143 results about "Ultrasonography" patented technology

The invention provides an index construction method for a medical ultrasonic database, and relates to the technical field of ultrasonic data processing, and the method comprises the steps: reading a multi-frame image sequence from a DICOM ultrasonic database, and generating a diagnosis intention vector for each frame; analyzing the diagnosis report, and segmenting the report into a plurality of segments; lesion detection and segmentation are performed on each frame of image to obtain lesion information, and a cross-frame aggregation strategy is adopted to identify a unified lesion object; extracting a feature vector of each focus object to obtain a focus object feature vector; establishing an alignment mapping between the focus object and the report fragment by adopting triple constraints, and generating a focus report mapping table; and constructing a multi-layer index structure, and storing the focus report mapping table and the multi-layer index structure in parallel. According to the method, a multi-layer index structure comprising a metadata index, a text index, a focus object vector index and a cross-modal embedding index is formed, so that efficient organization and focus-level accurate retrieval of medical ultrasonic data are realized.

The invention belongs to the technical field of biomedical materials, and particularly relates to preparation of a hydrogel ultrasonic coupling patch for long-term stable continuous monitoring. According to the patch, an interpenetrating double-network structure system is formed by an alginate component and a polyacrylic acid component through intermolecular interaction, and the patch has excellent adhesion performance and mechanical performance. Compared with the prior art, by optimizing the components and the preparation process, the obtained hydrogel patch has the following advantages that the excellent acoustic impedance matching characteristic is achieved, and high-fidelity transmission of ultrasonic signals is ensured; the tissue adhesion is strong, and long-term stable attachment can be realized; good mechanical stability and durability are achieved, and the method is suitable for continuous monitoring application. The product effectively solves the technical problems that the traditional liquid coupling agent is easy to lose, the solid coupling patch is insufficient in adhesion and the like, and has important application value in the fields of medical ultrasonic diagnosis and long-term monitoring.

The invention belongs to the technical field of medical image segmentation, and particularly relates to a medical ultrasonic image segmentation method based on cross-domain self-adaption and boundary optimization, which comprises the following steps: constructing and training a medical ultrasonic image segmentation model based on an SAM large model, and inputting an image to be segmented into the trained medical ultrasonic image segmentation model to obtain a segmentation result; the medical ultrasonic image segmentation model comprises a cross-domain style alignment module, a multi-stage adaptive feature calibration module and a new mask decoding module; according to the method, the inter-domain difference between the natural image and the medical ultrasonic image is effectively bridged, the generalization bottleneck of a traditional normalization method is broken through, and the segmentation precision is improved.

The invention provides a comprehensive solution for a medical ultrasonic image diagnosis task, which comprises two innovative parts, namely a CAPT parameter efficient fine tuning method based on a convolution adapter and embedded prompt tuning and a model lightweight method based on evolution pruning. Aiming at double challenges of scarcity of data and difficulty in model adaptation in the field of medical ultrasonic images, on one hand, the CAPT method introduces a convolution module into a traditional adapter to enhance the fine-grained feature extraction capability by fusing adapter tuning and prompt tuning mechanisms, and dynamically generates a prompt vector embedded with attention calculation by using adapter learning context information; the adaptability and the small sample generalization ability of the Transform model in an ultrasonic image classification task are obviously improved; on the other hand, aiming at a model edge deployment requirement, designing an evolution pruning algorithm, taking DenseNet-121 as a basic framework, inheriting parent strong neuron connection by adopting an asexual reproduction mechanism, and through a channel importance evaluation method for coupling a BN layer scaling factor and a weight L1 norm and in combination with a sparse evolution strategy guided by environmental constraint, constructing a model edge deployment model. And the classification precision is maintained, and meanwhile, the model parameters and the calculated amount are greatly compressed. The two technologies respectively break through the technical bottlenecks of medical image diagnosis from two dimensions of parameter efficient fine tuning and model structured pruning, the former improves the adaptability of the model field through feature extraction optimization, and the latter balances network lightweight and performance stability by means of an evolutionary algorithm. And an innovative technical path is provided for efficient deployment of an ultrasonic image auxiliary diagnosis system in a data limited scene and an edge computing environment.

