113 results about "Thyroid nodular" patented technology

The invention discloses a thyroid nodule ultrasonic image processing method based on cross-layer sparse cavity convolution. A novel cross-layer cavity convolution network structure, a sparse constraint network, a separation sparse cavity convolution layer, and a loss function with adaptive weight adjustment and sparse constraint are established, the method overcomes the defects that an existing method is poor in thyroid nodule ultrasonic image nodule region semantic resolution capability, and semantic feature extraction of the nodule region is susceptible to interference of similar backgrounds, and solves the problem of poor extraction effect of a thyroid nodule ultrasonic image semantic probability heat map caused by limited receptive field expansion ability of a deep learning network ina forward propagation step.

The invention provides a group of thyroid cancer markers and an application thereof. The markers comprise thyroid cancer molecular typing related genes, targeted medication related genes, chemotherapymedication related genes, operation prompt related genes, prognosis related genes and thyroid cancer heredity related genes. According to the invention, aiming at all exon regions of 44 genes relatedto thyroid molecular typing, targeted medication, chemotherapy medication, operation prompt, prognosis and heredity, high-depth sequencing is carried out; meanwhile, various variation types like SNV / Indel and gene fusion of genes are analyzed; and molecular level information of thyroid nodules and thyroid cancer is deeply analyzed. Aiming at a capture probe designed for the 44 genes, 558 targeting target regions are covered; the probe comprises 3633 sequences with a total size of 254.096 Kbp; and a prepared kit is wide in coverage, high in cost performance and high in effectiveness, can provide a reference basis for further molecular typing, medication prompt, genetic risk assessment and the like of a thyroid patient, and is applicable to clinical popularization and application.

The invention is applicable to the computer field, and provides an analysis method for of thyroid nodules. The analysis method includes the steps: receiving a thyroid nodule analysis parameter input by a user, wherein the thyroid nodule analysis parameter includes basic information of the user and basic information of a thyroid; and determining a malignant risk for thyroid nodules of the user according to the thyroid nodule analysis parameter and a thyroid nodule analysis model generated through training, and outputting the result, wherein the thyroid nodule analysis model is generated throughtraining based on a random forest algorithm or a neural network algorithm. The analysis method for thyroid nodules directly outputs the diagnosis result according to the relevant information input bythe user, and the diagnosis process is convenient and quick, and the thyroid nodule analysis model which is generated through training based on the random forest algorithm or the neural network algorithm, utilized in the diagnosis process can effectively guarantee the accuracy of the diagnosis results.

The invention discloses Rhizoma pinelliae, herba taraxaci and bock greenbrier rhizome nodule rehabilitation oral liquid and a preparation method thereof. The preparation method comprises the following steps of: S1, extracting five types of poria cocos, pericarpium citri reticulatae viride, bighead atractylodes rhizome, radix astragali seu hedysari and ganoderma lucidum pieces for two times according to a conventional water extraction method; fermenting an extracting solution with edible yeast for 24 h; then inactivating bacteria at high temperature to obtain a fermentation solution; S2, washing 11 types of rhizoma chuanxiong, rhizoma pinelliae, radix bupleuri, radix curcumae, herba taraxaci, spica prunellae, rhizoma sparganii, rhizoma curcumae, herba patriniae, bock greenbrier rhizome and herba euphorbiae hirtae with water; extracting for two times according to a water extraction technology to obtain an extracting solution; S3, mixing the fermentation solution and the extracting solution and uniformly stirring in a reaction kettle for 35 min; and S4, filling a 50ML glass bottle with a liquid material through a special production line to obtain the Rhizoma pinelliae, herba taraxaci and bock greenbrier rhizome nodule rehabilitation oral liquid. According to the Rhizoma pinelliae, herba taraxaci and bock greenbrier rhizome nodule rehabilitation oral liquid disclosed by the invention, all the medicinal materials are reasonably matched and have the effects of detoxifying and eliminating swelling, removing stasis and reducing phlegm, tonifying Qi and nourishing Yin, removing dampness and discharging turbidity, strengthening body resistance and eliminating evil; and thyroid nodules are reduced and the serum thyroglobulin level is reduced, so that cancer recurrence and metastasis are prevented and the living quality of patients is improved.

The invention relates to an ultrasonic image-based thyroid nodule automatic segmentation method. The method comprises the following steps of 1, establishing a training set and a test set by using a public thyroid nodule data set; processing an image and an XML file, performing cutting to obtain the image and a label corresponding to the image, and dividing the image into a training set, a test set and a cross validation set in proportion; 2, establishing a thyroid nodule segmentation network, wherein network structures such as cavity convolution, dense connection and repair-module (correction module) are used; 3, training the thyroid nodule segmentation network by using the training set to obtain a trained segmentation model; and 4, verifying the segmentation model in a test set, and segmenting the thyroid nodule to obtain nodule lesion information. The thyroid nodule segmentation network is trained by using the training set, the trained segmentation model is obtained, and doctors are assisted in improving the diagnosis efficiency.

The invention discloses a thyroid nodule real-time segmentation method based on a full convolution dense hole network. The method comprises the following steps: 1, obtaining thyroid data and carryingout preprocessing; 2, labeling the obtained data to serve as a data set for training a full convolution dense hole network model; 3, constructing a full convolution dense hole network model based on dense connection, and performing parameter training; 4, replacing a convolution kernel in the convolution layer with hole convolution, and decomposing the convolution kernel by convolution kernel decomposition; 5, performing data standardization and nonlinear activation processing on the input of the convolution layer; and 6, analyzing and comparing the segmentation effect and efficiency of the full convolution dense hole network model.

The invention discloses an ultrasonic image thyroid nodule classification method based on feature decoupling, which is applied to the technical field of image processing and aims at solving the problem that the prior art is limited to change the input of a neural network to obtain features under different views. According to the method, a new local / global feature extraction method is established, a tissue-anatomy decoupling module is designed by using a self-attention mechanism to connect two paths of What and Where, and the task of thyroid nodule benign and malignant classification is completed in a multi-task learning form; according to the method, local / global feature decoupling can be completed in a feature space in a self-adaptive mode, compared with an existing method, a larger view field range is achieved, and more effective and stable features can be obtained. The benign and malignant thyroid nodule classification under the ultrasonic image has better diagnosis performance than doctors.

The invention discloses a primer for detecting variation of benign and malignant related genes of thyroid nodules, a kit and a detection method. According to the primer, the kit and the detection method, variation of 15 loci of the six genes and variation of the three fusion genes can be detected simultaneously, and the BRAF gene, the KRAS gene, the HRAS gene, the NRAS gene, the TERT gene, the EIF1AX gene, RET / PTC1 fusion, RET / PTC3 fusion and PAX8 / PPARgamma fusion are involved. Hotspot mutation and fusion variation of the genes are closely related to the benign and malignant thyroid nodules. Therefore, the primer, the kit and the detection method are used for detecting a sample of a patient and can assist doctors in benign and malignant identification of the thyroid nodules which cannot be clearly diagnosed in the cytology, the accuracy of identifying the benign and malignant thyroid nodules is improved, excessive medical treatment for the patient with the thyroid nodules is reduced, and the primer, the kit and the detection method have important practical significance and high economic benefit for saving medical resources of China.