Automated Cell Counting via Multi-Plane Imaging and Area Analysis
Find Innovative SolutionsGenerate Solutions
Solution Overview
Problem
Manual cell counting in hemocytometers is time-consuming and prone to human error, often resulting in inaccurate cell concentrations due to difficulties in distinguishing live cells from debris and focusing issues, which can lead to inappropriate cell cultures and failed experiments.
Innovation Solution
An automated system that uses an imaging system to capture images of cells in multiple focal planes, identifies the focused image by determining the smallest cell area, and estimates cell numbers through image processing techniques, including object classification and counting, to reduce human error and improve accuracy.
Engineering Contradictions & Design Principles
Engineering Contradiction Analysis
1Measurement precision
If manual cell counting using hemocytometer and microscope is performed, then cell concentration can be determined, but the process is time-consuming and prone to human error
Solution Approach 1:
The patent replaces the manual mechanical counting process (microscope viewing and manual tallying) with an automated imaging system that captures images of cells in multiple focal planes and uses image processing algorithms to automatically count and classify cells. This substitution eliminates human intervention in the counting process, significantly reducing time while maintaining or improving accuracy through consistent automated measurement criteria.
Solution Approach 2:
The system creates digital copies (images) of the cell sample across multiple focal planes, allowing the cell concentration to be determined from these captured images rather than direct microscopic observation. The image processing system analyzes these copies to identify and count cells, replacing the need for manual visual inspection and eliminating the time-consuming nature of manual counting.
2Measurement precision
If manual focusing on single focal plane is used, then cell counting can be performed, but focusing issues lead to inaccurate cell concentrations
Solution Approach 1:
The patent segments the cell sample observation into multiple focal planes rather than relying on a single focal plane. The imaging system captures images at several different depths (z-stacks), ensuring that cells at various focal positions are all captured in at least one plane. This segmentation approach eliminates focusing issues by distributing the observation across multiple depth levels, improving both accuracy and reliability.
Solution Approach 2:
The system transitions from two-dimensional imaging (single focal plane) to three-dimensional imaging by capturing multiple focal planes at different z-heights. This addition of the depth dimension ensures complete sample coverage regardless of focal positioning, eliminating the reliability issues associated with manual focusing and single-plane observation.
3Measurement precision
If automated image processing is used to classify cells, then counting accuracy improves, but system complexity increases
Solution Approach 1:
The patent applies staining techniques that create distinct color or optical property differences between live cells, dead cells, and debris. This visual differentiation enables the image processing system to classify cell types based on their optical characteristics, improving identification accuracy while keeping the processing algorithms relatively simple by relying on established staining patterns rather than complex machine learning models.
Solution Approach 2:
The system uses multiple parameters (area, circularity, intensity, texture) to characterize and classify cellular objects in the images. By analyzing multiple parameters simultaneously rather than relying on a single feature, the system achieves high classification accuracy. The use of standard image processing parameters keeps the system complexity manageable while still enabling sophisticated cell type differentiation.
Data Source
AI summary
According to at least one aspect, a system configured to count cells in a vessel is provided. The system comprises an imaging system configured to image cells in the vessel and a controller coupled to the imaging system. The controller is configured to control the imaging system to capture a focused image of the cells and estimate a number of cells in the focused image. The controller is configured to control the imaging system to capture a focused image of the cells at least in part by controlling the imaging system to capture a plurality of images of the cells in a plurality of focal planes, determining an area of at least one cell in each of the plurality of images, and selecting one image from the plurality of images as the focused image using the area of the at least one cell in the plurality of images.