5 results about "Semi automatic segmentation" patented technology

The application discloses a kind of nnUNet zebra fish juvenile whole brain vascular system segmentation methods based on autonomous data set training, it is related to high-resolution imaging technology, image processing and medical image segmentation field, the method makes full use of zebra fish live transparency and fluorescent label advantage, obtains high-resolution whole brain three-dimensional vascular image data, and constructs high-quality segmentation truth value database by semi-automatic segmentation and artificial correction, training is carried out using nnU-Net deep learning model, realize the three-dimensional automatic segmentation of zebra fish brain vascular system signal.The application method significantly improves the degree of automation and precision of image segmentation, effectively solves the problems of low efficiency, high artificial dependence and poor repeatability of traditional brain vascular segmentation.The method is suitable for large-scale high-throughput data processing, can provide efficient, standardized image processing scheme for zebra fish brain vascular development mechanism and brain vascular disease model research, and has wide application prospect.

One aspect of the invention concerns a method for characterizing the internal three-dimensional organization of a biological tissue sample comprising a plurality of types of biological elements (201, 202), said method having the following steps:For at least one type of biological elements (201, 202, 203, 204) of interest among the plurality of types of biological elements (201, 202, 203, 204), automatic or semi-automatic segmentation in each image (IZ) from a stack of images (I3D), of at least one region containing at least one biological element (201, 202, 203, 204) having as type, the type of biological elements (201, 202,203, 204) of interest, the stack of images (I3D) having been acquired by Z-series imaging by automated ultramicrotomy under scanning electron microscopy and including a plurality of images (IZ) each acquired in a plane perpendicular to a depth axis (Z) and each associated with a position on the depth axis (Z), the plurality of images (IZ) being ordered by increasing position in the stack of images (I3D, 102);Characterization of a set of biological elements (201, 202, 203, 204) having as type the type of biological elements (201, 202, 203, 204) of interest, by calculation, for each biological element (201, 202, 203, 204) from the set of biological elements (201, 202, 203, 204), of at least one indicator (301, 302) relating to the structure, the morphology, the size, the polarity, the texture, the constitution, the orientation, a surface area, the alignment, the convergence, the density, the convexity or the concavity of the biological element (201, 202, 203,204), from each corresponding segmented region (104);Comparison between the indicators (301, 302) calculated for the set of biological elements (201, 202, 203, 204).

This invention provides a method and system for turbine blade CT image segmentation and point detection, relating to the field of image processing. The method includes: S1, acquiring industrial CT images of turbine blades and constructing a dataset; S2, performing semi-automatic segmentation and annotation, as well as key point annotation; S3, performing image flipping, rotation, and contrast adjustment operations for data enhancement; S4, constructing an image segmentation and point detection model; S5, designing a loss function to train a multi-task learning model; and S6, model training, testing, and output. The system includes an image acquisition module, an image annotation module, a segmentation and point detection model construction module, and a segmentation and point detection module. This invention uses multi-task learning to simultaneously segment and detect points in industrial CT images of turbine blades, achieving automated and high-precision detection of turbine blade wall thickness parameters, and providing a reliable digital solution for quality control and process optimization of key components of aero-engines.

The invention provides a turbine blade CT image segmentation and point location detection method and system, and relates to the field of graphic processing, and the method comprises the steps: S1, collecting a turbine blade industrial CT image, and constructing a data set; s2, performing semi-automatic segmentation labeling and key point labeling; s3, turning over and rotating the image, and adjusting the contrast to enhance the data; s4, constructing an image segmentation and point detection model; s5, designing a loss function to train a multi-task learning model; and S6, training, testing and outputting the model. The system comprises an image acquisition module, an image labeling module, a segmentation and point location detection model construction module and a segmentation and point location detection module. According to the method, segmentation and point location detection are simultaneously carried out on the industrial CT image of the turbine blade by using multi-task learning, automatic high-precision detection of the wall thickness parameter of the turbine blade is realized, and a reliable digital solution is provided for quality control and process optimization of key parts of an aero-engine.

The invention discloses an nnUNet zebra fish juvenile fish whole-brain blood vessel system segmentation method based on autonomous data set training, and relates to the technical field of high-resolution imaging technology, image processing and medical image segmentation. According to the method, high-resolution whole-brain three-dimensional blood vessel image data is obtained by fully utilizing the transparency and fluorescence labeling advantages of a zebra fish living body; and a high-quality segmentation truth value database is constructed through semi-automatic segmentation and manual correction, and an nnU-Net deep learning model is adopted for training, so that three-dimensional automatic segmentation of zebra fish cerebrovascular system signals is realized. According to the method, the automation degree and precision of image segmentation are remarkably improved, and the problems of low efficiency, high manual dependency, poor repeatability and the like of traditional cerebral vessel segmentation are effectively solved. The method is suitable for large-scale high-throughput data processing, can provide an efficient and standardized image processing scheme for zebra fish cerebrovascular development mechanism and cerebrovascular disease model research, and has a wide application prospect.