Computational Pathology Slide Quality Control System

Resolve Bottlenecks,
Find Innovative SolutionsGenerate Solutions

Solution Overview

Problem

In computational pathology, the variability in slide preparation and storage across different institutions leads to inconsistent slide quality, making it challenging for pathologists and AI algorithms to accurately diagnose and analyze whole slide images.

Innovation Solution

The development of a comprehensive quality control system, iQC, which analyzes image data to identify suspect slides, classify tissue as biopsy or non-biopsy, and assess slide quality by calculating various metrics such as stain fading and acrylamide aging.

Engineering Contradictions & Design Principles

VSEngineering Contradiction Analysis

1Reliability

If manual restaining of aged slides is performed, then slide quality can be improved, but labor time and processing speed decrease significantly

Engineering Contradiction:

Improveslide qualityVSAvoidprocessing time

Core Design Contradiction:

ReliabilityVSLoss of time

Solution Approach 1:

The patent replaces the manual mechanical restaining process with an automated image processing system that uses computational algorithms to detect and correct slide quality issues. The system automatically identifies aged slides through image analysis and applies digital corrections rather than requiring physical restaining operations.

Inventive Principle:

Principle #28Mechanics substitution (Replace mechanical system)

Solution Approach 2:

The system creates a digital copy of the aged slide and applies virtual corrections to the image data rather than physically restoring the original slide. This allows multiple quality adjustments to be made on copies of the image without affecting the physical slide or requiring repeated manual restaining.

Inventive Principle:

Principle #26Copying

2Measurement precision

If comprehensive quality control analysis is performed on all slides, then diagnostic accuracy is improved, but processing speed and productivity decrease

Engineering Contradiction:

Improvediagnostic accuracyVSAvoidprocessing speed

Core Design Contradiction:

Measurement precisionVSProductivity

Solution Approach 1:

The quality control process is segmented into multiple independent detection modules that analyze different aspects of slide quality separately (stain quality, bubble detection, artifact identification, etc.). Each module processes specific features in parallel, allowing comprehensive quality assessment without requiring sequential analysis of all slide attributes.

Inventive Principle:

Principle #1Segmentation

Solution Approach 2:

The system performs rapid preliminary screening to identify obviously quality-passing slides, then applies more comprehensive analysis only to slides that show potential issues. This partial action approach maintains high diagnostic accuracy for problematic slides while quickly processing the majority of quality-acceptable slides.

Inventive Principle:

Principle #16Partial or excessive action

Data Source

PatentUS20250086994A1Methods and systems for determining an object map

Publication Date: 2025.03.13 THE UNITED STATES OF AMERICA AS REPRESENTED BY THE DEPT OF VETERANS AFFAIRS

AI summary

A method and systems for automatically determining and classifying quality control issues in slide image data are disclosed. A method includes receiving image data associated with a slide, and determining, based on the image data, information associated with one or more pixels in the image data. The method further includes determining based on the information associated with the one or more pixels in the image data, one or more quality control indications; and identifying, based on the one or more quality control indications, the slide as quality control deficient.