Patents
Literature
Hiro is an intelligent assistant for R&D personnel, combined with Patent DNA, to facilitate innovative research.
Hiro

34 results about "Electron tomography" patented technology

Electron tomography (ET) is a tomography technique for obtaining detailed 3D structures of sub-cellular macro-molecular objects. Electron tomography is an extension of traditional transmission electron microscopy and uses a transmission electron microscope to collect the data. In the process, a beam of electrons is passed through the sample at incremental degrees of rotation around the center of the target sample. This information is collected and used to assemble a three-dimensional image of the target. For biological applications, the typical resolution of ET systems are in the 5–20 nm range, suitable for examining supra-molecular multi-protein structures, although not the secondary and tertiary structure of an individual protein or polypeptide.

Three-dimensional particle category detection method and system based on convolutional neural network

The invention provides a three-dimensional particle category detection method and system based on a convolutional neural network. The method comprises the following steps: constructing a three-dimensional mixed-scale dense convolutional neural network comprising a mixed-scale three-dimensional extended convolutional layer, dense connection and a loss function, training the convolutional neural network by using a three-dimensional frozen electron tomography image marked with the particle coordinates to obtain a particle selection model, and training the convolutional neural network by using thethree-dimensional frozen electron tomography image marked with the particle category to obtain a particle classification model; acquiring the three-dimensional frozen electron tomography image through a sliding window to obtain to-be-detected three-dimensional reconstructed subareas, predicting each subarea through the particle selection model, and combining prediction results of the subareas toobtain coordinates of each particle in the three-dimensional frozen electron tomography image; and extracting a three-dimensional image of each particle according to the coordinate of each particle, and inputting the three-dimensional image of each particle into the particle classification model to obtain the category of each particle.
Owner:INST OF COMPUTING TECH CHINESE ACAD OF SCI

Method for making customized acetabular prosthesis and auxiliary method for total hip replacement arthroplasty

ActiveCN110251277APlace stableLow surgical repair rateJoint implantsHip jointsSoftwareReverse engineering
The invention relates to a method for making customized acetabular prosthesis and an auxiliary method for total hip replacement arthroplasty, which relate to the technical field of the total hip replacement arthroplasty. The method comprises the followings steps: scanning the hip joint of a patient by using an electron tomography technique before an operation, obtaining three-dimensional data of the hip joint of the patient, and introducing the obtained three-dimensional data into the three-dimensional software to reconstruct an acetabular model of the patient; processing the patient's acetabular model in the three-dimensional software to obtain the acetabular model of the patient after milling; using a reverse engineering technique to obtain a prosthetic model matching the above model, and then using a 3D printing technology to print the prosthetic model to the customized acetabular prosthesis, and using the patient acetabular model to formulate a tool milling trajectory and the milling process parameters; before the operation, introducing the tool milling trajectory and the process parameters into the robot control software, and using a robot for doctor to mill the patient's acetabulum, wherein the customized acetabular prosthesis is provided for the doctor to mount the acetabulum of the patient after milling. The method can reduce the doctor's surgical burden and improve the quality of milling.
Owner:GUANGDONG UNIV OF TECH

Freeze electron cross-sectional image-oriented mismatching removal method

The invention discloses a frozen electron cross-sectional image-oriented mismatching removal method, which comprises the following steps of: S1, screening stable matching from a group of frozen electron cross-sectional image pairs, and extracting motion information between feature points as a training sample; s2, inputting the training sample obtained in the S1 into a pre-constructed nonlinear regression model, and fitting an identification function for calculating all matching correctness probabilities of the frozen electron cross-sectional image pair through training; s3, an identification function is obtained based on training fitting in the S2, and the frozen electron cross-sectional image pair is calculated to obtain an initial matching group; s4, repeating S1, S2 and S3 until an initial matching group of all the frozen electron cross-sectional image pairs is obtained; and S5, on the basis of all the initial matching groups, finishing final mismatching removal work through an RANSAC (Random Sample Consensus) algorithm. According to the method, the wrong matching is removed by using the motion consistency between the electron tomography projection image sequences, so that the correct matching between the images is effectively kept, and meanwhile, the accuracy of the alignment result is improved.
Owner:ZHEJIANG UNIV
Who we serve
  • R&D Engineer
  • R&D Manager
  • IP Professional
Why Eureka
  • Industry Leading Data Capabilities
  • Powerful AI technology
  • Patent DNA Extraction
Social media
Try Eureka
PatSnap group products