AR Laser Capture Microdissection for Automated Cell Selection
Find Innovative SolutionsGenerate Solutions
Solution Overview
Problem
Current laser capture microdissection (LCM) machines require manual identification of cells of interest by operators, which is time-consuming and diverts attention from the specimen, and existing technologies lack efficient automated methods for real-time identification and excision within the microscope view.
Innovation Solution
An augmented reality (AR) subsystem integrated with a microscope, utilizing a machine learning model to automatically identify cells of interest and overlay an AR image, allowing operators to view and confirm selections directly through the eyepiece, triggering laser capture and microdissection with a simple input mechanism.
Engineering Contradictions & Design Principles
Engineering Contradiction Analysis
1Measurement precision
If manual identification of cells of interest is used, then the operator can select cells with high accuracy, but the process is time-consuming and requires diverting attention from the specimen
Solution Approach 1:
A machine learning model acts as an intermediary between the specimen and the operator, automatically identifying and outlining cells of interest in the field of view. This intermediary system processes images captured by the microscope camera and presents pre-identified cell outlines to the operator through the augmented reality display, eliminating the need for manual scanning and selection while maintaining high accuracy through automated image analysis
Solution Approach 2:
The system performs preliminary identification of cells of interest by automatically analyzing microscope images and generating outlines of potential target cells before the operator makes the final selection. This preliminary action of pre-identifying and highlighting cells in the augmented reality view prepares the information in advance, allowing the operator to quickly confirm selections without performing time-consuming manual identification
2Loss of information
If manual cell identification is performed on a workstation monitor, then the operator can review cell selections, but the operator must divert attention away from the specimen
Solution Approach 1:
The system transitions the cell identification and review interface from a separate 2D workstation monitor to an augmented reality display overlaid directly on the microscope's optical path. By projecting virtual outlines of cells of interest into the third dimension of the optical space, the system allows the operator to view both the specimen and the identification results simultaneously through the eyepiece, eliminating the need to shift attention between different viewing planes
Solution Approach 2:
The augmented reality display merges the specimen view with the cell identification interface by overlaying virtual outlines directly onto the magnified specimen image in the eyepiece. This combination allows the operator to see both the actual specimen and the AI-identified cell boundaries in the same field of view, integrating the selection workflow into a single unified viewing experience rather than requiring separate monitoring and control stations
Applied Scientific Principles
This section explains which scientific principles are used to turn an abstract innovation direction into a practical engineering solution.
Function Achieved in This Case
Enables real-time, efficient identification and excision of cells of interest without diverting attention from the specimen, improving the speed and accuracy of the LCM process by automating the cell selection and capture process within the microscope view.
Implementation Method 1
a machine learning model stored on a machine readable medium identifying cells of potential interest in the images
Implementation Method 2
an optics module projecting into the view of the microscope as seen through the eyepiece an outline of cells of potential interest identified by the machine learning model
Implementation Method 3
a laser capture and microdissection subsystem configured for excising the cells of interest from the sample with one or more lasers
Data Source
AI summary
An augmented reality (AR) subsystem including one or more machine learning models, automatically overlays an augmented reality image, e.g., a border or outline, that identifies cells of potential interest, in the field of view of the specimen as seen through the eyepiece of an LCM microscope. The operator does not have to manually identify the cells of interest for subsequent LCM, e.g, on a workstation monitor, as in the prior art. The operator is provided with a switch, operator interface tool or other mechanism to select the identification of the cells, that is, indicate approval of the identification of the cells, while they view the specimen through the eyepiece. Activation of the switch or other mechanism invokes laser excising and capture of the cells of interest via a known and conventional LCM subsystem.