Related Experiment Video
Updated: Apr 2, 2026
07:01
3D Imaging of Soft-Tissue Samples using an X-ray Specific Staining Method and Nanoscopic Computed Tomography
Published on: October 24, 2019
10.4K
Dense soft tissue 3D reconstruction refined with super-pixel segmentation for robotic abdominal surgery
Veronica Penza1,2, Jesús Ortiz3, Leonardo S Mattos4
1Department of Advanced Robotics, Istituto Italiano di Tecnologia, via Morego, 30, 16163, Genoa, Italy. veronica.penza@iit.it.
International Journal of Computer Assisted Radiology and Surgery
|September 28, 2015
Summary
New 3D reconstruction methods enhance surgical visualization by improving soft tissue modeling during minimally invasive procedures. These techniques offer greater accuracy and detail for intra-operative guidance systems.
Area of Science:
- Medical Imaging
- Computer Vision
- Surgical Technology
Background:
- Single-incision laparoscopic surgery (SILS) offers benefits but limits visualization.
- Enhancing intra-operative surgical visualization is crucial for SILS.
- Exploiting 3D information of the surgical site can improve visualization.
Purpose of the Study:
- To enhance intra-operative surgical visualization using 3D information.
- To develop new methods for dense 3D reconstruction of soft tissues.
- To improve deformation identification and registration processes for surgical guidance.
Main Methods:
- Proposed two methods for soft tissue 3D reconstruction: block matching and nonparametric modified census transform.
- Utilized Simple Linear Iterative Clustering (SLIC) for disparity refinement and hole filling.
- Validated methods using stereoscopic imaging and 3D reconstruction techniques.
Main Results:
- Achieved high accuracy (2.95 mm and 1.66 mm) in 3D reconstructions.
- Disparity refinement increased reconstructed points by up to 43%.
- Accuracy was not significantly affected by the refinement procedure.
Conclusions:
- Proposed methods compare favorably with state-of-the-art techniques.
- Computational time is a limitation for real-time application.
- GPU implementation can significantly improve performance.
