3 results about "Distant metastasis" patented technology

The present application relates to a kind of nasopharyngeal carcinoma distant metastasis risk prediction method and system based on cross-modal Transformer and depth consistency loss.Its method includes: collecting the multi-modal MRI image data and structured clinical data of patient;Using pre-training model to obtain tumor region mask, according to which T1, T1C and T2 three modal MRI image is cut, and the image of region of interest containing peritumoral microenvironment is constructed;Image is input three-dimensional image encoder, and deep image feature is extracted, while clinical variable is embedded coding;Through cross attention mechanism, image and clinical feature are fused to model, and the comprehensive feature representation of patient level is obtained;Based on the fusion feature, continuous type distant metastasis risk score is output, and combined with auxiliary classification branch and depth consistency loss, joint optimization is carried out, and the prediction result is obtained.The present application effectively focuses on tumor and peritumoral microenvironment information, enhances the deep layer interaction of multi-modal feature and early high-risk identification ability, and improves the accuracy of nasopharyngeal carcinoma distant metastasis risk prediction.

This invention discloses a joint detection system for nasopharyngeal carcinoma lesion segmentation and metastasis based on HSL-Net, including a weight management module for checking whether weight coefficients have been preset in the system; if the system has not preset weight coefficients, the model training module is activated; if the system has preset weight coefficients, the joint detection module is activated; the model training module generates weight coefficients for HSL-Net used for lesion segmentation and pathological staging classification; the joint detection module loads the weight coefficients onto the HSL-Net to perform lesion segmentation and pathological staging classification on the input image, and outputs the results after accuracy judgment, thus completing the joint detection; this invention introduces a novel neural network architecture based on a large-kernel convolutional global guided state space mechanism to achieve accurate segmentation of the spatial structure of the primary nasopharyngeal carcinoma lesion and sensitive identification of distant metastasis risk, thereby enhancing the comprehensive ability of intelligent disease diagnosis.

The application provides a TRIM29 inhibitor and its application in the preparation of a drug for resisting pancreatic ductal adenocarcinoma, and belongs to the technical field of biological medicine. The application provides the application of the TRIM29 inhibitor in the preparation of a drug for resisting pancreatic ductal adenocarcinoma, and the amino acid sequence of the TRIM29 is shown as SEQ ID NO. 3. It is proved by in-vivo and in-vitro functional experiments that the inhibition of the TRIM29 activity can significantly block the EMT process, migration and invasion ability of PDAC cells, inhibit the microvessel invasion and distant metastasis in the body, and has no obvious toxicity to normal cells, and has good biological safety and drugability. The application further provides a TRIM29 inhibitor, which can be used alone to block the early metastasis of PDAC, and can also be combined with a first-line clinical chemotherapy drug and an immunotherapy drug to synergistically enhance the anti-tumor effect, significantly improve the treatment benefit of the existing clinical scheme, and has a very high clinical transformation value.