89 results about "Thyroid ultrasound" patented technology

The invention relates to the technical field of computer vision, and discloses a thyroid ultrasonic robot automatic scanning method, device and equipment based on RGB images and depth information and a medium, and the method comprises the steps: obtaining image information and depth information, coding the depth information, fusing and recognizing a target scanning area, determining an initial scanning point and an initial scanning direction, controlling the scanning probe to scan and collect a real-time scanning image, analyzing the real-time scanning image to recognize a preset target and an artifact area, adjusting a scanning posture and a scanning path based on a recognition result, monitoring a continuous existence state of the preset target, and stopping scanning when the preset target is not recognized continuously. The target area is identified by fusing the multi-modal image information, the scanning posture and path are dynamically adjusted in combination with real-time image analysis, scanning termination is intelligently controlled according to the target detection result, the positioning accuracy, image quality and standardization level of ultrasonic scanning are improved, and the method is suitable for automatic ultrasonic imaging of thyroid and superficial organs.

The invention relates to the technical field of image data processing, in particular to a thyroid ultrasound image intelligent analysis system. The system obtains an ultrasonic image of a thyroid gland, and obtains a calcification edge feature value according to the distribution position and gray level distribution of edge pixel points in a local area of pixel points in the ultrasonic image of the thyroid gland; according to the complexity and the discrete condition of the gray value of the pixel point in each preset direction in the local area of the pixel point, the confusion index of each preset direction is obtained, the organization boundary ambiguity is obtained in combination with the calcified edge feature value, and then the gain coefficient in the ACE algorithm is adjusted to obtain the improved gain coefficient, so that the accuracy and the robustness of the algorithm are improved. And carrying out image enhancement on the ultrasonic image of the thyroid gland by using the improved ACE algorithm. The gain coefficient in the ACE algorithm is improved based on the fuzzy degree of the tissue boundary of the ultrasonic image of the thyroid gland, and the contrast ratio and the image quality of the ultrasonic image are effectively improved.

The invention relates to the technical field of medical image processing, in particular to a thyroid calcification detection method and system based on image processing, and the method comprises the following steps: dividing a thyroid region ultrasonic image according to a fixed grid, calculating local contrast intensity and edge tendency based on a gray difference, screening a gray variation region, and recording an edge pixel group as a feature point set; according to the method, the detection precision of the calcification region in the thyroid ultrasound image is improved through gridding processing and gray difference analysis, artifact interference is effectively inhibited through gradient direction and angle change analysis of edge pixels, the accuracy of the calcification region boundary is ensured, boundary extraction is enhanced through recognition of a closed curve, and the accuracy of the calcification region is improved. The method avoids the problem of curve fuzziness, enables the recognition of the calcification structure to be more stable and reliable through the gray concentration and stability analysis, improves the detection accuracy, is suitable for different image qualities and disease types, and improves the clinical diagnosis support capability.

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 discloses a multi-attention mechanism network model and a thyroid ultrasound contrast focus segmentation method and system based on a multi-attention mechanism network. The multi-attention mechanism network model adopts an RFM-ResNeXt module to extract spatial and temporal feature information of an input video; aggregating the three-dimensional feature maps into a two-dimensional feature map through a bidirectional convolution LSTM module; inputting the two-dimensional feature map into a double attention module (DAM) to obtain an attention feature map; and carrying out convolution and up-sampling on the attention feature map to obtain a binary segmentation result image. The time-space information of the ultrasound contrast video can be effectively extracted by utilizing three attention mechanisms of channel attention, time attention and space attention, and the ablation area in the thyroid ultrasound contrast image can be automatically and accurately segmented.

