Anatomical Feature Targeting for Fluoroscopy-Free Kidney Access
Find Innovative SolutionsGenerate Solutions
Solution Overview
Problem
Existing medical procedures for removing kidney stones, such as nephrolithotomy, are costly and imprecise due to the use of fluoroscopy, which exposes patients to radiation and requires lengthy hospital stays, and percutaneous access techniques lack real-time target tracking, leading to inaccurate incisions.
Innovation Solution
A medical system utilizing an endoscope with a camera and electromagnetic position sensor, coupled with robotic arms and control circuitry, enables real-time target detection and tracking of anatomical features, allowing precise percutaneous access and reducing the need for fluoroscopy.
Engineering Contradictions & Design Principles
Engineering Contradiction Analysis
1Measurement precision
If fluoroscopy is used for kidney stone removal, then real-time imaging is provided, but radiation exposure increases and procedure cost increases
Solution Approach 1:
The patent replaces fluoroscopy (radiation-based imaging) with an endoscope-based visual system. The endoscope with camera captures images of anatomical features, and a neural network processes these images to identify target features and adjust positioning, eliminating radiation exposure while maintaining real-time guidance capability
Solution Approach 2:
The patent introduces an intermediary neural network processing system between the endoscope camera and the surgeon. This intermediary automatically identifies anatomical features and adjusts target position based on image analysis, providing real-time guidance without requiring radiation-based fluoroscopy
2Ease of operation
If percutaneous access techniques are used, then incision is made to reach target, but real-time target tracking is lacking leading to inaccurate incisions
Solution Approach 1:
The patent implements a feedback loop where the endoscope continuously captures images of the target anatomical feature, the neural network analyzes these images to determine current position relative to target, and this information feeds back to guide the percutaneous access instrument positioning, enabling real-time target tracking and accurate incision
Solution Approach 2:
The patent performs preliminary identification and tracking of the target anatomical feature using the endoscope and neural network before making the percutaneous incision. This preliminary action ensures accurate target localization and positioning, allowing the surgeon to make precise incisions with confidence
3Productivity
If traditional nephrolithotomy procedures are used, then kidney stones can be removed, but hospital stay duration increases and procedure cost increases
Solution Approach 1:
The patent replaces traditional fluoroscopy-guided nephrolithotomy with an endoscope-guided procedure using neural network-based image analysis. This substitution enables more precise and efficient stone removal with reduced procedural complexity, allowing for shorter hospital stays and reduced costs while maintaining stone removal capability
Data Source
Figure 1
Figure 2
Figure 3
AI summary
Methods of positioning a surgical instrument can involve advancing a first medical instrument to a treatment site of a patient, the first medical instrument comprising a camera, recording a target position associated with a target anatomical feature at the treatment site, generating a first image of the treatment site using the camera of the first medical instrument, identifying the target anatomical feature in the first image using a pretrained neural network, and adjusting the target position based at least in part on a position of the identified target anatomical feature in the first image.