Ultrasound image devices, systems, and methods are provided. An intraluminal ultrasound imaging system, comprising a patient interface module (PIM) in communication with an intraluminal imaging device comprising an ultrasound imaging component, the PIM comprising a first reconfigurable logic block including a first plurality of logic elements interconnected by first reconfigurable interconnection elements; a configuration memory coupled to the first reconfigurable logic block; and a processing component coupled to the configuration memory, the processing component configured to detect a device attribute of the intraluminal imaging device in communication with the PIM; and load at least one of a first configuration or a second configuration to the configuration memory based on the detected device attribute to configure one or more of the first reconfigurable interconnection elements such that the first plurality of logic elements are interconnected for communication with the ultrasound imaging component.

The invention discloses a robust adaptive beam forming method based on a depth migration reconstruction network, which mainly solves the problems of signal self-cancellation and insufficient robustness of the existing beam former under non-ideal conditions, and comprises the following implementation steps of: modeling an array receiving signal; constructing real value signal covariance matrix input of the reconstruction network; designing an interference and noise covariance matrix reconstruction network based on a Unet framework; designing a guide vector estimation network based on a dual migration mechanism; real-value label construction and network generalization training are carried out; and calculating a beam forming weight vector. Under typical non-ideal conditions of random signal observation errors, coherent source local scattering errors and the like, the interference and noise covariance matrix and the expected signal guide vector can be accurately reconstructed, the signal self-cancellation phenomenon is effectively avoided, the robustness of a beam former is enhanced, and the method can be used for low-altitude target tracking, medical ultrasonic imaging and other scenes.

A medical ultrasound probe, a transducer module, and an ultrasound device. The medical ultrasound probe comprises a first transducer element (22) and a second transducer element (23), wherein the center frequencies of the first transducer element (22) and the second transducer element (23) are different from each other, such that the first transducer element (22) and the second transducer element (23) can detect different depths of an examination region. By means of a combination of the first transducer element (22) and the second transducer element (23), different depths of the same examination region can be probed to obtain images from tissues at different depths, allowing for a more comprehensive examination of organs to assist physicians in diagnosis.

The invention relates to the technical field of computer-aided diagnosis, and discloses a block classification aided diagnosis system based on a self-prompt mechanism, which comprises the following steps: dividing a medical ultrasonic image into a plurality of image blocks, carrying out convolution and flattening processing to obtain a feature vector, extracting a preliminary global feature through a plurality of visual conversion blocks, and carrying out self-prompt on the image blocks; a fusion feature is obtained through a plurality of prompt attention conversion blocks, a self-prompt mechanism is introduced into the prompt attention conversion blocks, a learnable space prompt vector and a channel prompt matrix are introduced into the self-prompt mechanism, and a space mask is generated by calculating cosine similarity of the space prompt vector and a preliminary global feature. After spatial screening operation is carried out on the initial global features, channel guiding operation is applied through a channel prompt matrix; and performing weighted adjustment on the fused features to obtain final features, and obtaining benign and malignant classification results through a classification head. The feature modeling capability of the local fine-grained discriminative region in the image can be effectively improved, and the auxiliary diagnosis accuracy is improved.

The invention relates to the technical field of medical ultrasonic detection, and discloses a medical ultrasonic detection probe posture adjusting method and system. Through an attitude sensor integrating an inertial measurement unit and an optical sensor, high-precision fusion attitude information is generated by using a sensor fusion algorithm. The system calculates attitude deviation based on a preset target attitude model, and drives the adjusting mechanism to automatically correct the probe attitude through a proportional-integral-derivative control algorithm. And a dynamic weighting function and an ultrasonic image feedback mechanism are introduced, so that accurate control of deviation quantification and adaptive attitude calibration are realized. The problems that a traditional method depends on manual adjustment and is low in precision are solved, the ultrasonic image quality and diagnosis efficiency are remarkably improved, and the biomedical engineering industry is promoted to develop towards the intelligent and precise direction.

