Image Recognition for Cell Statistics with Partial Scan Convergence
Find Innovative SolutionsGenerate Solutions
Solution Overview
Problem
Manual cell counting in cytology is time-consuming and prone to errors due to the need for manual selection and enumeration of cells on microscope slides, especially when dealing with multiple cell types, leading to inefficiencies and inaccuracies.
Innovation Solution
A system and method utilizing image recognition to divide a region of interest on a microslide into sub-regions, perform sequential scanning, and accumulate cell counts until cell ratios converge, allowing for rapid and accurate calculation of cell ratios without scanning the entire region.
Engineering Contradictions & Design Principles
Engineering Contradiction Analysis
1Measurement precision
If manual cell counting is performed, then measurement precision can be maintained, but productivity is significantly reduced and time is consumed
Solution Approach 1:
The patent replaces the manual mechanical counting process with an automated image recognition system. The system captures images of blood smears, processes them through image recognition algorithms, and automatically identifies and counts different cell types, eliminating the need for manual microscopic examination and counting by cytologists.
Solution Approach 2:
The patent creates digital copies (images) of the blood smear specimens and performs analysis on these copies rather than physically manipulating the actual specimens. The image recognition system processes multiple images of the same specimen to identify and count cells, allowing repeated analysis without disturbing the original sample.
2Measurement precision
If the entire region of interest is scanned to ensure accurate cell counting, then measurement precision is improved, but the time required increases significantly
Solution Approach 1:
The patent divides the region of interest into multiple sub-regions or multiple images that can be processed independently. The image recognition system analyzes these segmented portions and accumulates cell counts from each segment to determine the overall cell ratio, allowing the system to stop scanning once sufficient data has been collected from the segments to achieve convergence.
Solution Approach 2:
The patent employs partial scanning by analyzing only the necessary portions of the blood smear to achieve accurate cell ratio determination. The system continuously accumulates cell counts from scanned images and monitors convergence of the cell ratio calculation, stopping the scanning process when the accumulated data from the partial samples is sufficient to produce stable results, rather than requiring complete scanning of the entire region.
3Measurement precision
If multiple images are captured to ensure comprehensive cell detection, then measurement precision is improved, but device complexity and processing requirements increase
Solution Approach 1:
The patent employs a multi-functional image recognition system that performs multiple tasks using the same hardware and software platform. The system captures images, processes them through recognition algorithms, identifies different cell types, counts cells, and calculates ratios - all within a single integrated system rather than requiring separate specialized devices for each function.
Data Source
AI summary
A system and a method for cell statistics based on image recognition is disclosed. A microscope captures the full image of a microslide, selects an interest region from the full image, and divides the region into sub-regions. A camera scans and transits the sub-regions to a host. The host performs image recognition on the scanned images to recognize various cells, and accumulates the number of the various cells in each of the scanned images to obtain a cell ratio of each type of the cells. When the number is accumulated and a difference among the cell ratios of the N consecutive scanned images is less than a preset value, the host stops scanning the remains of the sub-regions and outputs the cell ratio of each type of the presently-accumulated cells. The method can obtain various cell ratios of tissue samples for diagnosis.