Cataract Surgery Video Analysis for Dynamic IOL Power Adjustment
Find Innovative SolutionsGenerate Solutions
Solution Overview
Problem
Existing methods for determining intraocular lens (IOL) parameters during cataract surgery are prone to complications due to unforeseen changes in the eye's anatomy, leading to refractive surprises for patients post-operation.
Innovation Solution
A computer-implemented method using machine learning, trained with video sequences of cataract operations, predicts actual refractive power by analyzing video data and additional ophthalmological measurements to dynamically adjust IOL parameters during surgery.
Engineering Contradictions & Design Principles
Engineering Contradiction Analysis
1Reliability
If plan parameters are determined during operation preparation, then the surgical plan is established, but refractive surprises may occur due to unforeseen changes during surgery
Solution Approach 1:
The system transitions from static preoperative planning to dynamic intraoperative adjustment. The machine learning model continuously processes video sequences and surgical parameters in real-time, allowing the IOL power calculation to adapt dynamically to unforeseen changes in capsulorhexis size, corneal refraction, and other intraoperative variations, thereby eliminating refractive surprises while maintaining surgical reliability
Solution Approach 2:
The system implements real-time feedback by analyzing video sequences of the surgical process and comparing actual intraoperative conditions against the original plan. The machine learning model processes feedback signals from surgical parameters (phaco-pressure, phaco-time, capsulorhexis size) and adjusts IOL power calculations accordingly, creating a closed-loop system that adapts to changing conditions while maintaining predictable refractive outcomes
2Reliability
If additional data is collected during operation, then refractive surprises are minimized, but device complexity increases
Solution Approach 1:
The system uses a single machine learning model that serves multiple functions: analyzing video sequences, processing surgical parameters, calculating IOL power, and predicting refractive outcomes. This multi-functional approach consolidates what would otherwise require separate systems into one integrated platform, improving predictive accuracy without proportionally increasing device complexity
Solution Approach 2:
The system transforms complex video data and surgical parameters into standardized numerical inputs for the machine learning model. By converting visual and physical measurements into quantifiable parameters (capsulorhexis size in mm, phaco-pressure in mmHg, phaco-time in seconds), the system simplifies data processing while maintaining the richness of the original data, thereby improving prediction accuracy without excessive complexity
Data Source
AI summary
A computer-implemented method for recognizing deviations from plan parameters during an ophthalmological operation is described, the method including: providing video sequences of cataract operations, the video sequences having been recorded by means of an image recording apparatus, training a machine learning system using the video sequences provided and also, in each case, a planned refractive power of an intraocular lens to be inserted during a cataract operation and a target refraction value following the cataract operation as training input data and associated prediction results in the form of an actual refraction value following the cataract operation to form a machine learning model for predicting the actual refraction value following the cataract operation, and persistently storing parameter values of the trained machine learning system.