The invention discloses a thyroid ultrasound image diagnosis method based on deep learning, and the method comprises the following steps: collecting a thyroid ultrasound original image set, and carrying out the preprocessing; performing focus segmentation on the standardized thyroid ultrasound image set; performing morphological constraint and boundary refinement; calculating the blood flow direction, blood flow velocity and blood flow power of each thyroid focus area and neighborhood; generating a preliminary fusion feature map based on a feature adaptive deep learning network, and fusing the preliminary fusion feature map with the thyroid focus blood flow feature vector set; obtaining a thyroid focus detection list through thyroid focus benign and malignant discrimination branches; and generating thyroid focus structured diagnosis data records based on the thyroid focus detection list, and writing the thyroid focus structured diagnosis data records into a computer-aided diagnosis system. According to the method, deep learning and multi-modal blood flow features are fused, intelligent diagnosis of the thyroid focus is achieved, and the method has the advantages of being high in precision, high in interference resistance and structured in result.

The invention provides a thyroid ultrasonic signal intelligent analysis and diagnosis method and system, and relates to the technical field of ultrasonic signal analysis, and the method comprises the steps: calculating different depth noise distribution, automatically adjusting a filtering parameter value, and carrying out the filtering through anisotropic diffusion; segmenting the processed image to obtain a nodule region; acoustic characteristic data, acoustic characteristic parameter data and image characteristic data are extracted to form a comprehensive characteristic vector, and dimension reduction is carried out; and calculating a feature association weight for optimization to obtain a classification result, and generating a diagnosis report. The thyroid ultrasound image analysis precision is improved, and intelligent diagnosis of benign and malignant nodules is achieved.

Theranostic targeted ultrasonic blasting nano-bubbles, a preparation method therefor, and use thereof, wherein the nano-bubbles are the targeted drug-gene nano-bubbles miRNA / FTY720 / PFP@PEI-T7 NBs. The nano-bubbles can be used for preparing a thyroid ultrasound diagnostic agent or a drug for treating thyroid cancer.

The invention discloses a thyroid ultrasound image nodule segmentation method based on spatio-temporal characteristics and frequency enhancement, and relates to the technical field of medical image processing, and the method comprises the following specific steps: multi-scale characteristic extraction: carrying out the gray normalization and median filtering preprocessing of a thyroid ultrasound image, and carrying out the segmentation of the thyroid ultrasound image nodule; extracting multi-scale features under different resolutions by using a pre-trained backbone network, obtaining the multi-scale features under different resolutions by the backbone network through multilayer convolution and pooling operation, and generating basic and advanced features through convolution operation; by designing an intra-frame feature extraction architecture based on frequency feature fusion and an efficient spatial-temporal feature aggregation mechanism, intra-frame and inter-frame collaborative optimization is realized, intra-frame and inter-frame high and low frequency features are solved by means of octave convolution, the perceptual ability of a model to ultrasonic image details and semantic information is improved, inter-frame and inter-frame feature fusion is realized, and the perceptual ability of the model to ultrasonic image details and semantic information is improved. A local circulation neighborhood propagation mechanism is adopted, and interference of thyroid movement on time sequence feature extraction is effectively restrained.

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 belongs to the cross field of multiple subjects such as artificial intelligence, computer vision, natural language processing and medical image processing, and discloses a thyroid ultrasound-assisted diagnosis method and system based on text-driven vision pre-training and cross-modal feature fusion. Wherein the model building and training stage comprises the following steps of: preprocessing to obtain an unlabeled image-text pair data set and a labeled image-text pair data set; an image encoder and a text encoder are constructed, pre-training is carried out, and text-driven visual pre-training is realized; using a cross-modal splicing attention fusion module (CMCAF) to realize fusion of text features and image features, inputting the fused text features and image features to a full-connection layer classifier, and performing training optimization through supervision; the application stage is to predict benign and malignant thyroid nodules for the to-be-predicted image-text pairs. The medical image multi-modal fusion method has the advantages of high accuracy, low dependence on pathological labels, high model interpretability, good clinical deployment feasibility and the like, and the problem of the existing AI model in the aspect of medical image multi-modal fusion is effectively solved.

