A model training, cell segmentation system, method and storage medium

By training the feature extraction model through self-supervised training and contrastive learning, the problem of insufficient cell segmentation accuracy in spatial omics data was solved, and higher accuracy cell segmentation results were achieved.

CN116564401BActive Publication Date: 2026-06-19MGI TECH CO LTD
2 Cites 0 Cited by

Patent Information

Authority / Receiving Office
CN · China
Patent Type
Patents(China)
Current Assignee / Owner
MGI TECH CO LTD
Filing Date
2023-04-10
Publication Date
2026-06-19

AI Technical Summary

⚠Technical Problem

Existing cell segmentation schemes lack sufficient segmentation accuracy in data obtained from spatial omics measurements, making it difficult to effectively segment the structure of the tumor microenvironment.

⚗Method used

A self-supervised training model is adopted, and the feature extraction model is trained through contrastive learning. The data is enhanced by the first encoder and the second encoder to construct positive and negative sample features. Contrastive learning is then performed to adjust the model parameters, resulting in a feature extraction model for cell segmentation.

🎯Benefits of technology

The accuracy of cell segmentation has been improved by reducing interference information through deep feature extraction, resulting in more precise cell segmentation.

✦ Generated by Eureka AI based on patent content.

Smart Images

  • Figure 1
    Figure 1
  • Figure 2
    Figure 2
Patent Text Reader

Abstract

This disclosure provides a model training and cell segmentation system, method, and storage medium. The model training system includes a first processor configured to: acquire a first dataset and a self-supervised training model; augment the first dataset to obtain first augmented data and second augmented data, inputting the first augmented data into a first encoder to obtain first positive sample features, and inputting the second augmented data into a second encoder to obtain second positive sample features; inputting the first positive sample features, the second positive sample features, and negative sample features constructed based on the second positive sample features into a contrastive learning module to obtain a contrastive learning result; and adjusting the model parameters of the self-supervised training model based on the contrastive learning result to obtain a feature extraction model, wherein the feature extraction model is used to implement the segmentation process of at least two cells. The technical solution of this disclosure can accurately segment cells.
Need to check novelty before this filing date? Find Prior Art