Robust Conformal Volume Estimation in 3D Medical Images

TL;DR

This paper introduces a new method for uncertainty quantification in 3D medical image volumetry that effectively handles distribution shifts by using compressed latent representations for density ratio estimation, improving predictive interval calibration.

Contribution

It proposes an efficient weighted conformal prediction approach utilizing latent space density ratio estimation to address covariate shifts in medical image analysis.

Findings

Reduces coverage error under covariate shifts

Effective in synthetic and real-world datasets

Accessible implementation available online

Abstract

Volumetry is one of the principal downstream applications of 3D medical image segmentation, for example, to detect abnormal tissue growth or for surgery planning. Conformal Prediction is a promising framework for uncertainty quantification, providing calibrated predictive intervals associated with automatic volume measurements. However, this methodology is based on the hypothesis that calibration and test samples are exchangeable, an assumption that is in practice often violated in medical image applications. A weighted formulation of Conformal Prediction can be framed to mitigate this issue, but its empirical investigation in the medical domain is still lacking. A potential reason is that it relies on the estimation of the density ratio between the calibration and test distributions, which is likely to be intractable in scenarios involving high-dimensional data. To circumvent this, we propose an efficient approach for density ratio estimation relying on the compressed latent representations generated by the segmentation model. Our experiments demonstrate the efficiency of our approach to reduce the coverage error in the presence of covariate shifts, in both synthetic and real-world settings. Our implementation is available at https://github.com/benolmbrt/wcp_miccai