Whole-Slide Biomarker Analysis With Precomputed Pathology Visualization

Resolve Bottlenecks,
Find Innovative Solutions
Generate Solutions

Solution Overview

Problem

Current digital pathology systems struggle with computationally intensive image analysis of large high-resolution digital images, requiring significant storage and limiting real-time diagnostic capabilities, and often force users to mentally approximate relevant areas of interest, leading to inefficiencies in quantitative analysis and visualization of entire tissue slides.

Innovation Solution

A digital pathology system with a workflow module that enables automated analysis and intuitive visualization of entire tissue slides, allowing users to manually or automatically select relevant areas, perform image analysis, and generate overlays for precise quantification of biomarker expressions, while excluding artefacts and unnecessary tissue content.

Engineering Contradictions & Design Principles

VSEngineering Contradiction Analysis

1Productivity

If conventional digital pathology systems analyze small fields of view to manage computational load, then processing time and memory usage are reduced, but the ability to perform quantitative analysis of entire tissue slides is compromised

Engineering Contradiction:
Improveanalysis speedVSAvoidfield of view coverage
Core Design Contradiction:
ProductivityVSArea of stationary object

Solution Approach 1:

The system segments the entire tissue slide into multiple smaller fields of view that can be processed individually by the digital pathology system. Each FOV is analyzed separately for biomarker expression, and the results are then aggregated to provide comprehensive quantitative analysis of the whole slide. This segmentation allows the system to manage computational load while ultimately covering the entire tissue area.

Inventive Principle:
Principle #1Segmentation

2Area of stationary object

If the system processes entire whole-slide images, then complete tissue coverage is achieved, but computational intensity and memory requirements increase significantly

Engineering Contradiction:
Improvetissue coverage areaVSAvoidcomputational processing power
Core Design Contradiction:
Area of stationary objectVSPower

Solution Approach 1:

The whole-slide image is divided into multiple smaller fields of view that can be processed sequentially or in parallel with reduced memory requirements. Each FOV is analyzed independently for biomarker expression levels, and the computational results are aggregated to provide comprehensive quantitative analysis of the entire tissue slide.

Inventive Principle:
Principle #1Segmentation

Solution Approach 2:

The system initially analyzes a representative subset of fields of view to estimate biomarker expression levels and provide preliminary diagnostic information. This partial analysis allows rapid assessment without processing the entire slide, and full quantitative analysis can be performed subsequently if needed.

Inventive Principle:
Principle #16Partial or excessive action

3Measurement precision

If pathologists manually examine digital images to identify treatment options, then diagnostic accuracy is maintained, but significant time and mental effort are required

Engineering Contradiction:
Improvediagnostic accuracyVSAvoiddiagnostic time
Core Design Contradiction:
Measurement precisionVSLoss of time

Solution Approach 1:

The digital pathology system automatically performs quantitative analysis of biomarker expressions in tissue slides without requiring manual examination by pathologists. The system independently processes whole-slide images, identifies relevant morphological features, quantifies biomarker expressions, and generates diagnostic reports, thereby eliminating the time-consuming manual review process while maintaining diagnostic accuracy.

Inventive Principle:
Principle #25Self-service

Solution Approach 2:

The manual visual examination process is replaced with automated digital image analysis algorithms that process whole-slide images computationally. The system uses computer vision and machine learning techniques to identify tissue morphology, detect biomarker expressions, and quantify results, substituting the pathologist's manual visual inspection with automated computational analysis.

Inventive Principle:
Principle #28Mechanics substitution (Replace mechanical system)

4Quantity of substance

If conventional systems limit field of view size to manage memory constraints, then memory usage is controlled, but the representative sampling of entire tissue slides becomes difficult

Engineering Contradiction:
Improvememory usageVSAvoidtissue representation accuracy
Core Design Contradiction:
Quantity of substanceVSLoss of information

Solution Approach 1:

The system segments the entire tissue slide into multiple smaller fields of view that can be processed and stored with manageable memory requirements. By analyzing multiple FOVs across different regions of the slide, the system captures comprehensive tissue representation without requiring excessive memory resources.

Inventive Principle:
Principle #1Segmentation

Solution Approach 2:

The system merges the analysis results from multiple smaller fields of view to provide comprehensive quantitative analysis of the entire tissue slide. By combining data from multiple FOVs, the system achieves complete tissue coverage and accurate biomarker expression quantification without needing to load the entire high-resolution slide into memory simultaneously.

Inventive Principle:
Principle #5Merging (Combining)

Data Source

PatentEP3523779B1Digital pathology system and associated workflow for providing visualized whole-slide image analysis
Publication Date: 2026.04.29 VENTANA MEDICAL SYSTEMS INC
  • EP3523779B1 patent drawingFigure 1
  • EP3523779B1 patent drawingFigure 2
  • EP3523779B1 patent drawingFigure 3

AI summary

A digital pathology system and associated method and computer program product provide a quantitative analysis of entire tissue slides as well as intuitive, effective, fast, and precise quantification of biomarker expressions across relevant areas of the entire tissue slides. The digital pathology system enables a novel workflow that allows the user to efficiently outline clinically relevant morphology in its entirety, including solid tumor areas. Quantitative analysis results are then efficiently and intuitively provided to the user for all tissue content (i.e., millions of cells) within seconds. This efficiency is made possible by a pre-computation step that computes and stores image analysis results for later retrieval. Visualizing vast amount of data effectively is another component of the system that provides information and confidence to the user about the biomarker expression levels.