Systems and methods for classifying blood cells
By using trained machine learning models to digitally stain and classify blood samples, the problem of time-consuming and error-prone blood cell classification in the prior art requires chemical staining, achieving efficient and accurate blood cell classification, and reducing laboratory costs and health risks.
CN120226047APending Publication Date: 2025-06-27SIEMENS HEALTHCARE DIAGNOSTICS INC
0 Cites 0 Cited by
Patent Information
- Application Number
- CN202380079910.0
- Authority / Receiving Office
- CN · China
- Patent Type
- Applications(China)
- Current Assignee / Owner
- Priority Date
- 2022-12-09
- Filing Date
- 2023-11-17
- Publication Date
- 2025-06-27
AI Technical Summary
Technical Problem
The prior art requires time-consuming and error-prone chemical staining methods when sorting blood cells, and the chemical reagents used are expensive and pose a threat to the health of laboratory personnel.
Method used
The images of blood samples were digitally stained using a trained machine learning model, intermediate features were extracted and provided to a multi-class classifier to classify components of the blood samples without using chemical staining.
Benefits of technology
Through digital staining and classification systems, laboratory costs are significantly reduced, chemical reagents are avoided health risks to laboratory personnel, and the efficiency and accuracy of blood cell classification are improved.
✦ Generated by Eureka AI based on patent content.
Abstract
In some embodiments, there is provided a method of classifying components of a blood sample, the method comprising: digitally staining an image of the blood sample using a trained machine learning model to generate a digitally stained image; extracting one or more intermediate features generated by the trained machine learning model during digital staining of the image; providing the extracted one or more intermediate features to a trained multi-class classifier; and employing the trained multi-class classifier to classify at least one component within the blood sample based on the extracted one or more intermediate features. Numerous other embodiments are provided.
Need to check novelty before this filing date? Find Prior Art