Cancer auxiliary analysis system and device based on HE staining pathological image
An auxiliary analysis and pathological image technology, applied in the field of medical imaging, can solve the problem of inability to accurately segment cytoplasm, achieve effective network model parameters, ensure segmentation accuracy, and ensure the effect of accuracy
- Summary
- Abstract
- Description
- Claims
- Application Information
AI Technical Summary
Problems solved by technology
Method used
Image
Examples
specific Embodiment approach 1
[0050] The existing cell segmentation methods cannot accurately segment the cytoplasm. On the one hand, the existing segmentation network model itself cannot accurately segment the cytoplasm. That is, for complex and difficult-to-divide images, the segmentation result of the network model itself is There are inaccurate problems; on the other hand, due to the current HE staining, the layers are not clear enough, the nucleus and cytoplasm are not clearly distinguished, and the layers of cytoplasm and extracellular space are even less clear, and the distinction is even less obvious, which further reduces the staining image of the neural network. Processing accuracy.
[0051] This embodiment is a cancer auxiliary analysis system based on HE-stained pathological images, including:
[0052] The dyed slice image acquisition module is used to acquire the stained slice image stained with HE, and perform image block segmentation on the image;
[0053] The cell nucleus segmentation module...
specific Embodiment approach 2
[0091] This embodiment is a cancer auxiliary analysis system based on HE-stained pathological images, which also includes:
[0092] The overall cell unit determination module, for the image block corresponding to the stained slice image, maps the segmentation result of the cytoplasmic segmentation module to the corresponding image block, and maps the segmentation result of the cell nucleus segmentation module to the same image block, and finally forms the stained slice The segmented image of the image, such as Figure 4 shown.
[0093] In fact, the segmentation results of the cytoplasmic segmentation module are mapped to the corresponding image blocks, and in the process of mapping the segmentation results of the cell nucleus segmentation module to the same image block, sometimes multiple nuclei are mapped in the same cytoplasmic division area. As long as the situation occurs when cells accumulate or become cancerous, such effects will not affect the auxiliary analysis of can...
specific Embodiment approach 3
[0095] This embodiment is a cancer auxiliary analysis system based on HE-stained pathological images, which also includes:
[0096] The auxiliary cancer analysis module is used to identify and classify cancerous cells based on the results of the overall cell unit determination module using the expert database. The identification and classification process is carried out in the form of an expert database, which stores the judgment rules of cancerous cells. The judgment rules of cancerous cells are the morphological characteristics of cancerous cells determined by experts based on the big data of pathological images, such as the arrangement of nuclei or cells state (whether disordered, clustered into pieces, etc.), nucleus size state (the size of each nucleus, and whether multiple nuclei are of different sizes), nucleus shape, etc., the feature of this embodiment is that it can also include Morphological characteristics, such as nuclear-cytoplasmic ratio, can improve the accurac...
PUM
Abstract
Description
Claims
Application Information
- R&D Engineer
- R&D Manager
- IP Professional
- Industry Leading Data Capabilities
- Powerful AI technology
- Patent DNA Extraction
Browse by: Latest US Patents, China's latest patents, Technical Efficacy Thesaurus, Application Domain, Technology Topic, Popular Technical Reports.
© 2024 PatSnap. All rights reserved.Legal|Privacy policy|Modern Slavery Act Transparency Statement|Sitemap|About US| Contact US: help@patsnap.com