The invention discloses a thyroid tumor evaluation system based on combination of an ultrasonic image and pathological data, and relates to the technical field of auxiliary decision making. Comprising the steps that an image acquisition module preprocesses a thyroid ultrasound image; the pathology acquisition module is used for extracting structured data containing pathology malignancy scores and molecular marker expression parameters; the feature extraction module generates feature vectors from the images and the pathological data respectively; the region screening module dynamically generates an image region sensitivity threshold value based on the molecular marker and the pathological malignant score; a weighted extraction module recognizes an image suspicious region and generates weighted features according to the image suspicious region; the multi-modal fusion module fuses bimodal features through a weight distribution rule; and the evaluation decision module outputs benign and malignant prediction results and confidence scores. Dynamic sensitivity regulation and control of deep coupling of pathological semantics and image features are realized, and image suspicious region identification precision and cross-modal decision reliability precision are improved.

The invention relates to the technical field of disease risk prediction, and discloses a risk prediction method for thyroid diseases, which comprises the following steps: acquiring thyroid ultrasound image data and preprocessing the thyroid ultrasound image data, the preprocessing comprising denoising, standardization and image enhancement; extracting feature information in the preprocessed thyroid image data, and performing feature extraction by using a convolutional neural network; obtaining gene data related to the thyroid disease, standardizing the gene data, removing redundant gene data, and selecting gene information related to the thyroid disease; and fusing the image data and the gene data. According to the method, the technical scheme of fusing the image data and the gene data is adopted, two types of data characteristics are effectively combined through mutual information maximization and weighted summation, and the technical effect of remarkably improving the disease risk prediction accuracy is achieved. According to the method, the defect that information of a single data source is incomplete is overcome, and a more comprehensive decision basis is provided.

The invention relates to the technical field of defect detection, in particular to a thyroid ultrasonic auxiliary scanning method and system, and the method comprises the following steps: obtaining a pixel gray value, local contrast and edge sharpness of a thyroid ultrasonic image, calculating a pixel gradient change rate, and screening a thyroid gland boundary region according to the gradient amplitude change rate. According to the method, the pixel gradient change rate is calculated, the boundary region is screened, the gland recognition accuracy is enhanced, noise interference is reduced, the boundary segmentation is optimized in combination with the multi-scale gradient change rate and the edge strength, the error recognition probability is reduced, the gradient difference weight matrix is constructed, and the boundary is adjusted based on the gray level uniformity, so that the segmentation is more in line with the tissue form; the low-contrast lesion detection capability is improved in combination with gray shift, gradient direction distribution and morphological parameters, the classification accuracy is improved through matching of the morphological change rate and global features, diagnosis support is optimized in combination with the gland volume, the hormone level and the lesion morphological ratio, and the credibility of personalized diagnosis is improved.

The invention provides a thyroid disease multi-omics mass spectrum construction analysis method and system.The thyroid disease multi-omics mass spectrum construction analysis method comprises the steps that a thyroid ultrasound image and multi-omics mass spectrum data are obtained, and a cross-modal incidence relation is generated based on anatomical structure characteristics of the thyroid ultrasound image and biomolecule space distribution characteristics of the multi-omics mass spectrum data; in combination with the thyroid anatomical structure deformation field and a multi-task optimization target, performing nonlinear coupling calculation on a back propagation error in a multi-task learning iteration process to obtain a gradient contribution weight between tasks; and generating a target multi-omics mass spectrum based on the cross-modal correlation features, the anatomical structure deformation field and the gradient contribution weight, and performing thyroid pathological feature analysis on the target multi-omics mass spectrum to obtain a three-dimensional positioning coordinate and a malignancy probability prediction value of the thyroid nodule. The thyroid disease diagnosis comprehensiveness and accuracy are improved.

The invention discloses a thyroid blood flow analysis method based on multi-modal data, and relates to a thyroid blood flow analysis method. The invention aims to solve the problems that an existing thyroid blood flow analysis method needs a large amount of time and energy due to the fact that manual labeling is needed, and image color deviation and wrong blood flow extraction can be generated. The method comprises the following steps: encoding three inputs of a thyroid ultrasound image, a thyroid Doppler image and clinical text data (including unstructured text data and structured detection data); fusing the extracted features by using a multi-modal feature fusion technology based on an attention mechanism and tensor fusion; a thyroid blood flow analysis model is obtained by finely adjusting a Chinese large model Baichuan-7B by adopting LoRA, fused features are input into the model to obtain blood flow condition analysis of thyroid glands, detailed description of the position, the area, the speed and the like of blood flow of thyroid glands and nodules is included, and suggestions for further diagnosis are given. The invention belongs to the technical field of medical image processing.

