Related Experiment Video
Updated: Jun 15, 2025
05:12
Robotized Testing of Camera Positions to Determine Ideal Configuration for Stereo 3D Visualization of Open-Heart Surgery
Published on: August 12, 2021
2.0K
Taking measurement in every direction: Implicit scene representation for accurately estimating target dimensions
Yuchen Zhou1, Rui Li1, Yu Dai1
1The College of Artificial Intelligence, Nankai University, Tianjin 300350, China; The Institute of Robotics and Automatic Information System, Tianjin Key Laboratory of Intelligent Robotics, Tianjin 300350, China.
Computer Methods and Programs in Biomedicine
|August 23, 2024
Summary
This study introduces a new image rendering method for accurate endoscopic size measurements of irregular targets in confined spaces. The approach achieves a mean error of 0.12 mm, enhancing diagnostic capabilities.
Area of Science:
- Medical Imaging
- Computer Vision
- Surgical Technology
Background:
- Accurate target size measurement is crucial for endoscopic medical diagnosis.
- Traditional vision-based methods struggle with limited space, poor image quality, and irregular shapes in endoscopy.
Purpose of the Study:
- To develop a novel image rendering approach for measuring irregular target sizes using monocular endoscopy.
- To overcome the limitations of existing methods in confined endoscopic environments.
Main Methods:
- Synthesized virtual endoscopic poses using known camera parameters and an implicit neural representation module.
- Rendered images considering brightness and target boundaries for virtual poses.
- Employed Swin-Unet and rotating calipers to determine maximum pixel length in image pairs.
- Applied similarity triangle principles for final size measurement.
Main Results:
- Evaluated the method using renal stone fragments in kidney models and isolated porcine kidneys.
- Achieved a mean measurement error of 0.12 mm.
Conclusions:
- The proposed method enables automatic object size measurement within narrow body cavities from any visible direction.
- Significantly improves measurement effectiveness and accuracy in limited endoscopic spaces.
