Related Experiment Video
Updated: Sep 14, 2025
10:23
Technical Approach for Infrared Tracking for Soft Tissue Navigation with a Holographic Head-Mounted Display and Preclinical Validation
Published on: September 2, 2025
32
Multiview 2D/3D image registration in minimally invasive pelvic surgery navigation
Fujiao Ju1, Ya Wang1, Jingxin Zhao2
1College of Computer Science, Beijing University of Technology, Beijing, 100124, China.
Scientific Reports
|July 18, 2025
Summary
This study introduces a novel multiview 2D/3D image registration method for accurate surgical navigation, even with limited data. The technique achieves high success rates and precision, improving minimally invasive pelvic surgery.
Area of Science:
- Medical Imaging
- Computer Vision
- Surgical Navigation
Background:
- 2D/3D medical image registration is vital for image-guided surgery and research.
- Existing multiview methods require extensive datasets, often unavailable in clinical settings.
- This work addresses multiview registration challenges with insufficient data.
Purpose of the Study:
- To develop and validate an innovative multiview 2D/3D image registration model for scenarios with limited training data.
- To improve the accuracy and reliability of image registration for minimally invasive pelvic surgery.
Main Methods:
- Proposed a model with three components: Points of Interest Tracking Network based on style transfer (POITT), a triangulation layer, and Shape Alignment based on Branch and Bound (SA-BnB).
- POITT tracks points of interest on X-ray images using style transfer.
- Triangulation layer and SA-BnB establish precise spatial mapping and calculate optimal transformation matrices.
Main Results:
- Achieved an average fiducial registration error of 6 mm (success threshold < 10 mm).
- Demonstrated a 96.67% average registration success rate on Digital Reconstructed Radiographs (DRRs).
- Attained an average Structural Similarity Index Measure (SSIM) of 0.77 between X-ray and aligned DRRs.
Conclusions:
- The proposed multiview 2D/3D registration model shows significant advantages over traditional methods, especially with limited data.
- This approach offers a reliable solution for enhancing minimally invasive pelvic surgery navigation.
- The method's effectiveness was validated using clinical data and simulated DRRs.
