Method for reconstructing magnetic resonance spectrum based on deep learning

    公开(公告)号:US11782111B2

    公开(公告)日:2023-10-10

    申请号:US17385104

    申请日:2021-07-26

    Inventor: Xiaobo Qu

    CPC classification number: G01R33/5608 G06N3/045 G06N3/08

    Abstract: A new method for reconstructing a full spectrum from under-sampled magnetic resonance spectrum data by using a deep learning network. First, the exponential function is used to generate a time-domain signal of the magnetic resonance spectrum, and a zero-filling time-domain signal is obtained after the under-sampled operation is completed in the time domain. The zero-filling time-domain signal and the full spectrum corresponding to the full sampling are combined to form a training data set. Then, a data verification convolutional neural network model is established for magnetic resonance spectrum reconstruction, where the training data set is used to train neural network parameters to form a trained neural network. Finally, the under-sampled magnetic resonance time-domain signal is input to the trained data verification convolutional neural network, and the full magnetic resonance spectrum is reconstructed.

    Method for embedding a load based on gel high hydrostatic pressure liquefaction

    公开(公告)号:US11505656B2

    公开(公告)日:2022-11-22

    申请号:US16374464

    申请日:2019-04-03

    Abstract: The invention relates to a method for embedding a load based on gel high hydrostatic pressure liquefaction. Using the phenomenon that the physical gel is liquefied under high pressure, the vacuum-packaged high-methoxyl pectin gel is treated under a pressure of 400-600 MPa for 5-30 min, mixed with the load, and then subjected to a pressure of 400-600 MPa for homogenization treatment for 5 to 30 min. After pressure relief, the liquefied gel is poured into a mold for reshaping, followed by removal of free water and coating treatment. This method combines the advantages of high hydrostatic pressure technology in modification and sterilization. It has mild embedding conditions and wide sources of raw materials to prepare the carrier, which has excellent biocompatibility and biodegradability. It can be widely used for embedding microorganisms, enzymes, proteins and small molecular substances. The loaded gel prepared by the method has high microbial safety, can effectively maintain the activity of the load. The load distribution is uniform, and the load amount is much larger than the traditional adsorption load.

Patent Agency Ranking