Assessing Uncertainty Estimation Methods for 3D Image Segmentation under Distribution Shifts

TL;DR

This paper evaluates various uncertainty estimation methods for 3D medical image segmentation under distribution shifts, highlighting the importance of multimodal approaches for reliable healthcare diagnostics.

Contribution

It compares Bayesian and non-Bayesian uncertainty methods, emphasizing the effectiveness of multimodal posterior approaches in medical image segmentation.

Findings

Multimodal methods provide more reliable uncertainty estimates.

Uncertainty methods improve detection of distributionally shifted samples.

Multimodal approaches outperform unimodal ones in robustness.

Abstract

In recent years, machine learning has witnessed extensive adoption across various sectors, yet its application in medical image-based disease detection and diagnosis remains challenging due to distribution shifts in real-world data. In practical settings, deployed models encounter samples that differ significantly from the training dataset, especially in the health domain, leading to potential performance issues. This limitation hinders the expressiveness and reliability of deep learning models in health applications. Thus, it becomes crucial to identify methods capable of producing reliable uncertainty estimation in the context of distribution shifts in the health sector. In this paper, we explore the feasibility of using cutting-edge Bayesian and non-Bayesian methods to detect distributionally shifted samples, aiming to achieve reliable and trustworthy diagnostic predictions in segmentation task. Specifically, we compare three distinct uncertainty estimation methods, each designed to capture either unimodal or multimodal aspects in the posterior distribution. Our findings demonstrate that methods capable of addressing multimodal characteristics in the posterior distribution, offer more dependable uncertainty estimates. This research contributes to enhancing the utility of deep learning in healthcare, making diagnostic predictions more robust and trustworthy.