Inter-Rater Uncertainty Quantification in Medical Image Segmentation via Rater-Specific Bayesian Neural Networks

TL;DR

This paper introduces a novel Bayesian neural network architecture to quantify inter-rater uncertainty in medical image segmentation, improving the understanding of expert variability in annotations.

Contribution

It proposes a rater-specific Bayesian neural network with attention modules, enabling effective modeling of inter-rater uncertainty with limited annotations.

Findings

Outperforms baseline methods on 5 of 7 tasks in the QUBIQ dataset.

Effectively captures inter-rater variability in synthetic and real-world data.

Provides publicly available code, models, and dataset for further research.

Abstract

Automated medical image segmentation inherently involves a certain degree of uncertainty. One key factor contributing to this uncertainty is the ambiguity that can arise in determining the boundaries of a target region of interest, primarily due to variations in image appearance. On top of this, even among experts in the field, different opinions can emerge regarding the precise definition of specific anatomical structures. This work specifically addresses the modeling of segmentation uncertainty, known as inter-rater uncertainty. Its primary objective is to explore and analyze the variability in segmentation outcomes that can occur when multiple experts in medical imaging interpret and annotate the same images. We introduce a novel Bayesian neural network-based architecture to estimate inter-rater uncertainty in medical image segmentation. Our approach has three key advancements. Firstly, we introduce a one-encoder-multi-decoder architecture specifically tailored for uncertainty estimation, enabling us to capture the rater-specific representation of each expert involved. Secondly, we propose Bayesian modeling for the new architecture, allowing efficient capture of the inter-rater distribution, particularly in scenarios with limited annotations. Lastly, we enhance the rater-specific representation by integrating an attention module into each decoder. This module facilitates focused and refined segmentation results for each rater. We conduct extensive evaluations using synthetic and real-world datasets to validate our technical innovations rigorously. Our method surpasses existing baseline methods in five out of seven diverse tasks on the publicly available \emph{QUBIQ} dataset, considering two evaluation metrics encompassing different uncertainty aspects. Our codes, models, and the new dataset are available through our GitHub repository: https://github.com/HaoWang420/bOEMD-net .