Eyeball-Tracked Image Processing for Surgical Microscope Guidance
Find Innovative SolutionsGenerate Solutions
Solution Overview
Problem
The superimposition of preoperative marks on the operative field image during ophthalmic surgery leads to occlusion, making it difficult for operators to perform surgeries accurately according to the preoperative plan.
Innovation Solution
An image processing apparatus and method that generates display images with boundaries indicating specific positions and sizes based on a preoperative plan, using different display modes to avoid occlusion and enhance visibility of the operative field.
Engineering Contradictions & Design Principles
Engineering Contradiction Analysis
1Loss of information
If marks indicating preoperative plan are superimposed on operative field image, then information regarding appropriate incision position and implant posture is presented, but occlusion occurs making part of operative field image invisible
Solution Approach 1:
The patent transitions from two-dimensional mark superimposition to three-dimensional virtual model reconstruction. By building a 3D virtual eye model that matches the preoperative plan and superimposing it on the real eye image, the system provides spatial information about incision positions and implant postures without occluding the operative field, as the 3D model can be viewed from multiple angles and depths.
Solution Approach 2:
The patent creates a virtual copy of the eye structure based on preoperative images and plans. This virtual eye model replicates the anatomical features and preoperative markings without requiring direct superimposition of 2D marks on the live operative field, thereby preserving visibility while conveying all necessary surgical guidance information.
2Ease of operation
If marks are superimposed to guide surgery, then preoperative plan information is visible, but operator cannot see operative field image clearly for accurate operation
Solution Approach 1:
By elevating surgical guidance from 2D marks to 3D virtual modeling, the system provides comprehensive spatial guidance for incision positions and implant postures without blocking the operator's view of the actual operative field, maintaining both guidance quality and visual clarity.
Solution Approach 2:
The patent introduces a virtual eye model as an intermediary between the preoperative plan and the operative field. This virtual model serves as a mediator that conveys surgical guidance information without directly obstructing the view of the real eye, allowing operators to reference the virtual model while maintaining clear visibility of the actual surgical field.
Data Source
Figure 1
Figure 2
Figure 3
AI summary
An image processing apparatus (13) according to an aspect of the present disclosure includes: an image input unit (13b) that receives an operative field image for an eye of a patient; an eyeball tracking unit (13e) that tracks an eyeball in the operative field image; and a display image generation unit (13f) that sets a plurality of regions having different display modes for the operative field image and generates a display image in which a boundary of the plurality of regions indicate at least one of a specific position, a specific direction, and a specific size for the eye, in which the display image generation unit (13f) changes a display mode of any or all of the plurality of regions on the basis of a tracking result of the eyeball, and changes at least one of a position, a direction, and a size of the boundary.