5 results about "Stain tissue" patented technology

This invention discloses a visual analysis and prediction method for the ZNF469 gene mutation status in colorectal cancer, belonging to the field of intelligent medical image analysis technology. It involves acquiring whole-slice images of H&E-stained tissue from colorectal cancer patients and corresponding ZNF469 gene mutation status data, constructing an image label pairing dataset; preprocessing the whole-slice images, cutting them into image patches, and using a pre-trained three-class classification model to filter out cancerous region image patches; extracting the macroscopic structural features of each image patch, and simultaneously constructing a nuclear perception map (Transformer) to extract microscopic nuclear morphological features and cell nuclear spatial topological features. This invention achieves rapid prediction of the ZNF469 gene mutation status in colorectal cancer based on pathological images, without relying on gene sequencing technology, reducing detection costs, shortening the diagnostic cycle, and enabling simultaneous mutation status prediction during pathological slide reading, thus improving the efficiency of colorectal cancer diagnosis.

Embodiments disclosed herein generally relate to identifying necrotic tissue in a multiplex immunofluorescence image of a sample section. In particular, aspects of the present disclosure relate to: accessing a multiplex immunofluorescence image of a sample section comprising a first channel for a nuclear marker and a second channel for an epithelial tumor marker, wherein the sample section comprises one or more necrotic tissue regions; providing the multiplex immunofluorescence image to a machine learning model; receiving an output of the machine learning model, the output corresponding to a prediction that the multiplex immunofluorescence image comprises one or more necrotic tissue regions at one or more particular portions of the multiplex immunofluorescence image; generating a mask for subsequent image processing of the multiplex immunofluorescence image based on the output of the machine learning model; and outputting the mask for the subsequent image processing.

A method for manufacturing a histologic tissue sample support device includes molding a tissue cassette, molding a frame, and coupling the tissue cassette to the frame by assembling a frame-cassette connector. The tissue cassette has a recess including at least one side wall and a bottom wall. The tissue cassette is formed of a first material that can be successfully sectioned in a microtome and is resistant to degradation from solvents and chemicals used to fix, process and stain tissue. The frame includes a bottom edge and is formed of a second material different from the first material and more rigid than the first material. The frame-cassette connector includes a first retaining structure formed integrally with the frame extending through a second retaining structure formed integrally with the cassette. The frame is capable of being decoupled from the cassette by separating the frame-cassette connector.

A histologic tissue sample support device includes a tissue cassette, a frame, and a lid. The tissue cassette has a recess including at least one side wall and a bottom wall and is formed of material that can be successfully sectioned in a microtome and is resistant to degradation from solvents and chemicals used to fix, process and stain tissue. The lid is coupled to the frame and includes a platen configured to be received within the recess of the tissue cassette. The tissue cassette is movably coupled to the frame by a frame-cassette connector. The lid and the tissue cassette are capable of moving from a first position to a second position with respect to the frame, and in the second position the bottom wall and at least a portion of the side wall extend beyond a bottom edge of the frame for sectioning in a microtome.

This application discloses a virtual staining method, apparatus, device, and medium for images, relating to the field of image processing technology. The method includes: inputting an image of tissue to be stained into a preset morphological instance detection model to locate morphological structural units of a preset category in the image, obtaining corresponding bounding box sets, and generating a target mask; inputting the image of tissue to be stained into a preset virtual staining generation model, performing staining transformation on the image of tissue to be stained through a global virtual staining path to generate a global staining result, and performing staining processing on the image regions where the morphological structural units in the image of tissue to be stained are located through instance virtual staining paths and according to the bounding box sets to generate instance staining results; performing geometric deformation correction processing on the instance staining results and outputting corrected instance staining results; and performing weighted summation and residual repair processing on the global staining results, corrected instance staining results, and target mask to generate a target virtual staining image. This achieves high-quality virtual staining.