Immunostaining Mask for Selective FISH Analysis

Resolve Bottlenecks,
Find Innovative Solutions
Generate Solutions

Solution Overview

Problem

Conventional fluorescence in situ hybridization (FISH) analysis in carcinoma tumor samples is hindered by the inclusion of non-epithelial cells, leading to less accurate dot counting measurements due to the lack of effective methods to selectively analyze epithelial cells.

Innovation Solution

A computer-implemented method processes image data by using an immunofluorescent marker to classify cells as epithelial or non-epithelial, filtering FISH analysis results to exclude non-epithelial cells, and employing techniques like wavelet transforms and Voronoi partitions to refine the analysis.

Engineering Contradictions & Design Principles

VSEngineering Contradiction Analysis

1Measurement precision

If conventional FISH analysis measures FISH signal for all cells in a field of view, then the analysis process is simple and quick, but the measurement accuracy deteriorates because non-epithelial cells contribute to the dot counting statistics

Engineering Contradiction:
Improvedot counting measurement accuracyVSAvoidanalysis process complexity
Core Design Contradiction:
Measurement precisionVSDevice complexity

Solution Approach 1:

The analysis process is segmented into distinct steps: first acquiring an immunofluorescence image to identify epithelial cells using cytokeratin markers, then acquiring a FISH image, and finally analyzing only the FISH signals from identified epithelial cells. This segmentation allows accurate cell-type-specific measurement while maintaining automated processing.

Inventive Principle:
Principle #1Segmentation

Solution Approach 2:

An immunofluorescence image acquisition step is introduced as an intermediary between sample preparation and FISH analysis. This intermediary step provides cell type identification information that guides the subsequent FISH signal analysis, enabling accurate filtering of epithelial cell signals from non-epithelial cell signals.

Inventive Principle:
Principle #24Intermediary (Mediator)

2Measurement precision

If manual intervention is used to select epithelial cells for FISH analysis, then the measurement accuracy improves, but the productivity and automation level deteriorate

Engineering Contradiction:
Improvedot counting measurement accuracyVSAvoidanalysis throughput
Core Design Contradiction:
Measurement precisionVSProductivity

Solution Approach 1:

The system performs self-service by automatically acquiring immunofluorescence images, identifying epithelial cells based on cytokeratin marker expression, and filtering FISH signals from only those epithelial cells. This automated self-service eliminates the need for manual cell selection while maintaining measurement accuracy.

Inventive Principle:
Principle #25Self-service

Solution Approach 2:

The system changes the parameter of cell selection from manual visual inspection to automated fluorescence intensity thresholding. By setting intensity thresholds for cytokeratin marker detection, the system automatically identifies epithelial cells based on their fluorescent signal characteristics, enabling high-throughput automated analysis.

Inventive Principle:
Principle #35Parameter changes

3Reliability

If no cell type classification is performed, then the ease of operation is maintained, but the reliability of FISH analysis results deteriorates due to inclusion of non-epithelial cells

Engineering Contradiction:
ImproveFISH analysis result reliabilityVSAvoidoperational simplicity
Core Design Contradiction:
ReliabilityVSEase of operation

Solution Approach 1:

Cell type classification is performed as a preliminary action before FISH signal analysis. The system first acquires and processes immunofluorescence images to classify cells as epithelial or non-epithelial based on cytokeratin marker expression, then uses this classification to guide the subsequent FISH analysis. This preliminary classification ensures reliable results while maintaining operational simplicity through automation.

Inventive Principle:
Principle #10Preliminary action

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

This approach enables accurate, automated FISH analysis by selectively focusing on epithelial cells, improving the precision of FISH dot counting statistics and enhancing the reliability of the results.

Implementation Method 1

receiving, by the processor, a first image of the tissue sample containing signals from an immunofluorescent (IF) morphological marker, wherein the tissue sample is stained with the IF morphological marker

Methodology Applied
Scientific EffectImmunofluorescence: Fluorescence

Implementation Method 2

receiving, by the processor, a second image of the same tissue sample containing signals from a fluorescent probe, wherein the tissue sample is hybridized in situ with the fluorescent probe

Methodology Applied
Scientific EffectIn situ hybridization: Absorption (physical)

Implementation Method 3

the act of segmenting the nuclei may include applying, by the processor, a wavelet transform to the second image

Methodology Applied
Scientific EffectWavelet transform:

Data Source

PatentEP2929505B1Systems and methods for using an immunostaining mask to selectively refine ISH analysis results
Publication Date: 2019.10.16 GENERAL ELECTRIC CO
  • EP2929505B1 patent drawingFigure 1
  • EP2929505B1 patent drawingFigure 2
  • EP2929505B1 patent drawingFigure 3

AI summary

A computer-implemented method of processing image data representing biological units in a tissue sample includes receiving a first image of the tissue sample containing signals from an immunofluorescent (IF) morphological marker, wherein the tissue sample is stained with the IF morphological marker, and receiving a second image of the same tissue sample containing signals from a fluorescent probe, wherein the tissue sample is hybridized in situ with the fluorescent probe. The method further includes classifying each biological unit in the tissue sample into one of at least two classes based on a mean intensity of the signals from the IF morphological marker in the first image, performing a fluorescence in situ hybridization (FISH) analysis of the tissue sample in the second image to obtain results therefrom, and filtering the results of the FISH analysis to produce a subset of the results pertaining to biological units classified in one class.