213 results about "Nodular lesion" patented technology

The invention discloses a thyroid nodule diagnosis method based on a deep learning network, and belongs to the field of image processing and artificial intelligence aided disease diagnosis. The methodcomprises the following steps: searching an ultrasonic original image and a pathological report of a thyroid nodule of a thyroid patient, and constructing a thyroid nodule database; preprocessing theultrasonic image; performing semantic segmentation on the ultrasonic image preprocessed in the step 2 through a Deeplab v3+ method based on Xception-JFT, and forming a semantic segmentation result graph; judging benign and malignant thyroid nodules based on a deep learning network; and forming a thyroid nodule diagnosis information report. According to the method, the Deeplab v3+ algorithm basedon Xeption-JFT is adopted to establish the thyroid ultrasound image segmentation network model, the optimal segmentation effect is achieved by continuously improving the backbone network Xception, nodule information can be automatically and rapidly recognized under high accuracy and high robustness, image features are automatically extracted for accurate segmentation to obtain a better diagnosis result, and an objective reference is provided for clinical diagnosis.

The invention discloses an ultrasonic image thyroid nodule intelligent detection system based on a Faster-RCNN. When the adopted Faster-RCNN model is used for carrying out target detection, speed increases and storage space is optimized compared with a regional convolutional neural network RCNN so that rapid and automatic detection of benign and malignant nodules is realized. The features are optimized in the model construction. Key features in an ultrasonic diagnosis standard ACR TI-RADS are calculated before deep learning training, key image feature factors influencing clinical diagnosis aresearched and added to a convolutional neural network feature layer for improvement, a new identification model is constructed, and therefore the accuracy of a prediction result is improved.

The invention discloses a thyroid nodule eliminating paste preparation for treating benign non-toxic thyroid nodules. The preparation is composed of the following medicinal raw materials in parts by weight: 6 to 11 parts of radix bupleuri, 10 to 15 parts of curcuma rhizome processed with vinegar, 15 to 20 parts of dioscorea bulbifera, 15 to 20 parts of fried semen brassicae, 6 to 11 parts of processed rhizoma cyperi, 30 to 35 parts of ternate buttercup root, 20 to 25 parts of prunella vulgaris, 10 to 15 parts of salt cake, 10 to 15 parts of rhizoma pinelliae preparata, 15 to 20 parts of laminaria, 15 to 20 parts of alga, and 30 to 35 parts of live oyster.

The present invention relates to methods, compositions and articles directed to diagnosing thyroid carcinoma, differentiating between thyroid carcinoma and benign thyroid diseases, testing indeterminate thyroid fine needle aspirate samples of thyroid nodules, and determining patient protocols and outcomes.

The invention discloses a thyroid nodule automatic detection model construction method, system and device based on a convolutional neural network, and the thyroid nodule automatic detection model construction method comprises the steps: carrying out the noise reduction of thyroid ultrasonic image data, and obtaining a thyroid ultrasonic image training data set; based on the training data set, using a Yolov3 network to train a thyroid nodule detection model; based on the training data set, using a Resnet network to train a thyroid nodule benign and malignant identification model; and fusing thethyroid nodule detection model and the thyroid nodule benign and bad recognition model to generate a thyroid nodule automatic detection model.

The invention provides a method for evaluating thyroid nodules by combining protein mass spectrometry with deep learning. According to the scheme, a genetic algorithm is adopted to obtain a protein combination capable of reflecting benign and malignant probabilities of thyroid nodules; based on a deep learning model, thyroid nodules are accurately classified by utilizing the selected protein combination; the possibility of malignant nodules is assessed, the surgical treatment cost and the treatment cost generated by subsequent medication can be greatly reduced, and meanwhile, the medical resource waste caused by excessive treatment can be reduced while the life quality of a patient is greatly improved.

The invention discloses a thyroid nodule focus region generation data enhancement method based on a deep convolutional generative adversarial network. According to the method, thyroid ultrasound images of a real patient are classified according to benign nodules and malignant nodules; a focus area image is generated by using a deep convolutional generative adversarial network; According to the method for generating image fusion in the lesion area, the image which is generated from the lesion area and is close to the real lesion is selected and fused with the thyroid image of a normal person toachieve the purpose of data enhancement, and the method for generating image fusion in the lesion area improves the quality and diversity of enhanced data, enables the generated image to be close tothe real image to the maximum extent and is more credible.