An ultrasonic transducer probe holder suitable for holding an ultrasonic transducer probe of a medical ultrasound system to hold or secure the probe in place against a patent as an ultrasound technician releases the probe may include a grip portion and a skirt portion. The grip portion may be configured for deployment on the ultrasonic transducer probe. The grip portion may provide a comfortable and secure grip for the ultrasound technician as the technician applies the ultrasonic transducer probe against the skin of the patient. The ultrasonic transducer probe with the grip portion thereon may be insertable in the skirt portion of the ultrasonic transducer probe holder. The skirt portion may be configured to hold or support the ultrasonic transducer probe in an upward-standing position while forming a vacuum seal against the skin of the patient. A stand assembly may be configured for mounting on a bed, table, or other support on which the patient reclines. The stand assembly may be configured to hold or support the ultrasonic transducer probe holder as the holder remains deployed on the ultrasonic transducer probe. Accordingly, the stand assembly may maintain the ultrasonic transducer probe in place against the patient's skin to reduce or eliminate the manual pressure required for the technician to maintain the ultrasonic transducer probe in place during an echocardiography or other ultrasound procedure. The ultrasonic transducer probe holder may prevent carpel tunnel syndrome and other repetitive stress injuries in the hand of the technician.

The invention provides an ultrasonic image segmentation method and device, electronic equipment and a storage medium, and the method comprises the steps: constructing an image segmentation model which comprises a visual encoder module, a text encoder module and an affine transformation guide module; obtaining a to-be-segmented medical ultrasonic image and text auxiliary information representing medical priori knowledge corresponding to the medical ultrasonic image; the medical ultrasonic image is input into the image segmentation model, a segmentation mask image of the medical ultrasonic image is obtained, and the segmentation mask image is used for segmenting different organs in the medical ultrasonic image into different areas; wherein the visual encoder module is used for extracting multi-scale visual features of a medical ultrasonic image, the text encoder module is used for extracting semantic features of text auxiliary information, and the affine transformation guidance module is used for fusing the multi-scale visual features and the semantic features through affine transformation to generate a segmented mask image. According to the invention, accurate recognition and segmentation of the ultrasonic image can be realized.

This invention provides a medical ultrasound image recognition method based on generator domain alignment, relating to the field of image classification technology. The method includes: creating labeled generated medical ultrasound image samples for fine-tuning using a conditional diffusion model, where labels characterize the category corresponding to the generated medical ultrasound image sample; aligning each labeled generated medical ultrasound image sample to the generator domain using an unconditional diffusion model of the generator domain, obtaining a generator domain medical ultrasound image set; fine-tuning the source domain model using the generator domain medical ultrasound image set, obtaining a generator domain model; aligning a target medical ultrasound image to the generator domain using the unconditional diffusion model of the generator domain, obtaining a generator domain target medical ultrasound image; and inputting the generator domain target medical ultrasound image into the generator domain model to obtain a first predicted classification result for the target medical ultrasound image. This transforms a cross-domain task into an intra-domain prediction task, aligning both the source domain model and the target data to the same generator domain, thereby achieving accurate predicted classification results.

The article relating to the present design is a stand that allows the entire electronic device, such as a medical ultrasound probe, to be displayed upright at a slight incline by inserting the grip portion of the electronic device, which is held in one hand, into a hole. The grip portion of the electronic device is approximately 70 mm to 45 mm in width and approximately 25 mm in thickness, and is used in a manner that minimizes gaps when inserted.

This application relates to the field of medical ultrasound measurement technology, specifically providing a method for in-situ measurement of skull thickness and sound velocity using ultrasound. The method includes: acquiring reflected echo data from N transmitting array elements, wherein the N transmitting array elements sequentially transmit ultrasound waves to the location to be measured on the skull, and array elements centrally symmetrical to the transmitting array elements receive the reflected echoes of the ultrasound waves; arranging the reflected echo data from the N transmitting array elements together to form a wave train diagram of the N transmitting array elements; extracting the sound pressure amplitude values ​​corresponding to the normal incident reflection time from the wave train diagram, and superimposing the extracted sound pressure amplitude values ​​to form a superimposed amplitude spectrum, with the maximum superimposed sound pressure amplitude value corresponding to the wave train diagram being the equivalent matching velocity; and calculating the sound velocity and thickness at the location to be measured on the skull based on the equivalent matching velocities at the maximum superimposed sound pressure amplitude values ​​and the normal incident reflection time. This method can accurately measure the sound velocity and thickness of the skull in situ.

