332 results about "Nodular lesion" patented technology

The invention discloses a benign and malignant nodule grading evaluation system based on large model fusion ultrasonic imaging and thyroid gene markers, which can organically fuse non-invasive examination and serological detection, can simulate and diagnose multi-grade risk probability information provided by a gold standard, realizes similar risk grading estimation in a non-invasive mode, and has a wide application prospect. The thyroid nodule risk assessment method can provide visual explanation conforming to clinical logic based on comprehensive information of iconography and molecular biology, can significantly improve the accuracy of thyroid nodule risk assessment, can also effectively improve clinical decision-making efficiency and patient credibility, and has important clinical application prospects. The system comprises a data acquisition module, an ultrasonic image feature extraction module, a gene marker feature extraction module, a multi-modal fusion and hierarchical reasoning module and a generation module.

The invention relates to the field of medicine, and discloses a thyroid nodule surgical operation planning and navigation system based on artificial intelligence, which comprises a multi-modal medical image acquisition module, an image preprocessing and enhancing module, an intelligent anatomical structure analysis module, an operation planning decision module and an intraoperative real-time navigation module, the multi-modal medical image acquisition module is used for integrating data of various image equipment such as ultrasonic equipment, CT equipment and MRI equipment, and space-time consistency of multi-modal images is ensured. According to the thyroid nodule surgical operation planning and navigation system based on artificial intelligence, the real-time calculation problem is solved, the system delay is reduced, which is crucial to real-time navigation in an operation, the real-time performance and the operation efficiency are improved, the operation time is shortened, and complications are reduced; by integrating the advantages of different images, the system can provide more comprehensive dissection views, help doctors to more accurately position nodules and important structures and avoid injury to nerves and blood vessels, so that the accuracy is improved, and the surgical risk is further reduced.

The invention discloses a lung CT image segmentation method based on Transform and U-Net, and the method comprises the steps: firstly obtaining a pulmonary nodule CT scanning image, carrying out the preprocessing, then constructing a segmentation model MCSTU-Net, enabling the model to extract abundant features through the fusion of a convolutional neural network and a Swin Transform module, and enabling the segmentation model to obtain a segmentation model MCSTU-Net. Enhancing and fusing feature information from different levels through a multiple attention fusion module; dividing the data set into a training set, a test set and a verification set, training and verifying the segmentation model, and finally performing focus segmentation on the pulmonary nodule CT scanning image by using the trained and verified model. According to the model and the method constructed by the invention, lesion tissues in the lung CT image can be segmented more accurately, the effectiveness of each module is verified through an ablation experiment, and doctors are assisted to diagnose and treat lung diseases.

The invention relates to the field of medical image analysis, in particular to a deep learning prediction system and method based on multi-modal thyroid cancer lymph node metastasis, and the system comprises a data collection module, a preprocessing module, a nodule segmentation module, a feature extraction module, a feature fusion module, a metastasis prediction module, an interpretability analysis module and a result display module. An ultrasonic image, an elastic imaging image, an ultra-micro blood flow image and clinical index data of a patient are integrated, an improved U-Net algorithm is used for precise segmentation of a thyroid nodule region, a multi-branch deep network is used for extracting multi-modal features, a dynamic weight fusion algorithm is used for integrating the features, and the accuracy of the thyroid nodule region is improved. According to the method, the thyroid cancer lymph node metastasis state (non-metastasis, central region metastasis or lateral neck metastasis) is predicted, meanwhile, a two-dimensional interpretability framework of Grad-CAM activation diagram and SHAP value contribution degree analysis is introduced, an intuitive prediction basis is provided for doctors, and the thyroid cancer lymph node metastasis prediction accuracy is remarkably improved.

