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

Roberto Di Via, Vito Paolo Pastore, Francesca Odone, Siôn Glyn-Jones, Irina Voiculescu
1/26/2026
cs.CV

Official code: Malga-Vision/Landmarks-Hip-Conditions (0 stars, MIT, last commit 2026-01-26). 1 more implementation below.

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

View on arXivView PDF

Code Implementations(2)

Malga-Vision/Landmarks-Hip-ConditionsOfficial100%
MIT

Official repository of the paper "AUTOMATED LANDMARK DETECTION FOR ASSESSING HIP CONDITIONS: A CROSS-MODALITY VALIDATION OF MRI VERSUS X-RAY" accepted at ISBI 2026.

00PythonJan 23, 20268 months agoMIT
clinical-decision-supportequivalencelandmark-detectionmrivolumetric-computing+1 more
Malga-Vision/Landmarks-Hip-Conditions-AcademicPageOfficial100%

Academic page for the paper "AUTOMATED LANDMARK DETECTION FOR ASSESSING HIP CONDITIONS: A CROSS-MODALITY VALIDATION OF MRI VERSUS X-RAY" accepted at ISBI 2026.

00CSS, HTMLMar 6, 20267 months ago
clinical-decision-supportequivalencelandmark-detectionmrivolumetric-computing+1 more

Similar Papers

UAE: Universal Anatomical Embedding on Multi-modality Medical Images

79% match1 repo832023

Label Augmentation Method for Medical Landmark Detection in Hip Radiograph Images

79% match1 repo22023

Calculation of Femur Caput Collum Diaphyseal angle for X-Rays images using Semantic Segmentation

78% match2024

Retuve: Automated Multi-Modality Analysis of Hip Dysplasia with Open Source AI

78% match1 repo112025

Optimising for the Unknown: Domain Alignment for Cephalometric Landmark Detection

77% match1 repo82024

UNSCT-HRNet: Modeling Anatomical Uncertainty for Landmark Detection in Total Hip Arthroplasty

77% match2024

Cite this paper

@article{via2026automated,
  title  = {Automated Landmark Detection for assessing hip conditions: A Cross-Modality Validation of MRI versus X-ray},
  author = {Roberto Di Via and Vito Paolo Pastore and Francesca Odone and Siôn Glyn-Jones and Irina Voiculescu},
  year   = {2026},
  eprint = {2601.18555},
  archivePrefix = {arXiv},
  url    = {http://arxiv.org/abs/2601.18555v1}
}

Add a badge to your README

Shows whether official code is linked for this paper.

Code of Paper badge
[![Code of Paper](https://codeofpaper.com/badge/2601.18555.svg)](https://codeofpaper.com/paper/2601.18555)

Discussion