CheXmask-U: Quantifying uncertainty in landmark-based anatomical segmentation for X-ray images

TL;DR

This paper introduces a method for estimating uncertainty in landmark-based chest X-ray segmentation, demonstrating its ability to identify unreliable predictions and improve robustness, supported by a large annotated dataset with uncertainty measures.

Contribution

It proposes a hybrid neural network approach combining convolutional encoders with graph-based decoders to quantify uncertainty in X-ray landmark segmentation, and releases a large dataset with these uncertainty estimates.

Findings

Uncertainty measures increase with image corruption severity.

Uncertainty signals effectively identify unreliable predictions.

Supports out-of-distribution detection in chest X-ray segmentation.

Abstract

In this work, we study uncertainty estimation for anatomical landmark-based segmentation on chest X-rays. Inspired by hybrid neural network architectures that combine standard image convolutional encoders with graph-based generative decoders, and leveraging their variational latent space, we derive two complementary measures: (i) latent uncertainty, captured directly from the learned distribution parameters, and (ii) predictive uncertainty, obtained by generating multiple stochastic output predictions from latent samples. Through controlled corruption experiments we show that both uncertainty measures increase with perturbation severity, reflecting both global and local degradation. We demonstrate that these uncertainty signals can identify unreliable predictions by comparing with manual ground-truth, and support out-of-distribution detection on the CheXmask dataset. More importantly, we release CheXmask-U (huggingface.co/datasets/mcosarinsky/CheXmask-U), a large scale dataset of 657,566 chest X-ray landmark segmentations with per-node uncertainty estimates, enabling researchers to account for spatial variations in segmentation quality when using these anatomical masks. Our findings establish uncertainty estimation as a promising direction to enhance robustness and safe deployment of landmark-based anatomical segmentation methods in chest X-ray. A fully working interactive demo of the method is available at huggingface.co/spaces/matiasky/CheXmask-U and the source code at github.com/mcosarinsky/CheXmask-U.