Automated Cell Counting via Morphological Image Processing
Find Innovative SolutionsGenerate Solutions
Solution Overview
Problem
Current cell-counting methods in chemosensitivity assays are cumbersome, time-consuming, and prone to errors due to manual counting of cells, which hinders the efficient determination of drug efficacy against cancer.
Innovation Solution
An automated cell-counting method using a processing unit to apply an image processing sequence involving closing and opening operations on sample images, computing relevancy scores for pixel clusters, and determining cell presence based on these scores, thereby accurately reconstructing cells and filtering noise without requiring complex algorithms or extensive computational time.
Engineering Contradictions & Design Principles
Engineering Contradiction Analysis
1Measurement precision
If manual cell counting is performed, then the operator can individually count dead and living cells, but the process becomes very cumbersome and time-consuming
Solution Approach 1:
The patent replaces the manual mechanical counting process with an automated image processing system. The processing unit applies image processing sequences (closing followed by opening operations) to automatically identify and count cells in captured images, eliminating the need for manual operator intervention while maintaining counting accuracy through algorithmic analysis of cell morphology and staining patterns.
2Reliability
If manual cell counting is performed, then individual cell identification is possible, but errors may result from operator fatigue and inconsistency
Solution Approach 1:
The patent replaces the human operator's visual inspection and manual counting with an automated image processing system that applies consistent algorithms to all samples. The processing unit executes standardized image processing sequences including closing and opening operations, ensuring uniform application of counting criteria across all samples without operator fatigue or inconsistency.
Solution Approach 2:
The patent creates a digital copy of the sample through image capture and processing. Instead of directly manipulating or observing physical samples, the system works with digital representations that can be analyzed repeatedly without degradation, allowing for automated analysis while preserving the original sample integrity.
3Productivity
If complex algorithms are used for automated cell counting, then counting speed improves, but computational time and processing complexity increase
Solution Approach 1:
The patent applies local quality by using targeted image processing operations (closing and opening) specifically designed for the local characteristics of cell images. These morphological operations are applied selectively to enhance cell boundaries and remove noise in specific regions of the image, rather than using complex global algorithms that process the entire image uniformly.
Solution Approach 2:
The patent changes parameters of the image processing system by adjusting the sequence and parameters of closing and opening operations. By optimizing these parameters, the system achieves efficient cell counting with relatively simple operations, avoiding the need for complex algorithms while maintaining high productivity through parameter optimization rather than algorithmic complexity.
Data Source
AI summary
A computer implemented cell-counting method including using a computer to perform the steps of applying a predetermined image processing sequence to a sample sub-image to obtain a processed sub-image, the sample sub-image being extracted from a color sample image of a sample including cells of a subject, the image processing sequence including ga main processing series including a closing followed by an opening of the sample sub-image; and for each cluster of adjoining pixels of the processed sub-image: computing a corresponding relevancy score based on a value of at least one predetermined feature of the cluster; and determining that the cluster corresponds to a cell if the computed relevancy score belongs to a predetermined range.