The invention relates to the technical field of image classification, in particular to a thyroid nodule ultrasonic image classification method and system based on feature extraction, and the method comprises the following steps: based on thyroid nodule ultrasonic image data, calling a pixel normalization function to adjust a gray scale range to a set interval, screening an isolated noise region, and carrying out the smooth filtering, and acquiring the ultrasonic image after smoothing filtering. According to the method, by adjusting the gray scale range and screening isolated noise areas, gray scale distribution is balanced, noise interference is reduced, image readability is improved, edge change is recognized by analyzing the gradient direction through a small-scale convolution kernel, texture features are extracted through a medium-scale filter, redundancy is reduced in combination with pooling operation, and the feature hierarchical expression ability is enhanced; the edge sharpness parameter is calculated, the feature weight is optimized, the edge sharpness and the classification adaptability are improved, the local feature segmentation precision is improved, the classification boundary is adjusted according to the similarity score, the classification loss measurement is optimized, the error offset is reduced, and the classification stability and accuracy are improved.

The invention discloses a thyroid nodule automatic diagnosis method based on multi-modal deep learning. After ultrasonic image data, CT image data and clinical data of a patient are collected and preprocessed, spatial alignment of multi-modal data is achieved; extracting deep features from the multi-modal image data by using a convolutional neural network, performing image segmentation on a thyroid nodule region by using an improved ResNet structure and a U-Net structure, and extracting a region of interest; feature extraction and fusion are realized; constructing a deep neural network of a mixed mode, and training and optimizing a deep learning model; the model reasoning comprises the steps of preprocessing new input data, extracting and fusing features and generating a final diagnosis result. According to the invention, the automatic diagnosis of the thyroid nodules is realized by fusing the multi-modal data from different image sources and combining with the advanced deep learning model, so that the accuracy and efficiency of diagnosis are improved.

The invention discloses a thyroid cancer pathological image classification method and system based on multi-modal feature fusion and Bayesian optimization, and relates to the technical field of medical image processing, and the method comprises the steps: collecting a thyroid ultrasound image data set, and carrying out the preprocessing operation; extracting an improved local binary pattern feature, a Haralick texture feature and a VGG16 depth feature, and constructing a mixed feature space; and splicing the features in the mixed feature space into a 4119-dimensional mixed feature vector, and carrying out feature importance screening by utilizing ExtraTres. Improved local binary pattern features, Haralick texture features and VGG16 depth features are fused, a mixed feature space is constructed, feature importance screening and PCA dimension reduction are performed by using ExtraTrees, multi-level features of the image are effectively extracted, the accuracy of benign and malignant thyroid nodule classification is remarkably improved, meanwhile, network hyper-parameters are dynamically adjusted through a Bayesian optimization algorithm, and the classification accuracy of benign and malignant thyroid nodules is improved. And model convergence is accelerated in combination with a cosine annealing strategy, so that the generalization ability of the model is enhanced, and the model can be excellently expressed on different data sets.

The invention belongs to the technical field of medical image analysis, and relates to a lesion detection method and system based on multi-scan interactive deformable Mama, and the method comprises the steps: 1, image block embedding; 2, multi-scale feature extraction and interaction in the backbone network are scanned in parallel; 3, feature pyramid optimization based on dynamic weighted scanning fusion; 4, performing multi-scale fusion; according to the invention, through the adaptive scanning network and the deformable scanning mechanism, the characterization problem of the morphological heterogeneity of the oral cancer focus and the pulmonary nodule microstructure feature is effectively solved, the double breakthrough of the detection precision and the calculation efficiency is realized, and an efficient and reliable solution is provided for multi-cancer medical image analysis.