The invention belongs to the technical field of medical ultrasonic diagnosis auxiliary equipment, and discloses an electric right heart acoustic radiography foaming device which comprises a device body, the device body comprises a base, a mounting plate is fixedly arranged on the rear side of the base, a driving assembly is arranged on the front side of the mounting plate, and the driving assembly comprises fixing frames fixed to the upper side and the right side of the mounting plate; a stepping motor is fixedly arranged at the top of the fixing frame, a ball screw is fixedly arranged at the tail end of a main shaft of the stepping motor, a sliding block is spirally arranged on the outer side of the ball screw in a sleeving mode, and a connecting rod is fixedly arranged at the bottom of the sliding block, so that accurate controllability of power transmission and visual adjustment of parameters in the contrast agent injection process are achieved; specifically, key parameters such as injection speed and dosage can be accurately set through the operation panel, a traditional manual injection mode is replaced, and the stability of the foaming effect of the contrast agent is guaranteed.

This embodiment relates to an intelligent medical ultrasound image processing method and system. The target's output alternating voltage waveform is determined by invoking the cycle length and duty cycle of output PWM data. By inputting the target's output alternating voltage waveform into the steady-state function of a MOS transistor assembly, the induced electric field applied to the piezoelectric material can be determined. The piezoelectric material emits ultrasonic waves, which contact the target object, generating an abnormal wave. This abnormal wave, acting as a mechanical wave in the environment, can superimpose with the output mechanical wave to form an echo. The output mechanical wave and the received superimposed echo are analyzed. The echo data analysis identifies the abnormal wave, which is a characteristic echo. An ultrasound image is generated based on the characteristic echo-to-image function. The steady-state function of the MOS transistor assembly is used to analyze the induced electric field deformation during the startup and steady-state processes of the field-effect transistor, thereby reducing the blurriness of the ultrasound image.

A portable ultrasound imaging system includes a probe and a personal computer. The personal computer is connected to the probe by way of a THUNDERBOLT I / O interface. The probe includes a transducer that alternately transmits positive and negative ultrasound pulses to a target being imaged, which is a human body. Echoes of the ultrasound pulses reflected from internal structures of the human body are sampled from the transducer, digitized into echo data, and streamed to the personal computer over the THUNDERBOLT I / O interface. In the personal computer, scanlines are generated from the echo data. Overlapping scanlines are coherently compounded and positioned together to form an ultrasound image.

The invention discloses a medical ultrasonic examination system and method.The medical ultrasonic examination system comprises a base, a bed body movably installed on the base and an air bag assembly arranged on the bed body in a matched mode; the air bag assembly comprises a plurality of first air bags arranged in the length direction of the bed body, the first air bags can be driven to be inflated or deflated to be shrunk, and the first air bags can be driven to move in the length direction of the bed body; when the first air bags are driven to be inflated and expanded, the multiple first air bags jointly wrap and restrain a subject lying on the bed body on the back; when at least part of the first air bag is driven to move in the length direction of the bed body and / or deflated and contracted, a target detection part of a detected person on the bed body can be exposed. Therefore, the posture of the detected person can be automatically adjusted, the target detection part can be automatically exposed, excellent safety is achieved, and the overall efficiency of ultrasonic detection is improved.

