Related Experiment Video
Updated: Oct 10, 2025
05:56
Objectification of Tongue Diagnosis in Traditional Medicine, Data Analysis, and Study Application
Published on: April 14, 2023
2.7K
A Smoke Removal Method Based on Combined Data and Modified U-Net for Endoscopic Images
Summary
This study introduces a novel smoke removal technique for minimally invasive surgery using a modified U-net model trained on combined real and synthetic endoscopic images. This method effectively clears surgical smoke, enhancing surgeon visibility and improving operational flow.
Area of Science:
- Medical Imaging
- Surgical Technology
- Artificial Intelligence in Medicine
Background:
- Surgical smoke generated during minimally invasive procedures obstructs the surgeon's view.
- Effective smoke management is crucial for maintaining clear visualization during endoscopic surgery.
Purpose of the Study:
- To develop and evaluate a real-time smoke removal method for endoscopic images.
- To improve surgical field clarity in minimally invasive procedures.
Main Methods:
- A modified U-net architecture was employed for smoke removal.
- Combined real and synthetic datasets of endoscopic images with smoke were utilized for model training.
- The performance was evaluated using both qualitative and quantitative analyses.
Main Results:
- Training with combined real and synthetic data yielded the best smoke-free image quality.
- The proposed method demonstrated superior smoke removal effectiveness compared to using individual datasets.
- Both qualitative and quantitative evaluations confirmed the method's efficacy.
Conclusions:
- The developed smoke removal technique effectively clears surgical smoke in endoscopic images.
- Combining real and synthetic data enhances the performance of smoke removal models.
- This real-time solution can significantly aid surgeons by providing clear images during operations.
