Multispectral Cell Image Segmentation for Complex Morphology Classification

Resolve Bottlenecks,
Find Innovative SolutionsGenerate Solutions

Solution Overview

Problem

Current cytometric methods struggle to accurately classify complex cell morphologies such as sickle cells and spermatozoa due to heterogeneous shapes, relying on manual image analysis and limited data from flow cytometry.

Innovation Solution

A multispectral imaging flow cytometer acquires spatially aligned brightfield, side scatter, and fluorescent images, processed by a classifier engine that iteratively segments and correlates these images to enhance cell part localization, enabling automated classification of complex morphologies.

Engineering Contradictions & Design Principles

VSEngineering Contradiction Analysis

1Measurement precision

If manual image analysis is used to classify cell morphologies, then measurement precision can be maintained, but productivity is significantly reduced

Engineering Contradiction:

Improvecell morphology classification accuracyVSAvoidcell analysis throughput

Core Design Contradiction:

Measurement precisionVSProductivity

Solution Approach 1:

The patent uses digital image copies of cells captured by an imaging flow cytometer as input data. The system creates and processes multiple image copies across different channels (brightfield, fluorescent, side scatter) to enable automated classification while maintaining the precision of manual analysis through sophisticated image processing algorithms

Inventive Principle:

Principle #26Copying

Solution Approach 2:

The patent replaces manual mechanical image analysis with an automated computer-based classification system. The classifier engine uses algorithmic processing of digital images to identify cell morphologies, substituting human manual inspection with automated computational methods that achieve both high precision and throughput

Inventive Principle:

Principle #28Mechanics substitution (Replace mechanical system)

2Productivity

If flow cytometry is used for cell characterization, then productivity is improved, but measurement precision deteriorates due to limited data

Engineering Contradiction:

Improvecell analysis throughputVSAvoidcell morphology classification accuracy

Core Design Contradiction:

ProductivityVSMeasurement precision

Solution Approach 1:

The patent transitions from traditional one-dimensional flow cytometry measurements to multi-dimensional imaging data. By capturing cells across multiple channels (brightfield imaging, fluorescent imaging, side scatter) simultaneously, the system obtains rich morphological information that enables precise classification while maintaining high throughput

Inventive Principle:

Principle #17Another dimension (Dimensionality change)

Solution Approach 2:

The imaging flow cytometer performs multiple functions simultaneously: it captures brightfield images for morphology, fluorescent images for molecular detection, and side scatter data for physical characteristics. This multi-functional approach provides comprehensive cell data in a single high-throughput measurement

Inventive Principle:

Principle #6Universality (Multi-functionality)

3Device complexity

If single-channel imaging is used, then device complexity is reduced, but measurement precision deteriorates for complex morphologies

Engineering Contradiction:

Improveimaging system configurationVSAvoidcell part localization accuracy

Core Design Contradiction:

Device complexityVSMeasurement precision

Solution Approach 1:

The patent segments the imaging process into distinct channels (brightfield, fluorescent, side scatter), each optimized for specific cell characteristics. The classifier engine then integrates information from these segmented channels to achieve precise localization of cell parts and accurate morphology classification

Inventive Principle:

Principle #1Segmentation

Solution Approach 2:

The patent merges data from multiple imaging channels and scatter measurements into a unified classification output. The classifier engine combines brightfield morphology data, fluorescent signal locations, and side scatter information to achieve superior cell part localization and morphology identification accuracy

Inventive Principle:

Principle #5Merging (Combining)

Applied Scientific Principles

This section explains which scientific principles are used to turn an abstract innovation direction into a practical engineering solution.

Function Achieved in This Case

Achieves over 90% sensitivity and specificity in identifying cell types, including sperm defects and cancer cells, by extracting advanced shape features and improving image data accuracy.

Implementation Method 1

cells are in most cases stained with the same type of fluorochromes that are used by image cytometers

Methodology Applied

Scientific EffectFluorescence: Fluorescence

Implementation Method 2

side scatter images

Methodology Applied

Scientific EffectLight scattering: Scattering

Data Source

PatentUS12579830B2Combining brightfield and fluorescent channels for cell image segmentation and morphological analysis in images obtained from an imaging flow cytometer

Publication Date: 2026.03.17 CYTEK BIOSCI

AI summary

A classifier engine provides cell morphology identification and cell classification in computer-automated systems, methods and diagnostic tools. The classifier engine performs multispectral segmentation of thousands of cellular images acquired by a multispectral imaging flow cytometer. As a function of imaging mode, different ones of the images provide different segmentation masks for cells and subcellular parts. Using the segmentation masks, the classifier engine iteratively optimizes model fitting of different cellular parts. The resulting improved image data has increased accuracy of location of cell parts in an image and enables detection of complex cell morphologies in the image. The classifier engine provides automated ranking and selection of most discriminative shape based features for classifying cell types.