IEEE Access (Jan 2025)

Optimization and Benchmarking of Image Segmentation for Improved Landmark Detection in Lower Limb X-Rays and Accurate Coronal Plane Alignment of the Knee Classification

  • Sebastian Amador Sanchez,
  • Ashkan Zarghami,
  • Philippe van Overschelde,
  • Jef Vandemeulebroucke

DOI
https://doi.org/10.1109/ACCESS.2025.3572342
Journal volume & issue
Vol. 13
pp. 92350 – 92364

Abstract

Read online

Recent studies have explored image segmentation for landmark detection in computer vision and medical imaging of the lower limb, showing promising results. However, the proposed methodologies vary significantly, and a comparison with existing methods is lacking. In the present study, we investigated image segmentation for landmark detection on full lower-limb X-rays in detail and benchmark it against conventional landmark detection approaches. We detected eight landmarks in full lower limb X-rays and investigated methodological aspects to optimize image segmentation performance: network architecture (U-Net vs. Swin-UNETR), mask size centered at the landmark position to segment, and coordinate computation technique from the segmentation map. We contrasted image segmentation against optimized heatmap, coordinate, and segmentation-guided coordinate regression methods. The evaluation assessed the landmark detection error and phenotype classification accuracy based on lower limb alignment. The optimal segmentation approach employed a U-Net to segment circular masks (radius = 15 pixels), using probability thresholding before the centroid computation. Regarding landmark detection accuracy, image segmentation (median Euclidean distance (interquartile range) = 1.16 mm (1.50 mm)) was more accurate than heatmap (1.19 mm (1.61 mm)), coordinate (3.11 mm (2.87 mm)), and segmentation-guided coordinate regression (1.47 mm (1.67 mm)). Image segmentation outperformed heatmap, coordinate, and segmentation-guided coordinate regression in phenotype classification accuracy, achieving an average F1-score of 0.79, versus 0.72, 0.47, and 0.77, respectively. Our study led to an optimized approach for landmark detection using image segmentation, outperforming alternative detection approaches tuned and tested on the same data, highlighting image segmentation’s potential for broader medical imaging research applications.

Keywords