The invention discloses a thyroid nodule Tirads grading automatic identification model construction method and device. The method comprises the following steps: S1, carrying out data preprocessing on a thyroid ultrasound image; s2, performing ellipse fitting conversion on the preprocessed thyroid ultrasound image to generate a segmentation mask as a training label; and S3, building a multi-task model based on a convolutional neural network, inputting the training label into the multi-task model, and performing training by adopting a preset loss function to obtain a trained thyroid nodule Tirads grading automatic identification model. According to the invention, in thyroid nodule TI-RADS grading automatic identification, the latest convolutional neural network framework is used for carrying out automatic identification tasks on thyroid ultrasound images in an end-to-end mode, TI-RADS grading is completed, detection work can be completed in the early stage of thyroid cancer, and therefore expensive work such as puncture does not need to be used; and a doctor is assisted to complete thyroid cancer screening.

The invention relates to a biomarker for preoperative identification of benign and malignant thyroid nodules, a kit and application thereof. The level of 17 metabolites in peripheral blood plasma of a thyroid nodule patient is detected through metabonomics analysis, and omics analysis and a machine learning method are combined to construct a diagnosis model and evaluate the thyroid cancer diagnosis efficiency by using a subject working curve (ROC). The area of the metabolic marker combination diagnosis model composed of the metabolites under the ROC curve in thyroid nodule diagnosis can reach 95.05%, the sensitivity and specificity are both higher than 88%, and the metabolite marker combination diagnosis model can be applied to identification of thyroid benign and malignant nodules.

The invention belongs to the technical field of image processing, and particularly relates to a thyroid nodule invasiveness prediction method based on target detection. The method comprises the following steps: S1, preprocessing a thyroid ultrasound image obtained clinically to obtain an original data set; S2, constructing a positioning network model of a network structure based on a traditional Faster RCNN, and pre-training the positioning network model; S3, extracting nodule form information in the ultrasonic image by using a positioning network, and obtaining aspect ratio information of the nodules and context information of gland tissues; S4, constructing a classification network model; S5, establishing a multi-model fusion thyroid nodule invasiveness prediction network, and predicting the thyroid nodule invasiveness in the ultrasonic image; and S6, training and updating the classification network model in the fused network model, and storing the model with the highest accuracy in the verification set. According to the method, end-to-end full-automatic auxiliary diagnosis can be achieved, and the defects that a traditional method is insufficient in accuracy and low in detection rate are overcome.

The invention provides a thyroid nodule analysis system based on elastic ultrasonic imaging, and relates to the technical field of computer-aided analysis. The system comprises: a data obtaining module which carries out thyroid nodule selection on an obtained elastic ultrasonic image, and obtains a thyroid nodule image; an edge recognition module used for carrying out edge recognition on the thyroid nodule image to obtain a nodule edge image; a feature analysis module used for respectively carrying out feature analysis on the thyroid nodule image and the nodule edge image to obtain a pluralityof image feature parameters; a feature selection module used for respectively calculating inter-class distances of the image feature parameters and adding the inter-class distances into a one-class interval sequence; and a nodule analysis module used for extracting the image feature parameters of the preset number of inter-class distances sorted in the front, and training to obtain a thyroid nodule state recognition model for subsequent thyroid nodule state recognition by taking the image characteristic parameters as input and the nodule state as output. The thyroid nodule analysis system hasthe advantage of effectively improving thyroid nodule state recognition accuracy.

The invention discloses a method and a device for automatically diagnosing benign and malignant thyroid nodules. The method comprises the following steps: step 1, carrying out noise reduction preprocessing on an original thyroid ultrasound image; 2, performing data enhancement on the preprocessed thyroid ultrasound image; 3, the thyroid ultrasound image after data enhancement being respectively put into three convolutional neural network models which are constructed through ResNet, DenseNet or ResNext in advance for training; and 4, carrying out model integration on images trained by different models in the step 3. According to the method, the problem that the automatic classification effect of benign and malignant thyroid nodules is poor is solved, the deep learning image automatic recognition technology is applied, the latest framework is used for extracting image features, the automatic classification task of benign and malignant thyroid nodules is completed in an end-to-end mode, and meanwhile high accuracy is guaranteed.