The utility model discloses a puncture rotary cutting needle for thyroid nodule treatment, which is characterized in that an outer tube and an inner tube are sleeved on the puncture rotary cutting needle, the inner tube is rotatably connected in the outer tube, and an outer side rotary cutting opening and an inner side rotary cutting opening are respectively arranged on the outer tube and the inner tube and are matched to form a rotary cutting window communicated with an inner cavity of the inner tube; the far end of the outer tube is constructed to be provided with the puncture tip, so that a puncture function is further realized on the basis of realizing rotary cutting and suction, thyroid tissues can be punctured and rotary-cut at the same time in a puncture entering process, the condition that the thyroid tissues need to enter and exit for multiple times is avoided, and the problem that an existing rotary cutting planer tool is difficult to adapt to a thyroid surgery scene is solved. According to the embodiment, the far end of the outer side rotary cutting opening extends to a part of the puncture tip, so that the opening position of the rotary cutting window at the far end is relatively lower than the opening position of the rotary cutting window at the near end, and when the thyroid tissue is sucked under negative pressure, the adsorption force to the thyroid tissue at the far end can be larger; and therefore, a better inhalation effect can be obtained.

The invention provides a screening method and application of an early prediction marker of papillary thyroid cancer, the early prediction marker of papillary thyroid cancer is P4HA2, application of a reagent for detecting the expression level of P4HA2 in preparation of a product is provided, and a P4HA2 inhibitor including a substance for knocking down P4HA2 gene expression is also provided. The invention also provides application of the P4HA2 inhibitor in preparation of a product for inhibiting migration and / or proliferation of thyroid cancer cells, and a screening method of a biomarker for predicting papillary thyroid cancer. The marker can be used for prediction and early prediction of papillary thyroid cancer, knock-down of the marker can also be used for prediction and early prediction of papillary thyroid cancer, early screening can be better completed, benign and malignant nodules are helped to be distinguished, unnecessary invasive detection is reduced, and the detection efficiency is improved. And a new view angle is provided for molecular mechanism research and early diagnosis of thyroid cancer.

The invention relates to the technical field of artificial intelligence, and provides a gastric cancer risk quantitative scoring method, system and equipment based on artificial intelligence, and the method comprises the steps: recognizing the image type of each image frame in alimentary canal endoscope image data; for the electronic dyeing image frame, identifying a part contour region and an intestinal contour region of the feature part in the image frame, determining an intestinal epithelial metaplasia grading category of the feature part according to an area proportion of the intestinal contour region in the part contour region, and performing electronic dyeing intestinal scoring on the image data; for the white light image frame, gastroscope part types included in the image frame and focus area types of all gastroscope parts are recognized; performing atrophy scoring on the image data according to the position distribution of the focus area of the atrophy type; performing table state scoring on the image data according to whether the plica enlargement, nodular gastritis and diffuse redness focus areas exist or not; and realizing gastric cancer risk quantitative scoring according to the electronic staining intestinal scoring, the atrophy scoring and the epistatic state scoring.

The invention discloses a thyroid nodule segmentation method based on a large model and cooperative consistent training, relates to the technical field of ultrasonic image analysis, and organically embeds the general reasoning ability of the large model into a semi-supervised model to complement the advantages of the semi-supervised model and the large model. The insufficient knowledge migration capability of the semi-supervised model is relieved by utilizing the general prediction capability of the large model, and meanwhile, the high-confidence misprediction of the large model is relieved by utilizing the feature collaborative consistency of the semi-supervised model, so that the actual prediction performance of the model is improved; through large model fine tuning operation under a semi-supervised framework, the large model can be subjected to fine tuning synchronously based on an unsupervised image and a supervised image, and meanwhile, the fine tuning convergence speed and accuracy of the model are accelerated based on collaborative loss and a high-quality pseudo tag; and through collaborative consistency training operation, the advantages of a semi-supervised model and an SAM model are organically complemented, and a high-quality pseudo-label generation scheme and collaborative loss based on self-reliability and collaborative reliability are provided.

The invention discloses a method for identifying benign and malignant thyroid nodules. The invention provides application of a reagent for detecting the expression level of genes in a sample of a subject to preparation of a kit for diagnosing or predicting thyroid cancer of the subject or identifying benign and malignant thyroid nodules of the subject, wherein the genes comprise one or more genes selected from the group consisting of TPO, SLC5A8, SLC26A4, GLIS3, DIO1, DIO2, TG, SLC5A5 and NKX2-1. The invention also provides a corresponding device and a kit.

