Logo
ScienceStack
Table of Contents
Fetching ...
Sign In

SX-Stitch: An Efficient VMS-UNet Based Framework for Intraoperative Scoliosis X-Ray Image Stitching

Yi Li, Heting Gao, Mingde He, Jinqian Liang, Jason Gu, Wei Liu

TL;DR

SX-Stitch tackles the challenge of achieving panoramic intraoperative scoliosis X-ray views despite limited C-arm FOV by delivering an end-to-end two-stage framework. It introduces VMS-UNet, a Vision Mamba-based Spine-UNet for accurate pedicle screw segmentation, followed by an energy-driven stitching pipeline that first aligns images using screw centroids and then fuses them along a hybrid seam to suppress parallax. The approach shows consistent improvements over state-of-the-art methods on clinical data, achieving higher quality stitching with real-time performance at high resolutions. By enabling robust, efficient intraoperative panoramic imaging, SX-Stitch has the potential to enhance surgical planning, decision-making, and patient outcomes in scoliosis procedures.

Abstract

In scoliosis surgery, the limited field of view of the C-arm X-ray machine restricts the surgeons' holistic analysis of spinal structures .This paper presents an end-to-end efficient and robust intraoperative X-ray image stitching method for scoliosis surgery,named SX-Stitch. The method is divided into two stages:segmentation and stitching. In the segmentation stage, We propose a medical image segmentation model named Vision Mamba of Spine-UNet (VMS-UNet), which utilizes the state space Mamba to capture long-distance contextual information while maintaining linear computational complexity, and incorporates the SimAM attention mechanism, significantly improving the segmentation performance.In the stitching stage, we simplify the alignment process between images to the minimization of a registration energy function. The total energy function is then optimized to order unordered images, and a hybrid energy function is introduced to optimize the best seam, effectively eliminating parallax artifacts. On the clinical dataset, Sx-Stitch demonstrates superiority over SOTA schemes both qualitatively and quantitatively.

SX-Stitch: An Efficient VMS-UNet Based Framework for Intraoperative Scoliosis X-Ray Image Stitching

TL;DR

SX-Stitch tackles the challenge of achieving panoramic intraoperative scoliosis X-ray views despite limited C-arm FOV by delivering an end-to-end two-stage framework. It introduces VMS-UNet, a Vision Mamba-based Spine-UNet for accurate pedicle screw segmentation, followed by an energy-driven stitching pipeline that first aligns images using screw centroids and then fuses them along a hybrid seam to suppress parallax. The approach shows consistent improvements over state-of-the-art methods on clinical data, achieving higher quality stitching with real-time performance at high resolutions. By enabling robust, efficient intraoperative panoramic imaging, SX-Stitch has the potential to enhance surgical planning, decision-making, and patient outcomes in scoliosis procedures.

Abstract

In scoliosis surgery, the limited field of view of the C-arm X-ray machine restricts the surgeons' holistic analysis of spinal structures .This paper presents an end-to-end efficient and robust intraoperative X-ray image stitching method for scoliosis surgery,named SX-Stitch. The method is divided into two stages:segmentation and stitching. In the segmentation stage, We propose a medical image segmentation model named Vision Mamba of Spine-UNet (VMS-UNet), which utilizes the state space Mamba to capture long-distance contextual information while maintaining linear computational complexity, and incorporates the SimAM attention mechanism, significantly improving the segmentation performance.In the stitching stage, we simplify the alignment process between images to the minimization of a registration energy function. The total energy function is then optimized to order unordered images, and a hybrid energy function is introduced to optimize the best seam, effectively eliminating parallax artifacts. On the clinical dataset, Sx-Stitch demonstrates superiority over SOTA schemes both qualitatively and quantitatively.
Paper Structure (12 sections, 7 equations, 4 figures, 2 tables)

This paper contains 12 sections, 7 equations, 4 figures, 2 tables.

Table of Contents

  1. Introduction
  2. Methodology
  3. VMS-UNet
  4. Pedicle screw registration
  5. From disorder to order
  6. Seam Estimation
  7. Experiment and result
  8. Dataset and Implement Details
  9. Quantitative Comparison
  10. Qualitative Comparison
  11. Ablation Study
  12. Discussion and conclusion

Figures (4)

  • Figure 1: SIFT matching on X-ray image.Due to weak features and repetitive textures of X-ray images, manually designed features perform poorly in robustness.
  • Figure 2: Pipline of SX-Stitch.
  • Figure 3: Qualitative Comparison on Paired Image Stitching
  • Figure 4: Qualitative Comparison on Multi-Image Stitching.