Surgical Planning System for Glenoid Implant Positioning
Find Innovative SolutionsGenerate Solutions
Solution Overview
Problem
Computerized surgical planning systems for shoulder replacement surgeries face challenges in generating plans that align with individual surgeon preferences, particularly for less experienced surgeons who lack sufficient training data, leading to impracticality in training separate machine learning models and increased resource consumption.
Innovation Solution
A computing system that obtains surgeon preference parameters and determines suggested surgical options based on both anatomic and surgeon-specific preferences, reducing the need for extensive training datasets and minimizing resource utilization by filtering implant types and determining optimal placement parameters.
Engineering Contradictions & Design Principles
Engineering Contradiction Analysis
1Adaptability or versatility
If separate machine learning models are trained for each individual surgeon to generate predictions based on surgeon preferences, then the surgical planning system can accommodate individual surgeon preferences, but the storage requirements and computational resources increase significantly
Solution Approach 1:
The patent combines multiple surgeon preference parameters into a single machine learning model instead of training separate models for each surgeon. The model accepts surgeon preference parameters as inputs and generates surgical predictions that reflect individual surgeon preferences, thereby merging the functionality of multiple models into one resource-efficient system.
Solution Approach 2:
The machine learning model is designed to be universal by accommodating multiple surgeon preferences through a single model instance. It processes different surgeon preference parameters (such as glenoid implant positioning preferences) and generates customized predictions for each surgeon without requiring separate model training, thus achieving multi-functionality.
2Adaptability or versatility
If machine learning models are trained for surgeons who do not frequently perform shoulder replacement surgeries, then those surgeons can receive personalized surgical suggestions, but sufficient training data is not available for such surgeons
Solution Approach 1:
The patent uses surgeon preference parameters as intermediaries that bridge the gap between limited training data and personalized surgical suggestions. Instead of relying on extensive surgeon-specific training data, the system incorporates explicit preference parameters (such as preferred implant positioning ranges) that guide the machine learning model to generate suggestions consistent with each surgeon's preferences, even when training data is scarce.
Solution Approach 2:
The system changes from relying on data quantity to utilizing parameter quality by incorporating explicit surgeon preference parameters. These parameters (such as preferred glenoid implant version and inclination ranges) serve as direct guidance to the machine learning model, allowing it to generate personalized suggestions without requiring large volumes of surgeon-specific training data.
Data Source
AI summary
A method comprises obtaining, by a computing system, one or more surgeon preference parameters that specify values of one or more surgical parameters, wherein the surgical parameters include one or more positioning parameters for a glenoid implant to be attached to a glenoid fossa of a patient during a surgery; determining, by the computing system, based on one or more anatomic parameters of the patient and the surgeon preference parameters, one or more suggested surgical options, each of the surgical options corresponding to a. different combination of the positioning parameters for the glenoid implant and types of glenoid implant; and outputting, by the computing system, for display, the one or more suggested surgical options.