6 results about "Cellular Morphology" patented technology

The invention relates to a cell morphology feature extraction and prediction analysis method, in particular to a cell morphology feature extraction and prediction analysis method for a high-throughput cervical TCT image. The method aims at solving the problems that in the cell analysis technology of the cervical TCT image, complex morphological characteristics of cells are not fully considered, the characteristic extraction precision is low, and the manual dependence degree is high. The method comprises the following steps: selecting cellular morphology characteristics of cervical TCT image auxiliary diagnosis; obtaining a segmentation result of the cell nucleus and the cytoplasm based on the segmentation network; extracting, measuring and calculating cell morphological characteristics based on a cervical TCT image segmentation result; and analyzing and visualizing the measurement and calculation results of the morphological characteristics of the cells. According to the method, medical priori knowledge and data-driven research methods are fused, and more interpretable quantitative data are provided for subsequent cervical cell research through conjoint analysis of shape features and texture features. The invention belongs to the technical field of medical image analysis and computer vision.

The invention provides a pepper pungency degree rapid detection method based on specific parenchyma cell thickness and application, and belongs to the technical field of pepper quality detection. According to the method, the pungency degree can be rapidly calculated by taking the radial thickness of the specific parenchymal cells on the inner side of the peel of the fresh red chili fruit as a morphological marker, measuring the thickness through sampling, vibration slicing and microscopic observation and substituting the thickness into a linear regression equation y = 25.751 x-3078.4, x is the cell thickness [mu] m, and y is a predicted Scovier index SHU. According to the method, the direct correlation between the pungency degree of the pepper and the cell morphology parameters is established for the first time, and the limitations of high cost, long period and sample damage of a traditional high performance liquid chromatography method are broken through, and the bottleneck of poor model universality of a near-infrared analysis method is broken through. The method has the outstanding advantages of being non-destructive, high in efficiency, low in cost, high in precision and the like, is particularly suitable for large-scale rapid screening of processing type pepper breeding populations, and remarkably accelerates the breeding process.

The present invention discloses a fluorescence in situ hybridization method for co-localization of multiple genes in shellfish hemocytes, belonging to the technical field of cell biology of marine invertebrates. By optimizing the osmotic pressure buffer system and the preparation method, the present invention can stably obtain a monolayer sample with complete and uniform cell morphology. By advancing the cell morphology imaging step, the complete morphological information of cells is obtained and fixed as a reference before implementing the stringent in situ hybridization process. The present invention can achieve in situ visualization of multiple target genes while better preserving the cell morphological structure, which helps to obtain more accurate and stable spatial distribution information of gene expression at the single-cell level, improves the overall reliability of the experiment, and provides a more effective analysis tool for the study of cell functions of marine invertebrates.

The invention discloses a rice stem multi-scale mechanical simulation modeling method, device and equipment and a medium. The method comprises the following steps: selecting a second base node stem of a mature period base of a rice variety to be tested as a sample; microcosmic characteristic parameters of the sample are extracted; based on the extracted microscopic characteristic parameters, material parameter calculation is carried out based on an HP-TS equation, hemicellulose-lignin matrix equivalent calculation, cellulose-matrix composite equivalent calculation, flexibility matrix and initial stiffness matrix construction and microfibril angle correction are completed in sequence, and an engineering constant of each layer of cell wall is obtained; performing image processing on the rice stalk paraffin section; constructing a rice stem tissue three-dimensional shell finite element model based on the cellular morphology contour and topological information obtained through image processing and the cell wall engineering constants obtained through calculation, and executing finite element simulation; actual measurement data are obtained through a rice stem tensile test and compared with a finite element simulation result for verification, and rice stem multi-scale mechanical simulation modeling is completed.

The invention relates to the technical field of variety identification, and provides a fresh ginger brittle variety identification method based on cellular morphology and moisture distribution, and the method comprises the following steps: S1, selecting a fresh ginger variety to be identified, and planting the fresh ginger variety according to a unified cultivation management condition until harvesting; s2, during harvesting, selecting to-be-identified ginger varieties which are consistent in plant type and are not diseased, taking tender ginger parts, and detecting the brittleness value, the transverse relaxation time of bound water, the average cell area and the average vascular bundle area; s3, single score conversion: converting the detection values into corresponding single scores according to a preset five-level segmentation scoring rule; and S4, comprehensive discrimination: comprehensively discriminating the brittleness of different varieties of fresh gingers by adopting a weighted scoring function. The invention establishes a combined identification method of cellular morphology and NMR moisture distribution, realizes accurate and objective identification of the high-brittleness ginger variety, and provides technical support for germplasm resource protection, origin identification management and raw material quality control.

The invention relates to the technical field of image processing, in particular to a breast pathological section data generation method and system based on deep learning, and the method comprises the steps: firstly carrying out the semantic segmentation of an initial section, constructing a feature space through calculating the features of cellular morphology, density, spatial distribution and the like, and carrying out the clustering; and then a plurality of pathological regions are accurately segmented by using a region growing algorithm. Then, Fourier transform is carried out on each pathological region, and by analyzing amplitude distribution and range of a spectrogram and extracting detail information features, key frequency components are screened and inverse transform is carried out, so that pertinence enhancement of each region is realized; and finally, splicing the enhanced pathological areas into a complete image, and outputting a final enhancement result after filtering processing. According to the method, the quality and detail expressive force of the pathological image are effectively improved.