Learning Model Tissue Differentiation in Laparoscopic Surgery
Find Innovative SolutionsGenerate Solutions
Solution Overview
Problem
In laparoscopic surgery, it is challenging to recognize and distinguish nerves and ureters from blood vessels within the operative field image, which can lead to complications due to their overlapping appearance and rarity of complete exposure.
Innovation Solution
A computer-based system that utilizes a learning model trained on operative field images to recognize and differentiate nerves and ureters from blood vessels, generating a distinguishable display of these tissues to support surgical procedures.
Engineering Contradictions & Design Principles
Engineering Contradiction Analysis
1Measurement precision
If conventional image display methods are used in laparoscopic surgery, then the surgical procedure can proceed, but the operator cannot recognize and distinguish target tissues (nerves, ureters) from blood vessel tissue portions
Solution Approach 1:
The patent applies color changes by assigning distinct color tones to different tissue types through the learning model. Target tissues (nerves, ureters) are displayed with different colors than blood vessel tissue portions, enabling visual differentiation. This color coding allows operators to quickly identify and distinguish between critical structures without additional imaging equipment.
Solution Approach 2:
The learning model acts as an intermediary between the raw operative field image and the operator's perception. It processes the image data, identifies tissue types based on trained patterns, and presents enhanced visual information that highlights target tissues while distinguishing them from blood vessels, thereby mediating the information gap.
2Reliability
If the operator relies on visual inspection of operative field images, then the surgical procedure can continue, but the ability to distinguish target tissues from blood vessels is insufficient
Solution Approach 1:
The patent replaces the mechanical/physical inspection method (operator visual examination) with an intelligent system based on machine learning. The learning model automatically analyzes image data, identifies tissue characteristics, and provides enhanced visual feedback, substituting human visual limitation with computational analysis capabilities.
Solution Approach 2:
The system provides real-time feedback by displaying enhanced images with differentiated tissue visualization. The learning model continuously processes operative field images and returns enhanced versions that highlight target tissues, creating a feedback loop that improves operator awareness and surgical decision-making.
3Ease of operation
If no tissue differentiation is provided in the operative field image, then the imaging system remains simple, but the operator cannot identify nerves and ureters that require attention
Solution Approach 1:
The patent uses color changes to encode tissue type information directly in the displayed image. Different color tones represent different tissue categories, making critical structures (nerves, ureters) visually distinct from blood vessels. This color-based encoding preserves all tissue information while making it easily accessible to the operator.
Data Source
AI summary
A computer program causing a computer to execute processing includes acquiring an operative field image obtained by imaging an operative field of scopic surgery, and recognizing a target tissue portion included in the acquired operative field image so as to be distinguished from a blood vessel tissue portion appearing on a surface of the target tissue portion by using a learning model trained to output information regarding a target tissue when the operative field image is input.