Framing image registration as a landmark detection problem for label-noise-aware task representation (HitR)
This provides a more realistic evaluation for clinical and biomedical applications, though it is incremental as it builds on existing metrics.
The study tackled the challenge of evaluating image registration algorithms in biomedical image analysis by introducing the Landmark Hit Rate (HitR) metric, which assesses whether landmarks are positioned within confidence zones based on inter-rater variance, resulting in a more clinically relevant performance measurement.
Accurate image registration is pivotal in biomedical image analysis, where selecting suitable registration algorithms demands careful consideration. While numerous algorithms are available, the evaluation metrics to assess their performance have remained relatively static. This study addresses this challenge by introducing a novel evaluation metric termed Landmark Hit Rate (HitR), which focuses on the clinical relevance of image registration accuracy. Unlike traditional metrics such as Target Registration Error, which emphasize subresolution differences, HitR considers whether registration algorithms successfully position landmarks within defined confidence zones. This paradigm shift acknowledges the inherent annotation noise in medical images, allowing for more meaningful assessments. To equip HitR with label-noise-awareness, we propose defining these confidence zones based on an Inter-rater Variance analysis. Consequently, hit rate curves are computed for varying landmark zone sizes, enabling performance measurement for a task-specific level of accuracy. Our approach offers a more realistic and meaningful assessment of image registration algorithms, reflecting their suitability for clinical and biomedical applications.