Microscopy Image Segmentation with Pattern-Based Mask Correction

Resolve Bottlenecks,
Find Innovative SolutionsGenerate Solutions

Solution Overview

Problem

Existing microscopy systems face challenges in generating error-free segmentation masks due to unfavorable illumination conditions, dirt, and transparent sample carriers, leading to erroneous image processing and complicating the calculation of accurate segmentation masks.

Innovation Solution

A parameterized model is used to adjust a pattern to the segmentation mask, exploiting geometric properties of the image content, with adjustable parameters to define shapes and spacings, and iteratively or analytically optimizing the pattern to maximize correspondence with the segmentation mask.

Engineering Contradictions & Design Principles

VSEngineering Contradiction Analysis

1Extent of automation

If a segmentation model is used to calculate segmentation masks from overview images, then sample navigation and analysis can be automated, but erroneous segmentation masks occur due to unfavorable illumination conditions, dirt, and transparent sample carriers

Engineering Contradiction:

Improveautomation of sample navigation and analysisVSAvoidaccuracy of segmentation mask

Core Design Contradiction:

Extent of automationVSReliability

Solution Approach 1:

A verification model is introduced as an intermediary between the segmentation model and the final segmentation mask. This verification model checks the plausibility of the generated segmentation mask and can trigger a recalculation if errors are detected, thereby improving reliability while maintaining automation

Inventive Principle:

Principle #24Intermediary (Mediator)

Solution Approach 2:

The system implements a feedback mechanism where the verification model evaluates the segmentation mask and provides feedback to the segmentation model. If the verification model detects errors, it triggers a recalculation with adjusted parameters, creating a closed-loop system that improves accuracy through iterative refinement

Inventive Principle:

Principle #23Feedback

2Reliability

If a verification model is used to check segmentation mask plausibility, then erroneous segmentation masks can be detected, but the overall process complexity increases

Engineering Contradiction:

Improvedetection of erroneous segmentation masksVSAvoidcomplexity of image processing system

Core Design Contradiction:

ReliabilityVSDevice complexity

Solution Approach 1:

The verification process is segmented into distinct functional components: a verification model for plausibility checking, an error detection mechanism, and a recalculation trigger. This modular segmentation allows each component to be optimized independently and simplifies the overall system architecture

Inventive Principle:

Principle #1Segmentation

Solution Approach 2:

The verification model performs self-validation by automatically assessing the plausibility of segmentation masks without requiring manual intervention. The system self-corrects by triggering recalculation when errors are detected, reducing the need for external verification and simplifying operational complexity

Inventive Principle:

Principle #25Self-service

Data Source

PatentUS12555239B2Microscopy system and method for image segmentation

Publication Date: 2026.02.17 CARL ZEISS MICROSCOPY GMBH

AI summary

A microscopy system comprises a microscope configured to capture an overview image and a computing device comprising a model trained for image segmentation, which calculates a segmentation mask based on the overview image. The computing device adjusts a pattern described by a parameterized model to the segmentation mask. An updated segmentation mask is generated using the adjusted pattern.