Related Experiment Video
Updated: Feb 28, 2026
07:30
Electromagnetic Navigation Transthoracic Nodule Localization for Minimally Invasive Thoracic Surgery
Published on: May 4, 2022
3.8K
Continuous lung region segmentation from endoscopic images for intra-operative navigation
Shuqiong Wu1, Megumi Nakao1, Tetsuya Matsuda1
1Graduate School of Informatics, Kyoto University, Yoshidahonmachi, Sakyo Ward, Kyoto, 606-8501, Japan.
Computers in Biology and Medicine
|June 11, 2017
Summary
This study introduces a novel method for precise lung segmentation using endoscopic images during surgery. The approach improves intraoperative navigation accuracy for lung resection by overcoming challenges with lung deformation and background similarity.
Area of Science:
- Medical Imaging
- Surgical Navigation
- Computer-Aided Surgery
Background:
- Preoperative Computed Tomography (CT) lacks precision for deformable organs like lungs during surgery.
- Intraoperative endoscopic images offer real-time descriptions but face segmentation challenges due to lung deformability and background similarity.
Purpose of the Study:
- To develop an accurate lung region segmentation method using intraoperative endoscopic images.
- To enhance intraoperative navigation for lung resection surgeries.
Main Methods:
- A novel approach combining GrabCut and optical flow for continuous lung segmentation.
- A user-interaction technique for rapid boundary definition, enabling precise segmentation.
Main Results:
- The proposed method achieved an average F-measure exceeding 97%.
- Accurate identification of lung position, size, and boundary was demonstrated.
Conclusions:
- The novel segmentation approach provides accurate real-time lung information.
- This method significantly improves intraoperative navigation for lung resection procedures.
