Uncertainty-Aware Annotation Protocol to Evaluate Deformable Registration Algorithms

TL;DR

This paper presents a new uncertainty-aware annotation protocol for deformable registration that improves gold standard creation, evaluation accuracy, and error visualization, by iteratively selecting informative points and accounting for annotation uncertainty.

Contribution

It introduces a principled, iterative framework that incorporates spatial uncertainty and informativeness in landmark annotation for deformable registration evaluation.

Findings

Effective annotation selection based on informativeness.

Enhanced evaluation of registration algorithms.

Dense error visualization from sparse annotations.

Abstract

Landmark correspondences are a widely used type of gold standard in image registration. However, the manual placement of corresponding points is subject to high inter-user variability in the chosen annotated locations and in the interpretation of visual ambiguities. In this paper, we introduce a principled strategy for the construction of a gold standard in deformable registration. Our framework: (i) iteratively suggests the most informative location to annotate next, taking into account its redundancy with previous annotations; (ii) extends traditional pointwise annotations by accounting for the spatial uncertainty of each annotation, which can either be directly specified by the user, or aggregated from pointwise annotations from multiple experts; and (iii) naturally provides a new strategy for the evaluation of deformable registration algorithms. Our approach is validated on four different registration tasks. The experimental results show the efficacy of suggesting annotations according to their informativeness, and an improved capacity to assess the quality of the outputs of registration algorithms. In addition, our approach yields, from sparse annotations only, a dense visualization of the errors made by a registration method. The source code of our approach supporting both 2D and 3D data is publicly available at https://github.com/LoicPeter/evaluation-deformable-registration.