65 results about "Image guidance" patented technology

Disclosed are approaches that may provide image-guidance to interventionalists by providing true 3D visualization and quantitative feedback in real-time. A guidance system may allow a physician to manipulate a medical device and see a 3D rendering with quantitative feedback floating in mixed reality, next to standard monitors. Image tracking may detect and co-register the medical device's 3D position using, for example, bi-plane C-arm X-ray fluoroscopy and provide a 3D trajectory as quantitative feedback. Patterns in a fluoroscopic image may be used to accurately determine an object's z-position from a single angle projection.

The invention provides a text-enhanced cross-modal pedestrian retrieval method based on image guidance, and belongs to the field of artificial intelligence and multi-modal perception.The method comprises the steps that training images and texts are input into an image encoder and a text encoder respectively; obtaining a global feature representation of the image features, and mapping the global feature representation into a pseudo token; extracting pseudo text features; extracting pseudo token embedding, and screening the pseudo token embedding; the optimal pseudo token is embedded and interacted with the learnable query to obtain a knowledge-based query; fusing the knowledge-based query and the text features to obtain enhanced text features; aligning the enhanced text features with the image features to obtain a trained image and a text encoder; respectively inputting a pedestrian image and text description into the trained image and the text encoder, fusing knowledge-based query and original text features, and calculating cosine similarity expressed by the enhanced text features and image features; the invention further provides a retrieval system. The problems of low cross-modal matching precision and insufficient fine granularity alignment are solved.

The invention relates to the technical field of image guidance positioning, and provides a radiotherapy positioning system and a positioning structure based on image guidance, which are characterized in that a comprehensive, accurate and adaptive radiotherapy positioning system is constructed, the positioning structure is monitored and analyzed in real time from multi-modal image data fusion in combination with physiological features of target tissues, and the positioning structure is used for positioning the target tissues. In the radiotherapy process, parameters of the treatment bed and the positioning structure can be dynamically and accurately adjusted according to the actual position and state change of the target tissue, the integration mode effectively avoids the problem of positioning deviation caused by the fact that a traditional positioning method is single and lacks real-time dynamic adjustment, and the positioning accuracy is improved. The overall precision and reliability of radiotherapy positioning are greatly improved, and a solid guarantee is provided for accurate action of radiotherapy on target tissues.

The invention relates to the technical field of medical robots and image guidance, and discloses a target area operation method, device, equipment and medium based on a perceptual image, and the method comprises the steps: obtaining the perceptual image data of a target area, recognizing the boundary of the target area based on the perceptual image data, and planning and generating an operation path according to the boundary of the target area, and controlling the execution component to execute operation along the operation path, acquiring a contact feedback signal of the operation tool in the execution process, adjusting the operation state of the execution component, detecting interference information of the execution component in real time, dynamically correcting the operation path according to a detection result, and realizing autonomous perception and operation control of the target area. According to the method, a closed-loop autonomous control mechanism from sensing to operation is constructed by fusing sensing image recognition, path planning, execution control and real-time feedback correction processes, and accurate recognition and path adaptive adjustment of a target area in a dynamic environment are realized.

The application discloses a single-photon lidar point cloud denoising method based on multi-mode guidance and related equipment, and belongs to the field of lidar signal processing and computer vision. The three-dimensional point cloud of the single-photon lidar, the infrared image and the visible light image are synchronously collected; the infrared image and the visible light image are extracted and fused in parallel to generate multi-mode image guidance features; after the features of the point cloud are extracted, the features are projected onto the image plane to form spatially aligned alignment point cloud feature maps; the two features are interacted through bidirectional cross-attention calculation, the obtained features and the original features are aggregated, and then integrated through a multilayer perception machine to obtain multi-modal joint features; the joint features are decoded to output a denoising weight map and a signal enhancement map; the original point cloud is projected onto the image plane, noise points are filtered out by using the denoising weight map, and the reflection intensity of the reserved points is enhanced by using the signal enhancement map to generate a denoised three-dimensional image. The application realizes accurate noise filtering and effective signal enhancement, and improves the quality of the point cloud.