The invention relates to the technical field of computer medical detection, in particular to a thyroid nodule benign and malignant classification method based on clinical information, radiomics and gene detection. According to the method, pathological diagnosis of thyroid nodules is used as a dependent variable, detection data including radiomics characteristics and molecular omics are used as continuous variables, and the detection data of at least three genes CLDN10, HMGA2 and LANM3 are selected as the data of the molecular omics; meanwhile, in combination with part of clinical pathological characteristics including gender, age and BRAF V600E mutation condition factors, a thyroid nodule preoperative diagnosis prediction model based on radiomics and molecular omics is constructed through an SVM modeling method. Gene detection, radiomics and clinical basic information are combined, and a thyroid nodule diagnosis model based on the combination is established on the basis of Chinese population. The method is used for assisting clinicians in distinguishing benign and malignant thyroid nodules and guiding clinical decisions

The invention relates to the technical field of ultrasonic imaging analysis, in particular to a thyroid nodule ultrasonic examination method and system.The thyroid nodule ultrasonic examination method comprises the following steps that thyroid tissue ultrasonic echo signals are obtained, instantaneous characteristics of nodule area signals are analyzed, energy distribution and instantaneous frequency difference values are calculated, stable resonance modes are screened, and a resonance mode characteristic matrix is established. According to the method, the decomposition precision of echo data and the accurate recognition capability of a target signal are improved by optimizing instantaneous feature analysis of an ultrasonic signal, background noise interference is remarkably reduced by combining energy distribution and frequency difference screening, image enhancement is optimized through a gradient change rate and a transformation kernel matrix, the definition of image details is improved, and the recognition accuracy of the target signal is improved. Short-time frequency feature extraction and frequency deviation measurement enhance the recognition capability of lesion tissues, and meanwhile, through analysis of frequency shift stability parameters and the deviation change rate, the accuracy of automatic judgment of nodule properties is improved, so that the thyroid nodule ultrasonic examination is more scientific and accurate.

The invention discloses a thyroid nodule ultrasound image segmentation method fusing factorization VMama and characteristic frequency band separation, and relates to the field of computer vision assisted medical treatment. Preprocessing the thyroid nodule ultrasonic image data set; inputting the processed image into an encoder of a segmentation model FMVM-DFFT for processing, extracting image features in a multi-level manner by using an FMVSS module based on VSS, and further finely extracting and fusing feature information under different frequencies by using a feature frequency band separation module DFFT; the method comprises the following steps of: transforming input features into a frequency domain from a space domain by adopting improved fast Fourier transform, decomposing the input features into high and low frequency components, respectively optimizing the high and low frequency components through point-by-point convolution and a channel attention module, recombining the high and low frequency components in a complex domain, and restoring the high and low frequency components to the space domain through inverse Fourier transform; then, through dynamic convolution, layer normalization processing and reserved input features, merging and transmitting to a decoder; the details of the segmentation result are further optimized; the problem that edge segmentation is inaccurate and not fine is solved.

The invention discloses a medical image artifact identification and elimination method based on a big data technology, and relates to the technical field of medical image processing, and the method comprises the steps: carrying out the preprocessing of collected image data based on gray normalization, and then carrying out the semantic segmentation and ROI positioning of the image content; and performing lesion segmentation on the positioned image content, selecting lesion features for quantification and fusion, performing model verification, and performing distributed deployment on the verified lesion segmentation model. According to the method, the problems of high missed detection rate of small nodules and high missed diagnosis risk of malignant lesions are solved through the lesion detection model, the false positive rate is reduced, the recall rate of the malignant lesions is improved, and through the lesion segmentation model, the segmentation adaptability to lesions of different sizes is improved, clear segmentation boundaries are obtained, surgical planning is assisted, and boundary positioning errors are reduced.

