Stereoscopic Endoscope Camera Depth Estimation for Lung Navigation
Find Innovative SolutionsGenerate Solutions
Solution Overview
Problem
Current medical procedures face challenges in accurately navigating medical devices within a patient's lung anatomy due to small discrepancies between actual and estimated device locations, which can lead to undesired consequences.
Innovation Solution
The development of a stereoscopic endoscope camera and sensor tool that includes a sensor pack with cameras, an electromagnetic sensor assembly, an inertial measurement unit, and an illumination source, which captures stereoscopic images, estimates depth information, and generates a point cloud for registering patient anatomical positional information.
Engineering Contradictions & Design Principles
Engineering Contradiction Analysis
1Measurement precision
If conventional imaging methods are used to navigate medical devices in lung anatomy, then the procedure can be performed, but small discrepancies between actual and estimated device locations occur, reducing precision
Solution Approach 1:
The patent replaces conventional mechanical positioning methods with a stereoscopic vision system that uses optical cameras to capture 3D images of lung anatomy. This substitution enables more precise device location estimation by using image processing and depth calculation algorithms rather than traditional mechanical measurement methods, thereby resolving the contradiction between measurement precision and procedure reliability.
Solution Approach 2:
The patent transitions from 2D imaging to 3D stereoscopic imaging by using two cameras positioned at different angles. This dimensional change allows the system to calculate depth information and generate accurate 3D models of lung anatomy, significantly improving device location estimation precision while enhancing the reliability of medical procedures through better spatial understanding.
2Measurement precision
If a camera and sensor tool with multiple sensors is used, then measurement precision improves, but device complexity increases
Solution Approach 1:
The patent merges multiple sensors (cameras, electromagnetic sensors, IMU) into a single integrated sensor pack that can be incorporated into an endoscope. This consolidation approach allows the system to achieve high measurement precision through multi-sensor fusion while managing device complexity by combining functions into a unified modular structure rather than using separate discrete components.
Solution Approach 2:
The sensor pack is designed with multi-functionality, where the same hardware components serve multiple purposes: cameras capture images for 3D reconstruction, electromagnetic sensors provide positioning data, and IMU sensors track motion. This universal design improves measurement precision through diverse data sources while reducing overall device complexity by eliminating redundant separate systems.
Data Source
AI summary
Endoscopic systems and methods use a multi-view camera tool inside the body, including airways of a lung, to capture images, and use a combination of positional informational from EM and/or IMU sensors of the multi-view camera tool to estimate image depth and generate a three-dimensional (3D) point cloud volume of the patient anatomy. The 3D point cloud volume is generated from a known vantage point using stereoscopic images captured by the camera tool. This 3D structure generation may use a stereo image rectification algorithm. A machine learning algorithm may also be applied in place of, or in combination with, an image rectification algorithm to improve computational efficiency.