4results about How to "High clinical practical value" patented technology

This invention discloses a virtual immunohistochemical staining method and system based on relation generative adversarial networks (GANs) and sequence slide data, comprising the following steps: Step S1, constructing a sequence slide dataset, wherein each H&E-stained slide is followed by three consecutive Ki67-stained slides; Step S2, constructing a relation generative adversarial network (GAN) model, the model comprising two ResNet generators and two relation discriminators, used to train and evaluate the credibility of the sequence relationship between image pairs; Step S3, performing two-stage training on the relation generative adversarial network model, namely, basic style pre-training and Z-axis alignment relation adaptation. This invention fundamentally solves the Z-axis alignment problem, resulting in higher image fidelity and pathological accuracy, significantly improving clinical application value, and providing new research resources and evaluation paradigms.

The utility model relates to a porous plate sperm screening device based on upstream method, including porous plate base and sperm screening spare, the body middle part recessed and recessed bottom interval of porous plate base is provided with two or more than two culture holes, and each culture hole is provided with a sperm screening spare in a matched mode, the main part of sperm screening spare is embedded in the culture hole, and the culture hole wall top is sleeved in through the sleeve setting of sperm screening spare top, the main part bottom of sperm screening spare sets up the annular buffer ring groove that forms relative to the main part of sperm screening spare and extends inwards, and multiple channels are arranged on the inner side groove wall of buffer ring groove, and the main part bottom of sperm screening spare forms the communicating port in the inner side of buffer ring groove, and the filter membrane that seals the communicating port and is used for sperm upstream is arranged at the communicating port, at least one concave sampling groove is arranged at the bottom of buffer ring groove.

This invention discloses a prognostic assessment method and system for diffuse large B-cell lymphoma (DLBCL). The method first uses weighted gene co-expression network analysis (WGCNA) to screen gene modules closely related to lipid metabolism from DLBCL transcriptome data. Then, multi-step regression analysis (univariate Cox, LASSO, and multivariate Cox) identifies eight key prognostic genes from these modules: FNDC1, IL22RA2, C15orf48, OMD, MFAP2, BC017398, CXCL6, and TNFAIP6. Based on the expression levels and regression coefficients of these genes, a risk scoring model is constructed, which can classify DLBCL patients into high-risk and low-risk groups with significant survival differences. Further integration of the risk score with clinicopathological factors to construct a nomogram enables individualized survival probability prediction. This invention also provides a corresponding prognostic assessment system, electronic device, and storage medium. Validated with independent datasets, the prognostic model of this invention exhibits excellent predictive performance and clinical practical value.

The invention relates to the technical field of stomatology detection, and provides a tongue function detection method integrated with a multi-mode sensing array, which comprises the following steps: S1, providing a flexible attaching device and attaching the flexible attaching device to the tongue surface of a subject, and the flexible attaching device comprises a flexible substrate layer, a surface electromyographic electrode array, a micro inertial measurement unit and a flexible deformation sensing array; s2, collecting tongue muscle electrophysiological signals, tongue body local motion parameters and lingual surface local deformation through a surface myoelectricity electrode array, a micro inertial measurement unit IMU and a flexible deformation sensing array; s3, performing time alignment on the acquired data through a signal synchronization module; s4, through motion trail reconstruction, deformation form reconstruction and multi-modal information fusion, constructing a complete dynamic description of tongue body movement; and S5, performing quantitative evaluation on the tongue body activity function based on a reconstruction result. The objective of the invention is to solve the two bottlenecks in the lingual surface monitoring technology that only electrophysiological information exists, the synchronous recording capability of movement and deformation is not provided, and the multi-dimensional quantification of tongue body movement cannot be realized.