The invention discloses a thyroid nodule semi-supervised segmentation method based on an attention mechanism. The method comprises the following steps of: 1, carrying out preprocessing of a thyroid ultrasonic image, and removing an edge information region in the image; 2, constructing a semi-supervised segmentation neural network, performing classification and segmentation prediction tasks on theultrasonic image, and adjusting a network structure to adapt to a specific application scene; 3, adding an attention mechanism into the semi-supervised segmentation neural network to improve the network effect; 4, measuring the performances of a semi-supervised segmentation algorithm and an existing full-supervised segmentation algorithm in the field of thyroid nodule auxiliary diagnosis through an intersection-parallel ratio and a Dice coefficient; and 5, continuously reducing the number of the pixel-level labels, and observing the change condition of the network performance. According to theinvention, the thyroid nodule semi-supervised segmentation method based on an attention mechanism benefits from the semi-supervised effect of a small number of pixel-level labels while keeping the high segmentation performance of the semi-supervised segmentation model, learns the real benign and malignant characteristics of the nodules and improves the benign and malignant classification capacity.

The invention belongs to the technical field of medical treatment, and discloses a machine learning-based bimodal image omics ground glass nodule classification method, which comprises the following steps of: step 1, case data collection: collecting patients who receive 18F-FDG PET/CT examination due to suspicious ground glass nodules (GGN); step 2, image acquisition and reconstruction: performing image acquisition by adopting a PET/CT (positron emission tomography/computed tomography) imaging instrument; step 3, image feature extraction; and step 4, data processing and analysis. According to the method, the image omics model based on the combination of the PET image and the HRCT image is constructed by applying a machine learning method, the GGN is classified, including pre-infiltration lesion, micro-infiltration adenocarcinoma, infiltration adenocarcinoma and benign lesion, verification and testing, the method is good in robustness, high in accuracy, simple and feasible. According to the method, the functional metabolism information and the physical anatomical information of the molecular level of the focus are integrated, the prediction efficiency of traditional CT parameters and single CT radiomics is effectively improved, and clinical management of the GGN is facilitated.

The invention provides a method for detecting nodules in a thyroid ultrasound image based on deep learning. The method comprises the steps of preprocessing the thyroid ultrasound image; extracting features of the preprocessed thyroid ultrasound image to obtain a feature image; respectively inputting the obtained feature images into corresponding classification and regression structures, and obtaining specific position information of a thyroid nodule region in each feature image; for the classification loss, the central point distance regression loss and the offset loss generated by calculation of the feature images input into the corresponding classification and regression structures, obtaining the total loss of the to-be-trained model through weighted summation calculation; and training and testing the to-be-trained model. According to the method, an anchor box does not need to be arranged, the nodule region in the thyroid ultrasound image is efficiently detected, calculation and resource waste related to the anchor box are avoided, the training speed is increased, and the generalization performance of an experimental result is enhanced. The invention further provides a device for detecting the nodules in the thyroid ultrasound image based on deep learning.

The invention relates to an oriental blueberry fruit powder health product composition as well as a preparation method and application thereof, and belongs to the technical field of health products. The oriental blueberry fruit powder health product composition comprises the following components in parts by weight: 70-75 parts of oriental blueberry fruit powder, 16-20 parts of cassava starch, 7-9 parts of maltodextrin and 0.3-0.6 part of magnesium stearate. Verified by multiple experiments, the oriental blueberry fruit powder health product composition disclosed by the invention has good effects of repairing cell damages as well as maintaining beauty and keeping young by virtue of reasonable combination, is extremely wide in application prospects of products, and can be used for treating polycythemia, thyroid nodule, ovarian cysts, alcoholic liver diseases, fatty liver and adenomyosis of uterus; related reports of the effects are not provided in the field; and in addition, the preparation method of the oriental blueberry fruit powder disclosed by the invention is simple and reliable, ensures that anthocyanin and other nutritional components in oriental blueberry fruit can be effectively kept without being damaged, and is easy in popularization and application.

The invention relates to a thyroid nodule positioning and ultrasonic report error correction method based on a target detection network. The method comprises the following steps: establishing a deep convolutional neural network, wherein the deep convolutional neural network comprises a target detection network part and a classifier part, and the target detection network part detects a to-be-classified image to obtain a trachea and carotid artery detection result; the classifier part classifies the images according to the recognized relative positions of the trachea and the carotid artery in the images; and based on an input box event monitoring mechanism, comparing the classification result with keywords in the ultrasonic report, and if the classification result is inconsistent with the keywords in the ultrasonic report, giving a prompt. According to the invention, the phenomenon that left and right focuses are reversed due to manual errors is effectively avoided, so that the consistency and accuracy of text reports and pictures are ensured, and adverse medical accidents are reduced.