The invention discloses a thyroid nodule benign and malignant prediction method based on automatic segmentation and semi-supervised learning. The thyroid nodule benign and malignant prediction method comprises the following steps of data set establishment, image preprocessing, thyroid nodule segmentation model training, mask and image fusion processing, thyroid nodule benign and malignant classification model training and semi-supervised learning model construction. According to the method, the thyroid nodule effective area is segmented firstly, subsequent benign and malignant classification tasks are assisted, and information space is expanded and learned through semi-supervised learning, so that the problems of high medical image marking cost, insufficient data and limitation on deep learning model performance in the prior art are solved; and meanwhile, the second-generation basic model of the sliding window layered visual converter after mixing fusion is carried out on the basis of pre-training and by using the nodule region generated by the thyroid segmentation model realizes good performance, and high-precision thyroid nodule benign and malignant classification prediction can be realized.

The invention relates to a primer composition, kit and method for detecting benign and malignant thyroid nodule related gene mutation, and the primer composition comprises a primer pair for detecting benign and malignant thyroid nodule related gene DNA mutation and RNA fusion variation. The primer pair can be independently amplified, and can be used for performing efficient, high-sensitivity and high-specificity multiple amplification on DNA and cDNA templates to be detected under the same PCR reaction system and reaction program, and then the gene mutation condition of a related region can be obtained by constructing a library and sequencing, so as to assist clinical diagnosis of benign and malignant thyroid nodules. Moreover, specific nucleotide sequences are respectively connected to the 5'end of the upstream primer and the 3 'end of the corresponding downstream primer in a proper proportion in the primer composition, so that the homogeneity and specificity of multiple PCR amplification can be further improved, and the detected nucleic acid input amount and the lowest detection limit of mutation frequency (as low as 0.5%) are effectively reduced.

The invention relates to the technical field of image processing, in particular to an ultrasonic thyroid nodule feature pyramid edge weighted diffusion segmentation method, which comprises the following steps: acquiring an ultrasonic thyroid nodule image; a PEW-SegDiff model is constructed; gaussian noise is added through time in the forward diffusion process of the real mask image, and a label with noise is obtained; in the back diffusion process, the input image and the real mask image after forward diffusion are added to obtain a noise label feature image; training a PEW-SegDiff model by using the noise tag feature graph and the input graph to obtain a predicted initial image; and calculating the loss between the predicted image and the back diffusion image of the real mask. The thyroid nodule edge blurred image extraction method solves the problems that an original SegDiff model is limited in boundary learning capability and the effect is poor when thyroid nodule edge blurred images are extracted.

The invention discloses a thyroid ultrasound diagnosis report intelligent generation method based on a multi-mode large language model, and relates to a thyroid ultrasound diagnosis report intelligent generation method. The objective of the invention is to solve the problems of lack of term standardization and insufficient complex focus feature analysis in the prior art. According to the method, a full-flow technical system of double-flow coding, cross-modal alignment, dynamic man-machine cooperation and multi-dimensional evaluation is constructed. Multi-scale feature fusion of a thyroid global form and a nodule ROI region is realized through ResNet-50 and ConvNeXt double-flow coding networks, image-text semantic alignment is optimized by adopting a CLIP symmetry loss function, and training resource consumption is reduced in combination with an LoRA parameter fine tuning technology. A dynamic man-machine collaborative closed-loop mechanism is innovatively introduced, model parameters are iteratively optimized through doctor correction data, and a four-dimensional clinical evaluation system comprising ROUGE-L, BLEU-4, CIDEr and expert blind evaluation is established. The invention belongs to the technical field of medical artificial intelligence auxiliary diagnosis.

