Corneal Laser Parameter Optimization Using Post-Operative Feedback
Find Innovative SolutionsGenerate Solutions
Solution Overview
Problem
Current algorithms for determining laser parameters in corneal refractive surgery yield inconsistent results due to variations in ocular measurement parameters, and there is a lack of understanding among ophthalmologists regarding which algorithm to use in specific scenarios.
Innovation Solution
A method involving deep learning machines to estimate errors in existing algorithms by using verified post-operative results, adjusting targets, and redetermining laser parameter sets based on ocular measurement parameters, including the use of autorefractors and wavefront analyzers to correlate and train the system.
Engineering Contradictions & Design Principles
Engineering Contradiction Analysis
1Measurement precision
If existing algorithms are used to determine laser parameters, then the basic functionality is provided, but the accuracy and consistency of results vary significantly across different input parameters
Solution Approach 1:
The system collects post-operative refraction measurements and uses them to train a deep learning machine that predicts algorithm errors. This feedback loop continuously improves the accuracy of laser parameter determination by learning from actual surgical outcomes and adjusting predictions accordingly.
Solution Approach 2:
The system performs preliminary error estimation using the trained deep learning machine before final laser parameter determination. By predicting the error of existing algorithms in advance, the system can adjust the targets and compensate for expected inaccuracies before the actual surgery planning is finalized.
2Measurement precision
If multiple algorithms are compared to select the best one, then better results may be achieved in specific scenarios, but the complexity of the decision-making process increases
Solution Approach 1:
The deep learning machine acts as an intermediary that automatically evaluates and compares multiple existing algorithms. Instead of requiring ophthalmologists to manually understand and compare algorithm performances, the AI system performs this complex evaluation and provides error predictions that guide algorithm selection and parameter adjustment.
Solution Approach 2:
The system automatically trains the deep learning machine on its own post-operative data, enabling it to self-improve its error prediction capabilities over time. This self-learning mechanism eliminates the need for external expertise to continuously update and refine the algorithm selection process.
3Measurement precision
If algorithm adjustments are made to improve results for specific input parameters, then accuracy for those parameters improves, but the overall system complexity increases
Solution Approach 1:
Instead of creating multiple complex adjusted algorithms for different parameter ranges, the system uses the deep learning machine to predict errors based on input parameters and dynamically adjusts the targets accordingly. This approach handles parameter-specific accuracy requirements through a unified error prediction and adjustment framework rather than multiple specialized algorithms.
Data Source
AI summary
The disclosure provides methods and apparatuses for determining a laser parameter set for corneal refractive surgery. The apparatus may include an autorefractor configured to obtain at least two ocular measurement parameters for an eye and to obtain a post-operative refraction of the eye. The apparatus may include a user interface configured to obtain a target refraction for the eye. The apparatus may include a memory and a processor communicatively coupled to the user interface, the autorefractor, and the memory. The processor may be configured to determine the laser parameter set based on an algorithm using the at least two ocular measurement parameters. The processor may be configured to correlate the at least two ocular measurement parameters, the laser parameter set, and the post-operative refraction as a training set.