Whole Slide Image Quality Detection With Localized AI Analysis

Resolve Bottlenecks,
Find Innovative SolutionsGenerate Solutions

Solution Overview

Problem

Existing systems lack the ability to automatically identify and report quality issues in digital pathology slides, which can lead to errors in diagnosis and increase turnaround times, without providing specific locations of the issues within the slides.

Innovation Solution

A computer-implemented method using artificial intelligence (AI) to analyze digital whole slide images (WSIs) by extracting features and applying trained machine learning models to detect and classify quality issues, including their specific locations within the slides.

Engineering Contradictions & Design Principles

VSEngineering Contradiction Analysis

1Productivity

If automated systems are used to process digital pathology slides, then productivity increases, but the ability to accurately detect and report quality issues deteriorates

Engineering Contradiction:

Improveprocessing speedVSAvoidquality issue detection accuracy

Core Design Contradiction:

ProductivityVSMeasurement precision

Solution Approach 1:

The system divides the digital pathology slide into multiple foreground tiles and processes them in parallel. Each tile is independently analyzed by the machine learning model to detect quality issues such as blur, staining problems, and tissue artifacts. This segmentation enables high-speed processing while maintaining accurate detection through localized analysis of each tile region.

Inventive Principle:

Principle #1Segmentation

2Measurement precision

If manual review is performed to ensure quality, then measurement precision improves, but loss of time increases

Engineering Contradiction:

Improvequality assessment accuracyVSAvoidreview time

Core Design Contradiction:

Measurement precisionVSLoss of time

Solution Approach 1:

The system replaces manual mechanical review with an automated machine learning-based image processing system. The trained model automatically detects and classifies quality issues including blur, staining abnormalities, and tissue artifacts, providing accurate quality assessment without requiring time-consuming manual inspection by pathologists or technicians.

Inventive Principle:

Principle #28Mechanics substitution (Replace mechanical system)

3Loss of time

If automated quality control is implemented, then loss of time decreases, but reliability of quality assessment deteriorates

Engineering Contradiction:

Improvequality control timeVSAvoidquality issue detection reliability

Core Design Contradiction:

Loss of timeVSReliability

Solution Approach 1:

The system implements a feedback mechanism where the machine learning model processes foreground tiles and generates quality assessments with specific issue classifications. The system provides detailed feedback on detected quality problems including their types and locations, enabling reliable automated quality control that maintains accuracy while significantly reducing processing time compared to manual methods.

Inventive Principle:

Principle #23Feedback

Data Source

PatentUS12614378B2Systems and methods to process electronic images to determine histopathology quality

Publication Date: 2026.04.28 PAIGE AI INC

AI summary

A computer-implemented method for processing an electronic image may include receiving, by an artificial intelligence (AI) system at an electronic storage of the AI system, one or more digital whole slide images (WSIs) and extracting one or more vectors of features from one or more foreground tiles of tile images of the one or more digital WSIs. The method may include running a trained machine learning model on the one or more vectors of features and determining, based on an output of the trained machine learning model, whether one or more quality issues are present in the one or more digital WSIs.