The invention discloses a thyroid nodule image classification method. The thyroid nodule image classification method comprises the steps of obtaining an image of an existing thyroid part and performing preprocessing to construct a training data set; constructing a thyroid nodule image classification initial model based on the convolution module, the attention mechanism and the full connection layer, and training to obtain a thyroid nodule image classification model; and classifying actual thyroid nodule images by using the obtained thyroid nodule image classification model. The invention also discloses an imaging method comprising the thyroid nodule image classification method. The thyroid nodule image classification model is constructed and trained based on the convolution module, the attention mechanism and the full connection layer, classification and imaging of the thyroid nodule images are achieved, and the thyroid nodule image classification method is higher in reliability, better in accuracy and better in applicability.

The invention relates to the technical field of image analysis, in particular to a thyroid nodule grading identification method and system.The thyroid nodule grading identification method comprises the following steps that Gaussian filtering processing is conducted on the basis of an ultrasonic image, a two-dimensional Gaussian kernel with the same size as the image is constructed, and the weight of each element in the kernel is calculated; the weighted value is subjected to weighted operation according to the relative position of each pixel and the neighborhood pixel and the pixel value, each pixel value in the original image is updated through weighted average, and a noise reduction image is obtained. According to the method, the local brightness is optimized by dynamically adjusting the histogram, the contrast is enhanced, and the detail expression is obviously improved; the edge definition of a rapid change area is enhanced through second-order gradient sharpening processing, artifacts are reduced, edge detection utilizes a composite gradient and double-threshold strategy, the accuracy of edge recognition is improved, texture feature extraction is comprehensively analyzed through a gray-level co-occurrence matrix, the stability and discrimination of feature vectors are enhanced, and the accuracy of edge recognition is improved. And a more reliable basis is provided for medical diagnosis.

The invention discloses a composition for detecting benign and malignant thyroid nodules and a detection method thereof, and relates to the technical field of medical detection, the composition comprises the following components: a DNA / RNA extraction reagent and a fluorescent quantitative PCR reagent; by combining the DNA / RNA extraction reagent and the fluorescent quantitative PCR reagent, nucleic acid can be efficiently and accurately extracted from the thyroid nodule fine needle puncture sample, specific gene mutation and gene fusion are detected through the fluorescent quantitative PCR technology, the accuracy and sensitivity of benign and malignant judgment of the thyroid nodule are remarkably improved, and the method is suitable for clinical application. And a doctor can formulate a treatment scheme earlier and more accurately, and the prognosis of a patient is improved.

The thyroid nodule classification system based on the ultrasonic radio frequency signal comprises a data acquisition module, a model construction module and a classification module. The data acquisition module is used for acquiring ultrasonic radio-frequency signal data of thyroid nodules, preprocessing ultrasonic radio-frequency signals to form an instance set, and constructing a data set with labels. The model construction module is used for constructing a neural network model for performing feature classification on the thyroid nodules and training the neural network model based on the data set; the neural network model comprises a feature conversion layer, a dynamic weight generation layer, a self-attention layer and a classification probability fusion layer. And the classification module is used for carrying out feature classification on the thyroid nodules based on the trained neural network model. The method has the advantages that the original ultrasonic radio-frequency signals are directly analyzed, so that information loss caused by image reconstruction is effectively avoided, key information in the ultrasonic radio-frequency signals can be accurately captured and analyzed, and high-precision classification of thyroid nodules is realized.

The present invention discloses a weak-supervised-based lung nodule segmentation method, system, device and medium, belonging to the segmentation of lung nodules in the field of artificial intelligence technology. The purpose is to solve the technical problem that only the lesion area can be segmented and the solid component of the lung nodule cannot be evaluated. The lung nodule segmentation model includes an input module, a downsampling module, an upsampling module and an output module. The input module includes an input convolution sub-module. The downsampling and upsampling modules include a downsampling convolution sub-module and an upsampling convolution sub-module, and the downsampling convolution sub-module is skip-connected to the corresponding upsampling convolution sub-module. Both output convolution sub-modules of the output module include a convolutional layer and a sigmoid activation layer, and the outputs of the convolutional layer and the sigmoid activation layer of each output convolution sub-module are used as the outputs of the lung nodule segmentation model. Therefore, the model can output the ground glass of the lung nodule and the solid component of the lung nodule, effectively solving the technical problem that only the lesion area can be segmented and the solid component of the lung nodule cannot be evaluated.