The invention relates to the field of image processing, and provides a medical ultrasonic image segmentation method based on geometric guidance and concept perception fusion, which is characterized in that a geometric guidance text generation module is designed, and high-quality medical text description is automatically generated according to connected component analysis and multi-dimensional geometric analysis; according to the method, text-free segmentation is converted into text-guided segmentation, the problems that high-quality text description is limited in number, difficult to manufacture and high in cost are solved, a concept-aware cross-modal fusion module is designed, multi-scale space alignment and medical knowledge graph modeling are utilized, the problem that cross-modal fusion is insufficient is solved, and the cross-modal fusion efficiency is improved. According to explicit modeling of medical priori knowledge, professional knowledge in the medical field is fully utilized to guide a fusion process and a segmentation decision, a self-adaptive segmentation decoding module is further provided, an optimal strategy is dynamically selected according to feature complexity, the efficiency is improved while the precision is ensured, and the method is suitable for large-scale popularization and application. According to the invention, the precision and efficiency of medical ultrasonic image segmentation are improved.

This invention relates to the field of AI analysis technology for medical ultrasound images, specifically to an intelligent ultrasound image analysis method and system based on artificial intelligence. The method includes: acquiring ultrasound image sequences of a target patient and performing standardized preprocessing; extracting deep features through an anatomical structure recognition network to generate an anatomical structure description containing boundary contour coordinate sequences, tissue type classification identifiers, and spatial location depth information; using a lesion feature discrimination model to perform multi-dimensional feature fusion analysis on the three types of information to obtain preliminary lesion localization and attribute descriptions; then verifying spatiotemporal continuity based on adjacent frames of the image sequence to check the consistency of lesion evolution and generate a verification report; comparing the report with a medical knowledge base template to output an auxiliary diagnostic conclusion with diagnostic opinions and confidence ratings. This invention can enrich the dimensions of anatomical structure representation, improve the accuracy of lesion discrimination, ensure the temporal consistency of analysis results, and enhance the reliability of auxiliary diagnostic conclusions.

The application relates to a medical ultrasound image dataset construction method, which comprises the following steps: acquiring an ultrasound image for labeling; training a multi-modal segmentation model based on the labeled data; acquiring a to-be-labeled ultrasound image, calculating the similarity between the to-be-labeled ultrasound image and the labeled ultrasound image to select a reference image; performing weighted average on the mask corresponding to the reference image based on the similarity to obtain a fusion mask; performing weighted fusion on the circumscribed rectangular region corresponding to the mask of the reference image based on the similarity to obtain a bounding box prompt; taking the to-be-labeled ultrasound image, the corresponding fusion mask, a text label and the bounding box prompt as inputs of the multi-modal segmentation model to generate a segmentation result, adding the segmentation result to a dataset after confidence evaluation, and performing subsequent model training and reference image selection. Compared with the prior art, the application significantly reduces the workload of manual labeling, reduces the professional requirements for personnel, and greatly improves the data set labeling efficiency and the manual correction speed.

An ultrasonically transparent material used to transmit ultrasonic energy in medical ultrasound or non-destructive testing (NDT) applications.

This invention discloses a skin marking system for ultrasound imaging, a dedicated coupling agent, and its application method, relating to the field of medical ultrasound imaging auxiliary equipment and medical coupling agents. It includes a dedicated photocurable coupling agent and a specially designed ultrasound probe. The dedicated photocurable coupling agent comprises a water-soluble medical ultrasound coupling agent matrix, a photocurable hydrogel precursor, a photoinitiator, and a color developer. The specially designed ultrasound probe includes a probe housing with a built-in ultrasound transducer and a probe end face for contacting the skin. At least one ultraviolet light source is integrated in the central region of the probe end face. The relative position of the ultraviolet light source and the ultrasound transducer is spatially calibrated to establish a preset coordinate mapping relationship between the irradiation area of ​​the ultraviolet light source and the ultrasound scanning area of ​​the ultrasound transducer. This invention achieves simultaneous and precise skin marking and diagnostic guidance for ultrasound imaging through an ultrasound probe integrating an ultraviolet light source and a photocurable dedicated coupling agent.

The invention provides an ultrasonic tomography method based on virtual data reconstruction, and relates to the technical field of medical ultrasound. The method specifically comprises the steps of performing wave field inference based on frequency domain scattering wave observation data to realize virtual data reconstruction and obtain frequency domain virtual scattering wave observation data, and performing multi-scale inversion according to the frequency domain virtual scattering wave observation data to optimize a sound velocity model so as to generate ultrasonic tomography. According to the technical scheme provided by the invention, the calculation cost of wave field solution in the operation process can be effectively reduced by reducing the wave field calculation domain under the condition of ensuring the approximate traditional FWI inversion precision, the calculation complexity is reduced, and the ultrasonic tomography efficiency is improved.

