Digital Pathology Annotation Transfer via Image Recognition

Resolve Bottlenecks,
Find Innovative Solutions
Generate Solutions

Solution Overview

Problem

In digital pathology, there is a need to efficiently transfer and maintain annotations from a reference slide to corresponding sample slides, as manual handling can be error-prone and time-consuming, especially when multiple regions of interest are involved.

Innovation Solution

An apparatus comprising a reference providing unit, a sample providing unit, a recognition unit, a determination unit, and an illustration unit that generates digital images of both reference and sample slides, recognizes spatial links between them, determines annotation positions, and physically illustrates annotations on the sample slides, allowing direct visualization of annotations on the sample slides.

Engineering Contradictions & Design Principles

VSEngineering Contradiction Analysis

1Productivity

If manual handling and transfer of annotations from reference slide to sample slides is performed, then flexibility and adaptability are maintained, but time consumption and error rate increase

Engineering Contradiction:
Improveannotation transfer efficiencyVSAvoidtime for manual annotation transfer
Core Design Contradiction:
ProductivityVSLoss of time

Solution Approach 1:

The patent implements automatic copying of annotations from reference slide to sample slides using image recognition and spatial transformation. The system captures images of reference and sample slides, recognizes corresponding regions through feature matching, and automatically transfers annotation positions and content, eliminating manual copy-paste operations and significantly reducing time consumption.

Inventive Principle:
Principle #26Copying

Solution Approach 2:

The patent replaces manual mechanical operations (handwriting, physical marking) with automated computer vision and image processing systems. The system uses algorithms to detect slide features, calculate spatial transformations, and automatically place annotations, substituting human manual work with computational processes that are both faster and more accurate.

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

2Reliability

If manual annotation transfer is performed, then device complexity remains low, but reliability and precision of annotation positioning deteriorate

Engineering Contradiction:
Improveannotation accuracyVSAvoidcomplexity of automated annotation system
Core Design Contradiction:
ReliabilityVSDevice complexity

Solution Approach 1:

The patent introduces an intermediary computer system that acts as a bridge between the reference slide and sample slides. This intermediary performs image capture, feature extraction, spatial transformation calculation, and annotation placement, serving as a reliable mediator that ensures accurate positioning while managing the complexity of the automation process through modular software components.

Inventive Principle:
Principle #24Intermediary (Mediator)

Solution Approach 2:

The system creates digital copies of slide images and annotations, allowing for precise measurement, transformation calculation, and error-free replication. By working with digital representations rather than physical slides, the system maintains high reliability in annotation positioning while the complexity is contained within the software processing layer.

Inventive Principle:
Principle #26Copying

3Loss of information

If multiple regions of interest are annotated on separate slides, then diagnostic completeness is improved, but manual tracking and association of annotations across slides becomes increasingly difficult

Engineering Contradiction:
Improveassociation between annotations and regionsVSAvoidease of tracking annotations across slides
Core Design Contradiction:
Loss of informationVSEase of operation

Solution Approach 1:

The patent implements a universal annotation management system that handles multiple slides and multiple regions of interest through a single integrated process. The system recognizes slide-specific features, calculates individual spatial transformations for each slide, and automatically transfers annotations while maintaining their associations, providing a multi-functional solution that works across numerous slides without increasing operational difficulty.

Inventive Principle:
Principle #6Universality (Multi-functionality)

Solution Approach 2:

The system creates and maintains digital copies of annotation data structures that include metadata about each annotation's association with specific regions of interest. These digital copies are automatically transformed and placed on corresponding slides, preserving the link between annotations and their target regions even when distributed across multiple slides, thereby preventing information loss.

Inventive Principle:
Principle #26Copying

Data Source

PatentEP3323107B1Information transformation in digital pathology
Publication Date: 2021.03.10 KONINKLIJKE PHILIPS NV
  • EP3323107B1 patent drawingFigure 1
  • EP3323107B1 patent drawingFigure 2
  • EP3323107B1 patent drawingFigure 3~4

AI summary

The present invention relates to an illustration of an annotation (22) at a sample slide (14). It is the intention for the invention to copy the annotation (22) provided at a reference slide (12) to the sample slide (14). Typically, a reference image (26) of the reference slide (12) is provided, in particular by scanning the reference slide (12). The reference image (26) therefore has the information about a reference slice (16) which is carried by the reference slide (12). Furthermore, the reference slide (12) has been marked with a region of interest (20) and the annotation (22), which can be associated with the region of interest (20). If such reference slide (12) is scanned, the respective reference image (26) comprises the information about the marked region of interest (20) as well as the annotation (22), too. Furthermore, the sample slide (14) carrying a sample slice (18) can be scanned, in order to provide a sample image (28). The sample slice (18) and the reference slice (16) are cut from the same object (10) of a biological material. In particular, the sample slice (16) has been cut directly after a cut of a material block has been preformed to provide the reference slice (18). Since the reference slice (16) and the sample slice (18) are from the same object (10), their features are very likely that the reference image (26) and the sample image (28) are very similar. Due to this similarity, the annotation (22) of the reference slide (12) is copied on a basis of an image recognition between reference image (26) and the sample image (28) to the sample slide (14).