucial for assessing their utility. Since clinical parameters are usually derived from segmentation maps, there is no clear path for converting pixel-wise uncertainty values into uncertainty estimates in the downstream clinical metric calculation. In this work, we propose a novel uncertainty estimation method based on contouring rather than segmentation. Our method explicitly predicts contour location uncertainty from which contour samples can be drawn. Finally, the sampled contours can be used to propagate uncertainty to clinical metrics. Our proposed method not only provides accurate uncertainty estimations for the task of contouring but also for the downstream clinical metrics on two cardiac ultrasound datasets. Code is available at: https://github.com/ThierryJudge/contouring-uncertainty.

Figures (5)

• Figure 1: Schematic of the CASUS framework illustrating the three core components: (1) prediction of contour point uncertainty, (2) a contour sampling mechanism, and (3) propagation of sampled contour uncertainties to compute clinical metrics.
• Figure 2: Example of the posterior shape model output for various partial inputs of a given left ventricle shape for different slack parameter values ($\epsilon^2$).
• Figure 3: (a) Example of the sampling process. Given the initial points (cyan stars), the posterior shape model output (blue) is merged with the predicted distribution (red) to obtain a distribution (magenta) from which points are sampled (cyan). (b) The predicted contour and uncertainty distributions in red and the points sampled with the PSM sampler in blue. (c) Temporal consistent sampling. The yellow curve shows an example of the failure case of independent sampling where the ED area (left) is larger than the ES area (right) resulting in a negative FAC greatly differing from the mean prediction. The time-consistent sampling produces distributions (magenta) that are consistent with the ES contour, resulting in a plausible contour for ED (cyan).
• Figure 4: Example predictions from different methods. Each row corresponds to a different method and each column a specific image. In each image, 10 samples are shown. The top left and right sub-images are the pixel-wise error and uncertainty maps, respectively. For each image, the pixel-wise calibration reliability diagram is plotted in the bottom left corner. The histogram indicates the number of samples in each bin. The last row corresponds to the CASUS method, where the red ellipses correspond to 95% confidence intervals for the location of each point.
• Figure 5: Reliability diagrams for the [TOP] CAMUS and [BOTTOM] private datasets. Each row shows the calibration diagram for each aleatoric method with and without MC Dropout for each metric by column. Dashed lines indicate perfect calibration.