The invention discloses an ultrasonic temperature measurement method and system based on multi-feature fusion, and belongs to the technical field of medical ultrasonic monitoring. The system comprises a signal acquisition module, a data processing module and an output module. The method comprises the following steps: acquiring an original radio frequency signal acquired by a monitoring probe spatially associated with a focused ultrasound treatment probe; extracting three temperature rise characteristics based on thermal strain, nonlinear sound attenuation and a Nakagami distribution statistics principle in parallel; inputting the multi-parameter characteristics into a pre-trained knowledge distillation physical information neural network model, and directly outputting a predicted temperature value; and the accumulated equivalent heat dose can be calculated according to the predicted temperature to carry out damage judgment. Through multi-parameter complementary fusion and a lightweight intelligent model, accurate and real-time non-intrusive monitoring of the temperature change of a high-temperature treatment interval greater than 50 DEG C is realized, the temperature measurement root mean square error is less than or equal to 0.8 DEG C, the single-frame processing time is less than or equal to 5ms, meanwhile, standardized thermal damage assessment is provided, and the controllability and safety of focused ultrasonic treatment are improved.

This invention relates to the field of medical information technology and scheduling, and discloses a method for scheduling appointments based on medical ultrasound department data. The method addresses the hidden conflict of existing systems neglecting the reprocessing of intracavitary probes, leading to idle examination rooms but no available probes, and the time drift caused by continuous high-load scanning by operators. This solution collects patient requests and extracts probe status, estimating the expected time to offset individual differences; reads historical probe reprocessing events to obtain the processing time including the cleaning to storage and release cycle; combines the above time parameters to extrapolate the actual available time for each candidate appointment; further, it calculates the comprehensive cost of the candidate appointments based on historical delay results, selects the scheme with the minimum cost for dynamic scheduling, and corrects the historical average based on measured data in a closed-loop manner. This invention effectively alleviates queuing deadlock and improves the accuracy of resource scheduling in ultrasound departments.

A portable ultrasound imaging system includes a probe and a personal computer. The personal computer is connected to the probe by way of a THUNDERBOLT I / O interface. The probe includes a transducer that alternately transmits positive and negative ultrasound pulses to a target being imaged, which is a human body. Echoes of the ultrasound pulses reflected from internal structures of the human body are sampled from the transducer, digitized into echo data, and streamed to the personal computer over the THUNDERBOLT I / O interface. In the personal computer, scanlines are generated from the echo data. Overlapping scanlines are coherently compounded and positioned together to form an ultrasound image.

An improved ultrasound image speckle noise reduction method based on cycle generative adversarial network, obtains GAD noise reduction image of medical ultrasound image data set; the GAD noise reduction image is scored using the proposed ENR noise reduction image quality evaluation index, and the image used as the training set and the test set is screened out;Introduce the cycle consistency structure, build the cycle generative adversarial network model CycleGAN for noise reduction, and use two sets of generators and discriminators for bidirectional training. Training is carried out using the training set, and the appropriate CycleGAN model is determined according to the checkpoint and the noise reduction result;In the online stage, the test set image is denoised by the trained CycleGAN model, and the ENR is used to evaluate the image noise reduction quality. The present application can obtain excellent noise reduction effect for medical ultrasound images contaminated by speckle noise.

The invention provides a method of remote quality assurance for ultrasound systems, the method comprising: receiving from the user at a remote location an ultrasound image of a test object; processing the received image to determine quality assurance parameters of the ultrasound system under test; providing a notification to the user at the remote location the results of the quality assurance determination. The invention provides a method by which QA fault detection of medical ultrasound can be performed in a simple and scalable manner. A system and method is provided, in which QA encompassing fault detection can be performed remotely, easily, reliably and at low cost.