Microscope Image Focus Measurement with Gradient-Aware Neural Analysis

Resolve Bottlenecks,
Find Innovative Solutions
Generate Solutions

Solution Overview

Problem

Existing methods for determining the focusing quality of microscope images of biological cell substrates are prone to errors due to the presence of objects like particles, which can lead to incorrect focusing planes, resulting in blurred images and unreliable pattern detection.

Innovation Solution

A method utilizing a neural network that processes both image information and gradient information from a microscope image to determine a focusing measure, specifically by identifying and analyzing selected partial images from the gradient and microscope images, reducing complexity and enhancing reliability.

Engineering Contradictions & Design Principles

VSEngineering Contradiction Analysis

1Reliability

If conventional focusing methods are used to determine the focusing plane, then the focusing process is simple and quick, but the presence of particles or bubbles can lead to incorrect focusing planes and blurred images

Engineering Contradiction:
Improvereliability of focusing quality determinationVSAvoidcomplexity of focusing determination method
Core Design Contradiction:
ReliabilityVSDevice complexity

Solution Approach 1:

The patent divides the microscope image into multiple partial images and processes them separately through the neural network. This segmentation allows the system to evaluate different regions independently, reducing the impact of particles or bubbles in specific areas while maintaining overall focusing quality assessment.

Inventive Principle:
Principle #1Segmentation

Solution Approach 2:

The patent introduces a gradient image as an intermediary representation between the original microscope image and the focusing quality assessment. The gradient image highlights edges and transitions, providing the neural network with enhanced features for detecting focusing quality while being less susceptible to interference from particles or bubbles.

Inventive Principle:
Principle #24Intermediary (Mediator)

2Measurement precision

If all image information is processed to determine focusing quality, then the assessment is comprehensive, but the computational complexity and processing time increase significantly

Engineering Contradiction:
Improveprecision of focusing quality measurementVSAvoidprocessing time for focusing determination
Core Design Contradiction:
Measurement precisionVSLoss of time

Solution Approach 1:

The patent processes only selected partial images rather than the entire microscope image through the neural network. This partial action approach maintains sufficient precision for focusing quality assessment while significantly reducing computational complexity and processing time compared to analyzing the complete image.

Inventive Principle:
Principle #16Partial or excessive action

Solution Approach 2:

By segmenting the image into partial regions and selectively processing them, the system achieves a balance between comprehensive assessment and computational efficiency. The segmentation enables parallel processing and reduces the data volume requiring intensive neural network computation.

Inventive Principle:
Principle #1Segmentation

3Productivity

If gradient image information is used alone to determine focusing quality, then the processing is fast and simple, but the presence of particles can lead to false positive focusing quality assessments

Engineering Contradiction:
Improvespeed of focusing quality determinationVSAvoidaccuracy of focusing quality assessment
Core Design Contradiction:
ProductivityVSReliability

Solution Approach 1:

The patent merges gradient image information with original image information by feeding both into the neural network simultaneously. This combination allows the system to leverage the speed advantages of gradient-based processing while using the original image context to verify and correct potential false assessments caused by particles or bubbles.

Inventive Principle:
Principle #5Merging (Combining)

Solution Approach 2:

The neural network receives both gradient and original image information as feedback inputs, allowing it to cross-validate findings and adjust its focusing quality assessment. This feedback mechanism enables the system to maintain high processing speed while improving reliability by detecting when gradient information alone might be misleading.

Inventive Principle:
Principle #23Feedback

Data Source

PatentEP4625019A1Method for determining a focusing mass of a microscope image
Publication Date: 2025.10.01 EUROIMMUN MEDIZINISCHE LABORDIAGNOSTIKA
  • EP4625019A1 patent drawingFigure 1~2
  • EP4625019A1 patent drawingFigure 3
  • EP4625019A1 patent drawingFigure 4~5

AI summary

A method is proposed for determining a focusing measure of a microscope image, wherein the microscope image represents an image of a biological cell substrate, the method comprising: providing the microscope image, determining a gradient image based on the microscope image, processing image information of the gradient image and image information of the microscope image by means of a neural network to determine the focusing measure, wherein the focusing measure indicates a quality of a focus in the microscope image with respect to a cell substrate plane of the cell substrate.