5 results about "Microdissection" patented technology

This application discloses a cutting tool and collection system for laser micro-cutting. The cutting tool includes a sample stage, a tool body, a fan, and a microscope objective. The tool body has an airflow channel that runs through it, with a first air inlet and a first air outlet at each end. The cutting head is located at the first air inlet, and the first air outlet is connected to the fan. Thus, the fan draws in gas and creates a negative pressure area at the cutting head. The sample stage moves the tissue block closer to the cutting head, causing the cutting head to cut the tissue block and form tissue sections. The tissue sections remain connected to the tissue block and are not completely separated from it. Under controllable negative pressure, the tissue sections adhere tightly to the cutting head, thereby significantly reducing tissue section displacement, warping, and detachment caused by cutting vibration, fluid disturbance, or laser scanning. This improves the spatial stability and positioning accuracy of the tissue sections during laser micro-cutting.

The application discloses a kind of based on deep learning's pathological image proteomics analysis method and system, it is related to bioinformatics, the method includes: using laser microdissection and mass spectrometry constructs paired image-protein dataset;Adopt pre-training VGG16 convolutional neural network to extract image deep feature, fusion cell morphological feature constructs whole proteome regression mapping model;Through U-Net single cell recognition and iterative deconvolution algorithm output cell level protein expression matrix;Combining mixed semi-supervised learning strategy handles label scarcity problem;Based on protein expression matrix, dimension reduction clustering, spatial heterogeneity quantification (CV+SHI) and visual analysis are carried out.The application realizes the regression mapping of pathological image to whole proteome (>2800) for the first time, breaks through the flux bottleneck of traditional virtual staining, realizes true single cell resolution proteomics, and provides new means for precision medicine.

The application discloses a kind of based on execution end self-adapting calibration microdissection motion control method and device, method includes calibration stage, accounting stage and application stage: calibration stage is established by scale reference member conversion factor of pixel and physical scale, to execute end is feature point collection at least four non-collinear position point image pixel deviation and mechanical driving pulse increment, constructs homography mapping model and solves mapping matrix;Accounting stage is based on scale conversion factor and is verified by microdissection target area conversion into real physical area;Application stage is based on the pixel deviation of execution end and target point in real-time image, by mapping matrix conversion into mechanical driving pulse increment, and superimposed to current mechanical absolute coordinate to generate absolute execution instruction, drive cutting motion until target area is cut off.This application realizes the unified compensation of multiple source errors, free external medium self-calibration, absolute coordinate control, significantly improves microdissection precision and automation level.

The application provides an immunohistochemical combined gene detection system for early screening of skin lymphoma, which integrates ten function modules of intelligent sample pretreatment, multi-target synchronous immunohistochemical staining, high-resolution digital pathology scanning, laser microdissection assisted micro-nucleic acid extraction, skin lymphoma specific gene panel amplification, high-throughput sequencing, multi-modal data fusion, intelligent risk assessment, dynamic follow-up early warning and standardized report generation. The system realizes accurate matching of spatial localization of immunophenotype and high-sensitivity gene variation detection on the same tissue section, and automatically outputs individualized risk score and diagnosis suggestion by fusing multi-dimensional data through artificial intelligence algorithm. Compared with the traditional method, the detection rate and interpretation consistency of early skin lymphoma are significantly improved, the whole process is automatically and standardized, and the system is suitable for clinical early screening, differential diagnosis and dynamic monitoring, and has important application prospect.