Toric IOL Alignment Guide Using Automated Axis Detection
Find Innovative SolutionsGenerate Solutions
Solution Overview
Problem
Existing methods for aligning toric intraocular lenses (IOLs) during cataract surgery lack precision, which affects patient outcomes due to asymmetry correction for astigmatism.
Innovation Solution
A system utilizing a computing device to process images from an imaging device, segmenting the eye to identify toric IOL features, and calculating the angle difference between the IOL axis and a reference axis, generating an output image with alignment indicators to guide surgeons.
Engineering Contradictions & Design Principles
Engineering Contradiction Analysis
1Ease of operation
If a digital marker microscope is used to view the patient's eye during surgery with a superimposed reference axis, then the alignment process becomes automated and easier to operate, but the measurement precision of the IOL axis orientation is insufficient
Solution Approach 1:
The patent replaces the mechanical/manual alignment process with an automated image processing system. The computing device automatically detects IOL features (alignment dots, perimeter, haptics) in images from the digital marker microscope, calculates the IOL axis orientation, and determines the angle difference from the reference axis. This substitution of manual measurement with automated computational analysis resolves the contradiction by providing both ease of operation and improved measurement precision through algorithmic feature detection and orientation calculation.
2Device complexity
If manual alignment methods are used for toric IOL positioning, then the device complexity is low, but the manufacturing precision and alignment accuracy deteriorate
Solution Approach 1:
The patent introduces an intermediary computing device that acts as a mediator between the imaging system and the surgeon. This device processes images from the digital marker microscope, automatically detects IOL features, calculates the IOL axis orientation, and provides alignment guidance. The intermediary system bridges the gap between simple imaging and precise alignment, resolving the contradiction by adding controlled complexity to the system while significantly improving alignment precision through automated feature detection and angle calculation.
3Measurement precision
If image processing is used to detect IOL features and calculate orientation, then the measurement precision improves, but the loss of time for processing images increases
Solution Approach 1:
The patent applies preliminary action by pre-defining the feature detection algorithms and orientation calculation methods before surgery begins. The system is pre-programmed to recognize specific IOL features (alignment dots, perimeter, haptics) and calculate orientations using established geometric algorithms. During surgery, this pre-prepared processing framework enables rapid image analysis without requiring complex real-time computations, thus resolving the contradiction by maintaining high measurement precision while minimizing processing time through advance preparation of the analysis pipeline.
Data Source
AI summary
Particular embodiments disclosed herein provide an alignment guide for aligning a toric IOL during surgery. An image with a reference axis is obtained, such as from a digital microscope, and processed, to obtain a segmented image excluding portions of the image outside of a limbus of a patient's eye. The segmented image is processed, such as using an autoencoder, to label alignment marks on the IOL and possibly other features of the IOL. The label is processed, such as using a logistic regression model, to estimate an IOL axis of the IOL intersecting the alignment marks. An output image is generated from the image that has superimposed thereon guides to a surgeon, such as a line representing the IOL axis, a rotation direction indicator, and a number or other representation of a difference between the reference axis and the IOL axis.