A bone marrow cell few sample classification method, system and electronic equipment

By combining a histopathology pre-trained model and a multi-source text generation and selection module with a multi-scale, multi-modal network model, the problems of labor and material consumption and poor classification results in bone marrow cell classification were solved, and the accuracy of bone marrow cell classification with few samples was improved.

CN118587704BActive Publication Date: 2026-02-03WOMEN & CHILDRENS MEDICAL CENTER AFFILIATED WITH GUANGZHOU MEDICAL UNIVERSITY +1
0 Cites 0 Cited by

Patent Information

Application Number
CN202410739764.6
Authority / Receiving Office
CN · China
Patent Type
Patents(China)
Current Assignee / Owner
Filing Date
2024-06-07
Publication Date
2026-02-03
Estimated Expiration
2044-06-07

AI Technical Summary

Technical Problem

Existing technologies for bone marrow cell classification are extremely labor-intensive and resource-intensive in labeling categories, and deep learning models lack accurate text descriptions and fine-grained feature designs when classifying small sample sizes, making them unsuitable for effective bone marrow cell image classification.

Method used

By employing a histopathology pre-trained model and combining it with a multi-source text generation and selection module, more discriminative category text descriptions are generated through text feature extractors and image feature extractors. Furthermore, a multi-scale, multimodal classification network model is used to focus on both overall and detailed features, thereby improving classification accuracy.

Benefits of technology

It improved the accuracy of bone marrow cell classification in small sample sizes, especially significantly improving classification performance when the sample size is small.

✦ Generated by Eureka AI based on patent content.
Patent Text Reader

Abstract

The application discloses a kind of bone marrow cell few sample classification method, system and electronic equipment, method includes: obtaining bone marrow cell dataset, constructs few sample training set and test set establishes the multi-scale multi-modal few sample classification network model based on text multi-source generation selection;According to the few sample training set, the few sample classification network model is trained, and the trained bone marrow cell classification network model is obtained;The bone marrow cell image of test is input into the bone marrow cell classification network model, and the prediction class of bone marrow cell image is obtained, realizes the bone marrow cell image classification under the condition of few sample training.The present application selects histopathology pre-training model for bone marrow cell classification, and designs text multi-source generation selection module, standardizes the semantic description of each category of bone marrow cell, and further improves the few sample classification accuracy of bone marrow cell, which can be widely applied in the field of computer vision technology.
Need to check novelty before this filing date? Find Prior Art