Method for generating training data based on immunohistochemistry and storage device
An immunohistochemistry and training data technology, applied in the computer field, can solve the problems of low efficiency and high labor cost requirements, and achieve the effect of accurate labeling
- Summary
- Abstract
- Description
- Claims
- Application Information
AI Technical Summary
Problems solved by technology
Method used
Image
Examples
Embodiment 1
[0068] The core of Example 1 is: firstly, perform multiple immunohistochemical detection of specific biomarkers in specific tissue regions / cells on a slice, mark the specific regions, and then perform immunohistochemical detection of target biomarkers on the same slice Chemical detection to determine the interpretation range of target biomarkers.
[0069] The breast cancer tissue is used as an illustration below:
[0070] According to the requirements of the "2019 Chinese Breast Cancer HER2 Detection Guidelines", when interpreting the results of HER2 immunohistochemical detection, the "observation procedure" must be carried out first, that is, the entire section should be observed under a low-power microscope to judge whether the staining is satisfactory And whether there is heterogeneity of HER2 expression. Normal mammary epithelium should not show strong membrane staining. Only the coloring of invasive carcinoma is evaluated, and the coloring of carcinoma in situ cannot be...
Embodiment 2
[0088] In addition to calculating the number of PD-L1-positive tumor cells, the PD-L1 interpretation rules for gastric cancer also need to calculate the number of PD-L1-positive tumor-related immune cells including T lymphocytes, but excluding granulocytes, plasma cells and other immune cells. Therefore, the identification of normal PD-L1 positive T lymphocytes is a key factor in the development of AI software, and on the PD-L1 immunohistochemical staining section, only the H&E staining section of another section in the corresponding area is used to detect PD-L1. When labeling L1-positive T lymphocytes, the common sense, energy and other factors of pathologists can affect the accuracy of labeling. Therefore, in this embodiment, through multiple staining, the cells with T lymphocyte marker staining and PD-L1 positive staining in the same section are the PD-L1 positive T lymphocytes that need to be marked, and the results are more intuitive. And objective and accurate.
[0089]...
Embodiment 3
[0101] Prostate Lesion Tissue Immunohistochemical Double Staining Kit adopts combined monoclonal antibody and double enzyme labeling method to simultaneously detect three antigens in a prostate tissue section: AMACR / p504s, p63, CK (HMW). AMACR is highly expressed in prostate cancer, not expressed or very weakly positive in normal prostate tissue, but scattered in prostate intraepithelial neoplasia (PIN) and atypical hyperplasia (AAH) tissue. p63 and CK(HMW) mark the nucleus and cytoplasm of prostate basal cells respectively, and the combination of the two can improve the recognition ability of basal cells. Normal prostate glands have two layers of cells (basal cells and glandular epithelial cells), while prostate cancer has no or only a small amount of basal cells. In this way, various lesions can be directly observed in the same slice with three combined antibodies, which is convenient. It is beneficial to the diagnosis and differential diagnosis of prostate cancer, PIN and A...
PUM
Login to View More Abstract
Description
Claims
Application Information
Login to View More