Automated Cell Region Selection via Axis Detection

Resolve Bottlenecks,
Find Innovative Solutions
Generate Solutions

Solution Overview

Problem

Manual selection of regions of interest in biological cell images is time-consuming and inefficient, hindering the accuracy and reliability of experiments like FRAP and FLIP.

Innovation Solution

A method that automatically identifies regions of interest by detecting primary and secondary axes of a biological cell, dividing the cytoplasm into areas, determining geometric features, and selecting areas based on predefined criteria, using an analysis unit in a microscope system.

Engineering Contradictions & Design Principles

VSEngineering Contradiction Analysis

1Measurement precision

If manual selection of regions of interest is performed, then selection accuracy can be maintained, but time consumption increases and efficiency decreases

Engineering Contradiction:
Improveselection accuracyVSAvoidtime consumption
Core Design Contradiction:
Measurement precisionVSLoss of time

Solution Approach 1:

The system performs self-service by automatically detecting cell structures, calculating axes, dividing cytoplasm into areas, and selecting regions of interest without human intervention. The analysis unit autonomously completes the entire ROI selection process that previously required manual operator input, thereby eliminating time consumption while maintaining selection accuracy through algorithmic precision.

Inventive Principle:
Principle #25Self-service

Solution Approach 2:

The manual mechanical process of visually inspecting and selecting ROIs is replaced by an automated analysis unit that uses image processing algorithms. The system substitutes human visual inspection and manual selection with computational methods including axis detection, cytoplasm division, and automated ROI identification based on geometric features and predefined criteria.

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

2Productivity

If automated region selection is implemented, then efficiency and productivity increase, but system complexity increases

Engineering Contradiction:
Improveselection efficiencyVSAvoidsystem complexity
Core Design Contradiction:
ProductivityVSDevice complexity

Solution Approach 1:

The automated selection process is segmented into distinct functional modules: image acquisition, cell structure detection, primary axis detection, secondary axis detection, cytoplasm division into areas, geometric feature calculation, and ROI selection based on predefined criteria. This modular segmentation manages system complexity by organizing functions into discrete, manageable components within the analysis unit.

Inventive Principle:
Principle #1Segmentation

Solution Approach 2:

The analysis unit serves multiple functions: it detects cell structures, calculates axes, divides cytoplasm, analyzes geometric features, and selects ROIs based on various predefined criteria. This multi-functionality consolidates what would otherwise require multiple separate tools or manual operations into a single automated system, increasing productivity while managing complexity through integration.

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

3Reliability

If automated analysis with predefined criteria is used, then objectivity and reliability improve, but adaptability to different cell types may decrease

Engineering Contradiction:
Improveexperimental reliabilityVSAvoidcell type adaptability
Core Design Contradiction:
ReliabilityVSAdaptability or versatility

Solution Approach 1:

The system maintains reliability through predefined selection criteria while achieving adaptability by allowing modification of these criteria parameters. The analysis unit can adjust geometric feature thresholds, area selection rules, and ROI definition parameters to suit different cell types and experimental requirements, ensuring both objective consistency and flexibility across diverse biological samples.

Inventive Principle:
Principle #35Parameter changes

Data Source

PatentEP3385882B1Automatically identifying regions of interest on images of biological cells
Publication Date: 2023.09.20 CARL ZEISS MICROSCOPY GMBH
  • EP3385882B1 patent drawingFigure 1A
  • EP3385882B1 patent drawingFigure 1B~1C
  • EP3385882B1 patent drawingFigure 2

AI summary

Techniques for identifying a region of interest in an image of a biological cell include detecting a primary axis of a structure of the biological cell and defining a first section line along the detected primary axis, detecting at least one secondary axis of the structure of the biological cell and defining a second section line along each of the at least one secondary axes. Based on the second section line along each of the at least one secondary axes and the first section line along the detected primary axis, a cytoplasm of the cell is divided into a plurality of areas. A geometric feature of each of the areas is determined and one of the areas is selected according to predefined criteria. The image data of the selected area is analyzed, and the image data is compared with the predefined criteria to identify regions that comply with the provided criteria. At least one area complying with the predefined criteria to a pre-defined degree is selected as the region of interest.