Automated Landmark Detection for assessing hip conditions: A Cross-Modality Validation of MRI versus X-ray

TL;DR

This work tackles automated hip FAI landmark-based angle measurement by framing it as four-point localization and validating cross-modality performance on matched X-ray and MRI data. Using heatmap regression with a UNet++/ResNet18 backbone, the method localizes four landmarks (FHC, NA, LAE, LCP) to compute $\alpha$-angle and $LCE$-angle, achieving MRI and X-ray equivalence in localization and cam-type detection. Key results show MRI achieving $\text{MRE}=2.98\pm0.23\text{ mm}$ versus $3.02\pm0.10\text{ mm}$ on X-ray, and cam-type diagnostic accuracy of $87.5\%$ in both modalities, with strong LCE agreement and more variable $\alpha$-angle agreement due to landmark ambiguity. The findings support integrating automated MRI-based FAI assessment into clinical workflows and provide a foundation for future volumetric MRI analyses and uncertainty-aware predictions.

Abstract

Many clinical screening decisions are based on angle measurements. In particular, FemoroAcetabular Impingement (FAI) screening relies on angles traditionally measured on X-rays. However, assessing the height and span of the impingement area requires also a 3D view through an MRI scan. The two modalities inform the surgeon on different aspects of the condition. In this work, we conduct a matched-cohort validation study (89 patients, paired MRI/X-ray) using standard heatmap regression architectures to assess cross-modality clinical equivalence. Seen that landmark detection has been proven effective on X-rays, we show that MRI also achieves equivalent localisation and diagnostic accuracy for cam-type impingement. Our method demonstrates clinical feasibility for FAI assessment in coronal views of 3D MRI volumes, opening the possibility for volumetric analysis through placing further landmarks. These results support integrating automated FAI assessment into routine MRI workflows. Code is released at https://github.com/Malga-Vision/Landmarks-Hip-Conditions

Figures (3)

• Figure 1: FAI assessment from paired T1 MRI (top) and X-ray (bottom). The $\alpha$-angle and LCE angle quantify femoral head asphericity and acetabular coverage, respectively. Our study confirms that automated landmark detection achieves equivalent accuracy across modalities, confirming the feasibility of MRI landmark detection.
• Figure 2: Example of paired anteroposterior pelvic X-ray and corresponding T1-weighted MRI (slice 10) from the same subject, showing annotated landmarks: femoral head centre (FHC), neck-axis point (NA), lateral acetabular edge (LAE), and lateral cam point (LCP), illustrating their spatial correspondence across modalities.
• Figure 3: Bland--Altman plots comparing predicted and ground-truth $\alpha$- (left) and LCE-angles (right) for MRI (a) and X-ray (b).