The invention discloses a preparation method of granules for treating breast and thyroid nodules and canceration, which comprises the following steps: S1, raw material preparation: preparing 199g of codonopsis pilosula, 332g of astragalus membranaceus, 149g of glossy privet fruit, 100g of herba epimedii, 166g of selfheal, 100g of uniflower swisscentaury root, 100g of rhizoma pinellinae praeparata, 100g of curcuma zedoary, 199g of salvia chinensis, 332g of selaginella doederleinii hieron, 100g of curcuma aromatica and 149g of cortex albiziae according to a mass ratio; s2, adding water to decoct the twelve medicines twice, adding 8 times by mass of water for the first time, extracting for 2.0 hours, and filtering; s3, adding 6 times by mass of water for the second time, extracting for 1.5 hours, filtering, and combining filtrates; s4, concentrating under reduced pressure to obtain clear paste with the relative density of about 1.05-1.10 (60 DEG C); and S5, performing vacuum drying, crushing into fine powder, adding dextrin and 10g of stevioside, uniformly mixing, granulating with 75% by volume of ethanol, drying, preparing into 1000g, and packaging, thereby obtaining the product.

The present disclosure provides systems and methods for Al model(s) that are trained to identify characteristics associated with lesions within a blood vessel and provide a suggested procedure associated with the lesion. The Al model may receive, as input, intravascular and / or extraluminal image data associated with the blood vessel and provide, as output, characteristics, e.g., characterizations, associated with the blood vessel. The characterizations may include, for example, form or tissue nature (e.g., microcalcification, punctate, fragment, sheet, nodular, or otherwise), location within the vessel (e.g., intimal, superficial, medial, deep, etc.), size (e.g., length, depth, thickness, etc.), severity, and / or the like. The characterizations may be used as input to the same and / or a different model for providing a suggested procedure associated with the lesion. The suggested procedure may include, for example, orbital atherectomy, intravascular lithotripsy, rotational atherectomy, cutting and / or scoring balloons, and / or the like.

The invention discloses a lightweight multi-feature fusion thyroid nodule classification method. Relates to the technical field of medical image processing, in particular to the technical field of a lightweight multi-feature fusion thyroid nodule classification method. According to the method, the Hifuse model is improved, so that the parameter quantity and the calculation complexity can be reduced while the global features and the local features of the image are fully mined and the benign and malignant thyroid nodules are comprehensively discriminated in a multi-view and multi-azimuth manner. The method comprises the following steps: acquiring and preprocessing a thyroid nodule ultrasonic diagnosis report image data set; a Hifuse model is constructed and improved; a radiomics feature learning module is introduced into the Hifuse model, the local attention module is replaced by the improved local attention module, and the global attention module is replaced by an Officient ViM global extraction module; and completing thyroid nodule classification by adopting the trained Hifuse improved model.

The invention relates to a thyroid nodule classification method based on a global lightweight attention module, and belongs to the field of deep learning and medical image processing. Comprising the steps of constructing a thyroid nodule data set; preprocessing and expanding a data set; constructing an attention mechanism-based improved classification model; training an attention mechanism-based improved classification model; the model is used for thyroid nodule benign and malignant classification; according to the method, the region of interest of the thyroid nodule ultrasonic image with the unified size is input, a global lightweight attention module and a high-low channel jump connection module are combined, and particularly, local features and global dependency of a feature map are adaptively combined through the global lightweight attention module, so that the local features and the global dependency of the feature map are combined, and the local features and the global dependency of the feature map are combined. And according to the channel direction, high and low frequency features are divided into a jump connection module, and feature extraction is further carried out on the thyroid nodule. More comprehensive thyroid nodule features can be obtained by using the network model, so that a more accurate and more efficient classification result can be obtained.