The invention relates to the technical field of thyroid gland, in particular to a thyroid gland abnormity intelligent early warning system based on pattern recognition, which comprises a density distribution judgment module, a boundary amplitude recognition module, a function trend screening module, a multi-source trend fusion module and a risk level calibration module. And analyzing the pixel gray level distribution change trend of each region. According to the method, the spatial distribution and density characteristics of the thyroid ultrasound image are automatically extracted, local structure differences are subdivided, accurate capture of regional anomalies is achieved, active association between the image and data is completed in combination with dynamic changes of time sequence biochemical indexes and comprehensive trend judgment, multi-source information is subjected to standardized fusion, and the accuracy and the reliability of the system are improved. A hierarchical decision in a continuous risk interval is formed, an early warning result takes structural parameters, function changes and detection time as core elements, a closed loop of an early signal identification and risk calibration process is realized, and the early discovery efficiency of high-risk anomalies is improved.

The invention provides a thyroid ultrasound image segmentation method and device and a readable storage medium of the thyroid ultrasound image segmentation method and device, and provides a C2F-TransUNet network architecture. According to the network, on the basis of a traditional TransUNet, a cooperative multipath feature enhancement module (CMFEM) and a cross-layer feature interaction fusion module (CFIFM) are introduced. The CMFEM optimizes the channel discrimination ability of bottleneck layer features and spatial detail recovery through two-dimensional attention coupling, grouping feature interaction and a dynamic fusion gate; the CFIFM strengthens complementary association of high-layer and low-layer features of the decoder through multi-domain feature perception and channel and space dynamic weight fusion. Experiments show that according to the method, Dice coefficients on DDTI and a self-built data set reach 84.62% and 80.03% respectively, the 95% Hausdorff distance is remarkably reduced, the precision, noise immunity and stability of thyroid nodule segmentation are effectively improved, and reliable technical support is provided for clinical diagnosis.

The invention discloses a pricing method for a special insurance with a disease body and a related product, and can be applied to the technical field of insurance pricing, and the method comprises the steps: obtaining hospital medical data of a thyroid nodule patient; the hospital medical data comprises thyroid function examination result data, thyroid ultrasound image feature data and patient clinical feature data; predicting the cancerization risk probability of the thyroid nodule patient by using a risk probability prediction model in combination with the hospital medical data, and determining a risk level; based on the canceration risk probability and the risk level, determining the treatment cost of the thyroid nodule patient by using a medical cost estimation model; and pricing the special insurance with the disease body in combination with the canceration risk probability, the danger level and the treatment cost. Therefore, a more refined cancerization risk probability is generated through the risk probability prediction model, insurance pricing is carried out, and the pricing accuracy is improved.

The invention provides a thyroid nodule detection system, and the system comprises a receiving module which is configured to receive a thyroid ultrasound video; the multi-target instance segmentation module is configured to perform frame-by-frame detection on target objects in each video frame through a trained target instance segmentation model to obtain detection data of each target object in each video frame, the detection data comprises a detection frame and confidence, and each target object comprises a carotid artery, a thyroid gland and a thyroid nodule; the instance tracking module is configured to track each target object in the thyroid ultrasound video by adopting a multi-target tracking algorithm based on target detection based on each detection data to obtain each tracking trajectory of each target object; and the determination module is configured to determine a target thyroid nodule detection result corresponding to the thyroid ultrasound video based on each tracking trajectory of each target object. According to the invention, the video can be processed for an end-to-end screening scene, and the detection accuracy is improved.

