Percutaneous Access Planning Using Predicted Anatomical Distension
Find Innovative SolutionsGenerate Solutions
Solution Overview
Problem
Existing medical procedures face challenges in managing irrigation and aspiration to achieve optimal anatomical distension, leading to potential patient harm or procedure inefficiency due to over- or under-pressurization.
Innovation Solution
A method and system utilizing machine learning to predict anatomical distension based on case-specific features, generating recommendations for percutaneous access by training a model on fluidics simulations, enabling automated planning of medical procedures.
Engineering Contradictions & Design Principles
Engineering Contradiction Analysis
1Illumination intensity
If irrigation fluid is delivered to achieve anatomical distension, then visualization and access to anatomy is improved, but over-pressurization can cause tissue damage or fractures
Solution Approach 1:
The system performs pre-operative fluidics simulations to predict anatomical distension outcomes before the actual procedure. By simulating irrigation fluid delivery and predicting pressure distributions in advance, the system allows physicians to plan the procedure to achieve adequate distension while avoiding over-pressurization and tissue damage.
Solution Approach 2:
The system incorporates machine learning models trained on fluidics simulation data to predict anatomical distension based on patient-specific anatomical features. This predictive feedback allows the physician to adjust irrigation parameters during the procedure to maintain optimal distension without exceeding safe pressure thresholds that could cause tissue damage.
2Productivity
If percutaneous access is performed to remove urinary stones, then stone removal efficacy is improved, but improper fluid management can adversely affect patient health
Solution Approach 1:
The system performs pre-operative planning using machine learning models trained on fluidics simulations to predict the optimal irrigation strategy for stone removal. By simulating and analyzing fluid dynamics before the procedure, the system establishes a safe and effective fluid management plan that ensures both stone removal efficacy and patient safety.
Solution Approach 2:
The predictive model provides real-time guidance on fluid management during the procedure by predicting anatomical distension based on current irrigation parameters and anatomical features. This feedback loop allows the physician to maintain optimal conditions for stone removal while preventing adverse effects from improper fluid management.
Data Source
AI summary
This disclosure provides methods, devices, and systems for planning medical procedures. The present implementations more specifically relate to techniques for using machine learning to predict distension of an anatomy and recommend a plan for percutaneously accessing a target within the anatomy based on the predicted distension. In some aspects, a recommendation system may extract features from input data representing a mapping of an anatomy and infer, from the extracted features, a location on the anatomy for percutaneous entry based on a machine learning model trained on fluidics simulations that predict anatomical distension in response to irrigation. Example suitable input data may include three-dimensional images of the anatomy, two-dimensional images of the anatomy, and/or sensor data received via sensors disposed on an instrument within the anatomy. The recommendation system may further generate a plan for percutaneously accessing a target within the anatomy via the location inferred from the set of features.