X2P-Net: Context-Aware 2D/3D Vertebra Localization
Open Access
- 3 February 2026
- journal article
- research article
- Published by MDPI AG in Bioengineering
- Vol. 13 (2) , 178
Abstract
In the context of minimally invasive spine surgery, accurately estimating the 3D coordinates of the vertebrae from intraoperative 2D X-ray images is crucial for aligning preoperative data with the patient’s real-time posture. However, existing methods are hindered by the ill-posed nature of 2D-to-3D localization and the distinctive anatomical features of the spinal column, leading to ambiguities and reduced accuracy. In this paper, we introduce X2P-net, a novel prompt-guided and semantic context-enhanced 2D/3D vertebra detection framework. To achieve this, we design a novel Transformer architecture, referred to as BrickFormer, which can automatically extract the refined vertebral foreground context at low computational cost using a dual-attention mechanism. Comprehensive experiments were conducted to validate the proposed approach on two datasets: a large-scale synthetic dataset (BiSpineX) and a sheep spine dataset (SheepSpineX). Results obtained from these experiments demonstrate superior landmark localization performance of the proposed method compared to other state-of-the-art methods. Specifically, on the BiSpineX dataset, X2P-Net achieves percentages of 96.9% and 98.8% at 10 mm and 20 mm thresholds, respectively, a mean position error of 2.99 mm, and an of 0.9923. Similar superior performance was also observed when the proposed method was applied to the SheepSpineX dataset, with percentages of 98.4% and 100.0% at 10 mm and 20 mm thresholds, respectively, a mean position error of 1.08 mm, and an of 0.9972.
Keywords
Funding Information
- National Key Research and Development Program of China (2023YFB4706300)
- National Natural Science Foundation of China (62471293)
- National Natural Science Foundation of China (U20A20199)
This publication has 62 references indexed in Scilit:
- Deep learning for automatic vertebra analysis: A methodological survey of recent advancesComputerized Medical Imaging and Graphics, 2025
- Anatomical prior-based vertebral landmark detection for spinal disorder diagnosisArtificial Intelligence in Medicine, 2024
- Multi-perspective region-based CNNs for vertebrae labeling in intraoperative long-length imagesComputer Methods and Programs in Biomedicine, 2022
- 2D-to-3D: A Review for Computational 3D Image Reconstruction from X-ray ImagesArchives of Computational Methods in Engineering, 2022
- 3D hand pose estimation from a single RGB image through semantic decomposition of VAE latent spacePattern Analysis and Applications, 2022
- Deep 3D human pose estimation: A reviewComputer Vision and Image Understanding, 2021
- AdaFuse: Adaptive Multiview Fusion for Accurate Human Pose Estimation in the WildInternational Journal of Computer Vision, 2020
- Spinal navigation for minimally invasive thoracic and lumbosacral spine fixation: implications for radiation exposure, operative time, and accuracy of pedicle screw placementEuropean Spine Journal, 2018
- A 2D/3D correspondence building method for reconstruction of a patient-specific 3D bone surface model using point distribution models and calibrated X-ray imagesMedical Image Analysis, 2009
- Automated model-based vertebra detection, identification, and segmentation in CT imagesMedical Image Analysis, 2009