The invention relates to a thyroid nodule segmentation method based on prior attention and auxiliary guidance, belongs to the technical field of ultrasonic medical image processing, and solves the problems that the existing thyroid nodule ultrasonic image segmentation based on U-Net is poor in accuracy and low in clinical application value. Dividing the thyroid ultrasound image data set DS into a training set, a verification set and a test set in proportion; feature extraction is carried out by using the thyroid nodule ultrasound image ITN, minimum redundancy and maximum correlation feature selection is carried out on the extracted features, and optimized thyroid nodule benign and malignant prior features are obtained; calculating the overall loss L, training the PADPU-Net network by using the training set on the basis of the overall loss L, and verifying by using the verification set in the training process to obtain a PADPU-Net model MPADPU-Net; and the PADPU-Net model MPADPU-Net is utilized to test the thyroid nodule ultrasonic image test set DSTest, and a test result is optimized to obtain a final thyroid nodule segmentation result.

The application provides an AI-assisted thyroid scanning system and method, and relates to the technical field of ultrasonic examination.The application comprises the following steps: acquiring a video stream, dividing the video stream into multiple video clips in chronological order and associating time intervals, extracting optimal thyroid ultrasonic images from the video clips, uploading the optimal thyroid ultrasonic images to a cloud analysis system to obtain corresponding cloud analysis results, and distributing each video clip to multiple AI analysis lightweight models to obtain corresponding local analysis results; establishing a cache queue, adding video clips that have obtained local analysis results and cloud analysis results to the cache queue, adjusting the order, and then sequentially outputting each video clip and analysis result in the cache queue.The beneficial effects are as follows: the cost is reduced, the popularity of the system is improved, the real-time performance is improved, the data transmission pressure is reduced, the delay of diagnosis results caused by poor network conditions is reduced, and the reliability of diagnosis results is improved.

The present application provides a method and system for constructing and analyzing multi-omics mass spectrometry maps of thyroid diseases, wherein thyroid ultrasound images and multi-omics mass spectrometry data are obtained, and cross-modal correlation relationships are generated based on the anatomical structural features of the thyroid ultrasound images and the spatial distribution features of the biomolecules of the multi-omics mass spectrometry data. In combination with the thyroid anatomical deformation field and multi-task optimization objectives, nonlinear coupling calculations are performed on the back-propagation error during the multi-task learning iteration process to obtain the gradient contribution weights between tasks; based on the cross-modal correlation features, the anatomical deformation field, and the gradient contribution weights, a target multi-omics mass spectrometry map is generated, and the thyroid pathological characteristics are analyzed to obtain the three-dimensional positioning coordinates of the thyroid nodules and the predicted value of the malignancy probability. The present application improves the comprehensiveness and accuracy of thyroid disease diagnosis.

The present invention discloses an interpretable ultrasonic image nodule recognition method based on a hierarchical network, comprising: 1) establishing a thyroid ultrasonic image data set; 2) performing mosaic preprocessing on unlabeled data, and establishing a self-supervised learning network layer based on a 2D ultrasonic feature encoder to mine features of the unlabeled data; 3) establishing a nodule measurement network layer based on a 2D ultrasonic feature encoder to obtain the contour, size and aspect ratio of nodules; 4) establishing a self-supervised learning network layer based on a nodule ROI feature encoder to mine features of suspicious nodule ROIs; 5) establishing a nodule multi-factor quantification network layer to realize the recognition and quantification of edges, components, echo quality and calcification; 6) using a multi-layer perceptron to realize interpretable prediction of benign and malignant and lymph node metastasis. The experimental results prove that the present invention improves the accuracy of nodule contour measurement and multi-factor recognition, and further enhances the interpretability of automatically recognizing ultrasonic thyroid nodules.

The application provides a kind of construction and application of thyroid nodule benign and malignant classification model based on mask guide, the present application simultaneously inputs thyroid ultrasound original map, lesion mask and patient clinical structured information, designs anatomical boundary enhancement network, generates lesion anatomical boundary graph by mask inflation, erosion operation, adopts double-branch deep convolution to strengthen internal and boundary features of nodule respectively;Propose mask conditional attention mechanism, fuse three types of channel descriptors to weaken irrelevant background interference, and build BRM bidirectional mutual feedback modulation module, realize image and structured feature adaptive mutual calibration fusion through bidirectional gate weight, can accurately extract nodule boundary key diagnostic features, improve the defects of low contrast of ultrasound image, multi-modal information fusion imbalance, improve the accuracy of nodule benign and malignant identification.