The invention relates to the technical field of medical equipment and image guidance, and discloses a high-precision image guidance treatment supporting system, method and device, and the system comprises an image guidance module, a space distance measurement module, an artificial intelligence processing module, a closed-loop feedback control module, and a motor driving module. The method comprises the following steps: collecting coordinates of a tumor area and a treatment bed deformation model, combining real-time pose information, utilizing artificial intelligence to generate a pose compensation parameter, outputting a six-degree-of-freedom compensation control instruction, and driving a motor to realize accurate adjustment of the position and the pose of the treatment bed. Real-time accurate adjustment of the treatment bed under six degrees of freedom can be achieved, multi-source data fusion and an artificial intelligence compensation mechanism are combined, the positioning accuracy and the alignment stability of a tumor area are effectively improved, position errors caused by manual operation or deformation of the treatment bed are reduced, and the accuracy of the treatment bed is improved. And the safety, the accuracy and the clinical working efficiency of radiotherapy are remarkably improved.

The invention provides a bimodal integrated device for particle radiotherapy. The bimodal integrated device comprises a control system, a sitting and standing posture system, a bimodal imaging system and an image processing system, the sitting and standing posture system is used for bearing and driving a to-be-detected object to rotate; the bimodal imaging system comprises at least two scanning units composed of ray source assemblies and detection assemblies to obtain image data, the image data comprises first data and second data, the first data comprises two-dimensional image data of a to-be-detected object, and the second data comprises three-dimensional image data of the to-be-detected object rotating to a preset angle; the bimodal imaging system outputs acquired image data to the image processing system; and the image processing system is used for generating medical images for monitoring and registration according to the image data, and has the advantages of being suitable for image guidance and real-time monitoring of sitting and standing radiotherapy while giving consideration to the three-dimensional anatomical precision and the two-dimensional instantaneous speed.

The hybrid stimulation system is an electrical stimulation system serves to delivered an electrical stimulation impulse to the heart (human or animal heart) , using a combination of internal (intravascular) and external (body surface) electrodes, the hybrid electrical stimulation system can be used for pacing of the heart during slow heart beat (bradycardia), or shocking the heart during fast heart beat (Tachycardia) , or to terminate fast abnormal heart beat (tachy-arrhythmia) by means of override pacing (Anti-tachycardia pacing). This hybrid system can be used and introduced into the body without the need for imaging guidance such as fluoroscopy or echocardiography to insert the internal component, and does not require direct contact between the internal pacing wire and the myocardium (internal heart surface).

In certain embodiments, an ophthalmic system and computer-implemented method for automatically initializing an image guided surgery are described. The initialization includes monitoring a scene using multiple images captured by a first imaging device. An eye of a user is detected within a first image of the multiple images. In response to detecting the eye of the user, a registration procedure is initiated with the first image and a reference image of the eye of the user to generate a set of transformation information. A set of overlay content is generated based on the set of transformation information. The set of overlay content includes a transformed first image or a transformed reference image. Overlay content is presented onto the scene via a second imaging device.

The invention discloses a pure visual navigation method for a legged robot fusing image guidance and image understanding. An image guiding part of the method adopts a target navigation planning algorithm based on a Transform architecture, outputs a relative navigation target point with a target image as guidance, and guides a robot to complete key path selection; in the image understanding part, a lightweight semantic segmentation and obstacle avoidance algorithm based on an improved Yov5 model is adopted, a passable area is obtained based on a semantic segmentation result and a preset passable semantic table, coordinates of obstacle avoidance target points are distributed and output at the position of the passable area in a visual angle, and a robot completes path following and obstacle avoidance tasks by means of semantic understanding. According to the method disclosed by the invention, the robot can perform a navigation task in a complex environment including an outdoor environment by only depending on a small number of target images, so that the generalization problem of an original pure end-to-end vision algorithm is effectively solved, and a long-distance navigation task in a complex scene is realized.

