Monoclonality Image Matching for Floating CHO Cell Detection

Resolve Bottlenecks,
Find Innovative SolutionsGenerate Solutions

Solution Overview

Problem

Existing methods for determining cellular monoclonality in antibody-producing CHO cells require significant time and effort due to the challenge of identifying floating cells and morphologically similar objects, which are not accurately captured in same-day images.

Innovation Solution

A determination support device and method that utilizes a processor to analyze same-day and next-day images of cell cultures, extract cell-like objects using a machine learning model, and display low-similarity objects for easy identification, reducing the time and effort required for monoclonality determination.

Engineering Contradictions & Design Principles

VSEngineering Contradiction Analysis

1Device complexity

If only same-day captured images are used for monoclonality determination, then the determination process is simple, but floating CHO cells are missed and measurement precision deteriorates

Engineering Contradiction:

Improvedetermination process complexityVSAvoidmonoclonality determination accuracy

Core Design Contradiction:

Device complexityVSMeasurement precision

Solution Approach 1:

The system captures images at multiple time points (same-day and next-day) before final determination is made. By preliminarily capturing next-day images and performing preliminary object extraction and matching, the system ensures that floating cells are not missed while maintaining a structured determination process.

Inventive Principle:

Principle #10Preliminary action

Solution Approach 2:

The system creates a correspondence between same-day and next-day images by extracting cell-like objects from both images and matching them based on position and morphology. This copying approach allows verification of cell presence across time points without requiring direct observation of floating cells in the same-day image alone.

Inventive Principle:

Principle #26Copying

2Measurement precision

If extracted CHO cell-like objects are displayed for user verification, then measurement precision improves, but time and effort for user checking increases significantly

Engineering Contradiction:

Improvemonoclonality determination accuracyVSAvoiduser checking time

Core Design Contradiction:

Measurement precisionVSLoss of time

Solution Approach 1:

The system extracts only the cell-like objects from the captured images and presents them to the user for verification, rather than requiring the user to examine entire captured images. This extraction approach maintains measurement precision by focusing on relevant objects while significantly reducing the time and effort required for user checking.

Inventive Principle:

Principle #2Taking out (Extraction)

Solution Approach 2:

The system performs automatic extraction and matching of cell-like objects between same-day and next-day images, presenting only the extracted objects for user verification. This partial automation approach handles the time-consuming extraction and comparison tasks automatically, requiring user involvement only for final verification of the extracted objects.

Inventive Principle:

Principle #16Partial or excessive action

3Productivity

If multiple well plates (10-100 plates) are processed, then productivity increases, but the time and effort for user checking increases proportionally

Engineering Contradiction:

Improvenumber of well plates processedVSAvoidtotal user checking time

Core Design Contradiction:

ProductivityVSLoss of time

Solution Approach 1:

The system performs automatic extraction, matching, and comparison of cell-like objects across multiple well plates without requiring proportional user intervention for each plate. The automated processing handles the bulk work of analyzing 10-100 well plates, allowing productivity to increase while user checking time does not increase proportionally.

Inventive Principle:

Principle #25Self-service

Solution Approach 2:

The system combines the processing of multiple well plates into a unified workflow where cell-like objects are extracted and matched across all plates using the same automated algorithms. This merging approach allows batch processing of multiple plates, increasing productivity while maintaining consistent verification standards without linearly increasing user time requirements.

Inventive Principle:

Principle #5Merging (Combining)

Data Source

PatentUS20250356670A1Determination support device, operation method of determination support device, and operation program of determination support device

Publication Date: 2025.11.20 FUJIFILM CORP

AI summary

A determination support device that supports determination of monoclonality of a cell seeded in a container includes a processor configured to acquire a same-day image, which is a image of the container on the day the cell is seeded, and a next-day image, which is a image of the container on the day after the cell is seeded, extract a cell-like object, which is any of the cell or a similar object that is morphologically similar to the cell, from each of the same-day image and the next-day image, evaluate similarity between a first cell-like object, which is the cell-like object extracted from the same-day image, and a second cell-like object, which is the cell-like object extracted from the next-day image and corresponds in position to the first cell-like object, and display the first cell-like object of which the similarity is relatively low in an identifiable manner.