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

2026-01-26

AI Summary

This study addresses the limitations of conventional femoroacetabular impingement (FAI) screening, which relies on two-dimensional X-ray angle measurements and often requires supplemental MRI for comprehensive three-dimensional morphological assessment. Leveraging paired MRI and X-ray data from 89 patients, the authors employ a heatmap regression approach to automatically localize anatomical landmarks in coronal MRI scans and systematically evaluate their clinical equivalence to X-ray–based metrics in assessing cam-type FAI. The results demonstrate that the automated MRI-based landmark localization achieves diagnostic accuracy and precision comparable to standard X-ray measurements. This work provides the first evidence that MRI alone can support fully automated FAI evaluation, thereby establishing a foundation for integrating such analysis into routine clinical MRI protocols and enabling subsequent three-dimensional volumetric assessments.

Technology Category

• Knowledge Representation and Reasoning: Diagnosis and Abductive Reasoning
• Intelligent Robots: Localization, Mapping, and Navigation
• Computer Vision: Multi-modal Vision

Application Category

• Search and Retrieval-Augmented AI: Web evaluation methodologies and metrics
• Web Mining and Content Analysis: Web measurements
• User Modeling, Personalization and Recommendation: Fairness-aware retrieval and ranking

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

Problem

• Automated Landmark Detection
• Femoroacetabular Impingement
• Cross-Modality Validation
• MRI
• X-ray

Innovation

• cross-modality validation
• automated landmark detection
• hip MRI
• FAI assessment
• heatmap regression