Surgical System Region-of-Interest Setting via Image Segmentation
Find Innovative SolutionsGenerate Solutions
Solution Overview
Problem
Non-contact input methods in surgical systems, such as using a line-of-sight, are prone to misrecognition, leading to malfunctions and incorrect focusing on adjacent organs during surgery.
Innovation Solution
A surgical system that includes an image processing unit for segmentation, a region-of-interest candidate acquisition unit, and a control unit to set the region-of-interest based on the relationship between the segmentation region and candidate, ensuring accurate focus and exposure control by distinguishing the intended target from adjacent organs.
Engineering Contradictions & Design Principles
Engineering Contradiction Analysis
1Ease of operation
If non-contact input methods (line-of-sight) are used to control camera focus, then operator sterilization is improved and hands-free operation is achieved, but input recognition accuracy deteriorates leading to misrecognition of target organs
Solution Approach 1:
The patent segments the image into multiple regions of interest (ROI) based on anatomical structures and depth information. By dividing the complex surgical field into distinct segmented regions, the system can accurately identify and distinguish between the target organ and adjacent organs, resolving the misrecognition issue while maintaining hands-free operation through automated region-based focus control
Solution Approach 2:
The patent introduces an intermediary processing layer that includes image segmentation modules and depth information processing. This intermediary system acts as a mediator between the raw image data and the focus control decision, analyzing spatial relationships and anatomical context to accurately determine the operator's intended target without direct contact input
2Extent of automation
If line-of-sight tracking is used to determine focus target, then non-contact operation is achieved, but focus accuracy deteriorates when operator looks at end of operation target organ
Solution Approach 1:
The patent adds depth information as an additional dimension to the traditional 2D line-of-sight tracking. By incorporating depth data from stereo cameras or structured light, the system can distinguish between the front surface and back surface of organs, enabling accurate focus control even when the operator's line-of-sight points to the end of an organ by analyzing three-dimensional spatial relationships
Solution Approach 2:
The patent performs preliminary image segmentation and depth mapping before focus control is executed. By pre-processing the image to identify and label different anatomical regions and their depth information, the system is prepared to accurately determine the intended target organ, preventing misfocus on adjacent organs or the end of organs during automated focus adjustment
Data Source
AI summary
The present technology relates to a surgical system, a control method, and a program that enable a region-of-interest of an operator to be appropriately set. The surgical system according to one aspect of the present technology performs segmentation of an image captured by a camera and sets a segmentation region in which each target is displayed, acquires a region-of-interest candidate that is a region to be a candidate for a region-of-interest of an operator, and sets the region-of-interest on the basis of a relationship between the segmentation region and the region-of-interest candidate. The present technology can be applied to a surgical system using an endoscope.