Comparison of Evaluation Metrics for Landmark Detection in CMR Images

TL;DR

This paper compares various evaluation metrics for landmark detection in cardiac MRI images, revealing pitfalls and emphasizing the need for standardized, comprehensive metrics to improve the reliability of deep learning methods in this domain.

Contribution

It extends the ACDC dataset with new labels and systematically analyzes the limitations of common detection metrics in cardiac landmark localization.

Findings

Different metrics yield different method rankings.

Simple detection metrics can be misleading.

Standardization of evaluation metrics is necessary.

Abstract

Cardiac Magnetic Resonance (CMR) images are widely used for cardiac diagnosis and ventricular assessment. Extracting specific landmarks like the right ventricular insertion points is of importance for spatial alignment and 3D modeling. The automatic detection of such landmarks has been tackled by multiple groups using Deep Learning, but relatively little attention has been paid to the failure cases of evaluation metrics in this field. In this work, we extended the public ACDC dataset with additional labels of the right ventricular insertion points and compare different variants of a heatmap-based landmark detection pipeline. In this comparison, we demonstrate very likely pitfalls of apparently simple detection and localisation metrics which highlights the importance of a clear detection strategy and the definition of an upper limit for localisation-based metrics. Our preliminary results indicate that a combination of different metrics is necessary, as they yield different winners for method comparison. Additionally, they highlight the need of a comprehensive metric description and evaluation standardisation, especially for the error cases where no metrics could be computed or where no lower/upper boundary of a metric exists. Code and labels: https://github.com/Cardio-AI/rvip_landmark_detection