This invention discloses a wireless handheld thyroid ultrasound artificial intelligence screening system and method. The system is integrated into a single handheld casing and includes an ultrasound probe, an imaging processing unit, a resource monitoring unit, a quality assessment and coverage estimation unit, a multi-level artificial intelligence inference unit, a screening decision and interaction unit, a wireless communication module, and a power supply module. The multi-level artificial intelligence inference unit deploys lightweight and medium-sized models locally and a high-precision model in the cloud. Each level of model outputs at least nodule candidate regions, malignancy confidence, and uncertainty indicators. The screening decision and interaction unit performs hierarchical inference, keyframe selection, and asynchronous uploading of weak network cache based on resource status and risk thresholds, enabling reliable screening and traceable final review in resource-constrained and unstable network environments.

The present invention proposes a method for predicting the risk stratification of thyroid cancer in dynamic images based on a graph convolutional network, which includes the following steps: Step 1: Use image filtering enhancement and a super-resolution network to preprocess the ultrasound images, design an algorithm based on a graph convolutional neural network structure for thyroid ultrasound image segmentation, and establish a corresponding network model for training; Step 2: Use a feature extraction method of dynamic ultrasound radiomics based on artificial intelligence technology to extract features from the dynamic video sequence, and introduce a deep learning method to fuse the dynamic ultrasound radiomics to make the extracted radiomics features more abundant; Step 3: Use a multi-branch neural network model to comprehensively integrate various different modalities of data, and calculate multi-modal biomarkers by mining the complementary information of different modalities of data, so as to establish a risk stratification prediction model of thyroid cancer that can guide clinical decisions; The present invention can improve the accuracy and precision of thyroid cancer risk stratification.

The present invention discloses an automatic recognition method, device, terminal and storage medium for thyroid ultrasound images. By simultaneously extracting the feature data of the transverse view and the longitudinal view, and using a neural network regression model to determine the respective weights of the transverse view and the longitudinal view according to the feature data, the recognition results of the transverse view and the longitudinal view are weighted and fused to obtain the final recognition result. Compared with the prior art, the feature information extracted by the present invention is richer, and it can comprehensively focus on the ultrasound image recognition results of the two views, with a lower dependence on the clarity of the ultrasound image, and can automatically recognize the lesion area in the ultrasound image.

This paper proposes a semi-supervised thyroid ultrasound image segmentation method based on discrete wavelet transform and edge features. The method includes five steps: 1) image preprocessing; 2) feature extraction based on convolution and wavelet transform; 3) construction of a semi-supervised deep learning model based on Mean-Teacher; 4) edge feature evaluation based on convexity; and 5) edge feature evaluation based on active contours. The present invention uses wavelet transform to suppress speckle noise in ultrasound images, addressing the issue of speckle noise in thyroid ultrasound images. Convexity loss function and active contour loss function are used to evaluate edge features for semi-supervised semantic segmentation, enabling high-precision segmentation of thyroid organs from ultrasound images.

The utility model discloses a scanning mechanism and equipment for ultrasonic scanning of thyroid gland, and aims to solve the problems that the conventional auxiliary scanning equipment lacks reliable physical limit, is low in sensor integration level and is inflexible to adjust. The scanning mechanism comprises a man-machine holding assembly, a driving module, a probe transducer assembly and a limiting adjusting assembly which are integrally arranged; the probe transducer assembly comprises a mounting base, an ultrasonic detection piece and a scanning auxiliary element, the mounting base and an adjusting base of the limiting adjusting assembly are each provided with a distance measuring element, and the parallel state of the ultrasonic detection piece and a scanned object is judged through the parameter difference value of the distance measuring elements; the adjusting seat can be locked in a sliding mode along the guiding piece, and a non-contact limiting structure is formed by a laser indicating piece, a magnetic induction trigger and a magnetic element. The device is compact in structure, adapts to patients with different neck sizes, avoids mechanical collision risks, improves scanning accuracy and consistency, and is high in practicability.