The invention provides an external traditional Chinese medicine composition for treating thyroid nodules. The traditional Chinese medicine composition is prepared from the following raw materials in parts by weight: 10 to 80 parts of spica prunellae, 10 to 80 parts of kelp, 10 to 60 parts of airpotato yam rhizome, 10 to 60 parts of bulbus fritillariae thunbergii, 10 to 60 parts of rhizoma curcumae, 5 to 30 parts of frankincense and 5 to 30 parts of myrrh. The external traditional Chinese medicine composition for treating the thyroid nodules achieves the effect of reducing the thyroid nodules and is free of toxic and side effects; meanwhile, the invention also provides a dosage form and a preparation method of the external traditional Chinese medicine composition for treating thyroid nodules, so that the external traditional Chinese medicine composition is convenient to treat and use, low in cost, simple and convenient to operate and suitable for large-scale production.

The invention discloses a thyroid nodule automatic identification model construction method, system and device based on a convolutional neural network, and the thyroid nodule automatic identificationmodel construction method comprises the steps: carrying out the data noise reduction of a thyroid ultrasonic image, and obtaining a training data set and a test data set; inputting the training data set into ResNet, DenseNet, and/or ResNext to carry out thyroid nodule malignant probability training to obtain a thyroid nodule automatic identification model; and testing the thyroid nodule automaticidentification model by adopting the test data set.

The invention relates to a thyroid nodule benign and malignant related marker and application thereof. The marker is the following target markers: a TTC34 gene or a TTC34 sequence of a genome, an SLC16A3 gene or an SLC16A3 sequence of the genome, an RARG gene or an RARG sequence of the genome, and any one or all of two selected from an RCOR2 sequence of an RCOR2 gene or a genome and an ITPKA sequence of an ITPKA gene or a genome. The invention relates to application of primer molecules and/or probe molecules hybridized with the target marker in preparation of a detection reagent or a diagnostic kit for diagnosing benign and malignant thyroid nodules, and application of a device for determining the methylation level of the target marker in preparation of the diagnostic kit for diagnosing benign and malignant thyroid nodules.

The invention relates to a system, a model and a kit for evaluating the malignancy degree or probability of thyroid nodules. The method comprises the following steps: processing a fine needle puncture tissue biopsy sample by adopting a pressure circulation technology, detecting proteomics data of target protein or polypeptide in the obtained sample by adopting a high performance liquid chromatography method and a mass spectrometry method, processing peptide fragment peak area information of the mass spectrometry data, and carrying out AI modeling, the method obtains a final evaluation result (malignant probability), can provide a reference for the thyroid nodule malignant degree for clinic, and also can provide a second evaluation result (malignant probability) for doctors for thyroid nodules which cannot be clinically identified in the prior art. The invention also provides a corresponding kit, a system, an evaluation model and related uses.

The invention relates to the field of medical detection, in particular to specific gene markers for TMT (thyroid malignant tumor) and an application of the specific gene markers. On the basis of a weighted gene coexpression network analysis method and by combination with clinical cases, the TMT is specifically correlated with abnormal expression of 17 gene markers and can be taken as a specific gene detection marker set. By means of verification of a large number of independent clinicopathological samples, specific mutation sites of 5 specific genes are further determined as molecular diagnosis markers. The related gene diagnosis marker set has important clinical application value for early molecular accurate diagnosis of the TMT, can be used for preparing a molecular diagnosis kit for detecting malignant thyroid nodules which are indeterminate according to clinical aspiration biopsy cytology, and particularly has important clinical application value for early molecular accurate diagnosis of patients with an uncertain FNAB (fine needle aspiration biopsy) cytology result of malignant thyroid nodules.

The external traditional Chinese medicine preparation comprises the following raw materials in parts by weight: 15-25 parts of dragon bone, 18-25 parts of oyster, 18-22 parts of rhizoma corydalis, 15-25 parts of asarum, 15-25 parts of eupolyphaga, 18-25 parts of semen momordicae, 3-8 parts of borneol, 16-23 parts of honeysuckle, 16-22 parts of dandelion, 14-22 parts of selfheal, 15-22 parts of turtle shell, 15-22 parts of thunberg fritillary bulb, 9-15 parts of ligusticum wallichii, 8-10 parts of angelica sinensis and 4-12 parts of rhizoma cyperi. The traditional Chinese medicine composition has remarkable effects of regulating qi-flowing for removing phlegm, eliminating goiter and resolving masses, nourishing yin to lessen fire and calming heart and liver, can be used for fundamentally treating thyroid nodules, has the total effective rate of 95% and has no adverse reaction.