The present application relates to a new use of fluorocarbon phase transition microparticles as a therapeutic ablation agent for mechanically damaging or ablating diseased tissue. When fluorocarbon phase transition microparticles are in contact with diseased tissue, under the excitation of low-frequency focused ultrasound, gas-liquid phase transition (i.e. vaporization) and ultrasonic cavitation resonance of vaporized microbubbles occur, followed by controlled intensity cavitation and mechanical damage of local tissue, thereby producing an ablation therapeutic effect on diseased tissue. Vaporized fluorocarbon phase transition microbubbles become ideal exogenous cavitation nuclei, which can significantly reduce the cavitation threshold and induce enhanced inertial cavitation effects. This method has the characteristics of short treatment time, low required ultrasonic pressure and sound intensity, minimal damage to tissues outside the target area, easy operation, etc., improving the targeting and safety of treatment. Although this treatment method requires image guidance, it does not require very precise focusing, reducing the difficulty of operation, and has application prospects in multiple clinical treatment fields such as prostate hyperplasia and tumor immunotherapy.

The invention provides an ultrasonic image calibration device and an acupuncture path tracking method, and relates to the field of medical image guiding technologies and minimally invasive surgical navigation systems. The device is characterized in that a first optical passive part is mounted on an ultrasonic probe; a first detection plane determined by the first optical passive part is parallel to the scanning surface of the ultrasonic probe; the support frame is mounted on the ultrasonic probe; the second optical passive part is mounted on the support frame; a second detection plane determined by the second optical passive part is parallel to the scanning surface of the ultrasonic probe; the characteristic piece is arranged on the second optical passive piece and is positioned in the scanning surface of the ultrasonic probe; and the processing assembly determines a second conversion matrix between an ultrasonic probe coordinate system where the first detection plane is located and an ultrasonic image coordinate system of the ultrasonic image collected by the ultrasonic probe to calibrate the ultrasonic image.

The invention discloses a radionuclide-labeled isoindole-piperidinedione derivative and application thereof, and the structural formula of the radionuclide-labeled isoindole-piperidinedione derivative is shown in the specification. E3 ubiquitin ligase key protein CRBN is used as a new target for nuclear medicine molecular imaging research; dynamic expression of CRBN in a tumor microenvironment is accurately described by constructing a targeted molecular probe with an isoindole-piperidinedione parent nucleus structure, imaging guidance is provided for clinically and accurately screening benefited people and predicting the therapeutic effect of targeted CRBN, and imaging examples are also provided for researching dynamic expression of other key proteins in a ubiquitination system.

The disclosure provides a breast dynamic optical tomography system based on fluorescence image guidance, comprising: a first lifting platform for adjusting the height of a light source module and a detection module; a second lifting platform for controlling the movement of a pressing plate; one side of the pressing plate is fixed on the second lifting platform, and the other side is used for pressing the tissue to be detected; the light source module generates detection light; the detection module samples the surface emission light of the detection light after passing through the tissue to be detected to obtain each wavelength emission light image; a host module processes the surface fluorescence image by using a fluorescence diffuse optical tomography method to obtain a segmentation image; the time sequence of the surface diffuse light image is demodulated to obtain the time sequence of the surface diffuse light image corresponding to each wavelength; and a diffuse optical tomography method is used to process the segmentation image and the time sequence of the surface diffuse light image corresponding to each wavelength to obtain the time sequence of the three-dimensional image of the absorption coefficient change corresponding to each wavelength.

This application discloses a method for guiding orthopedic rehabilitation training movements using images, comprising: receiving a rehabilitation video stream sent by a terminal device, decoding and processing it according to a preset time sequence, and extracting a continuous sequence of original image frames; inputting the original image frame sequence into a preset posture detection network for inference calculation, and outputting a three-dimensional skeletal coordinate sequence corresponding to the trainee; retrieving a standard movement template matching the current rehabilitation project, and inputting the three-dimensional skeletal coordinate sequence and the standard movement template into a dynamic time warping module for time axis alignment processing to generate a warped coordinate sequence. This invention overcomes the pain points of home monocular vision through high-precision anti-interference object recognition and spatiotemporal reconstruction, strengthens the medical safety defense line by integrating compensatory discrimination and dynamic fatigue degradation mechanisms, and achieves accurate, safe and immersive out-of-hospital intelligent orthopedic rehabilitation guidance with audiovisual synchronized AR multimodal feedback.

The utility model relates to the technical field of ultrasonic treatment equipment, in particular to an automatic treatment device with image guidance, which is characterized in that a host is arranged on one side of a control console, a follow-up arm is mounted on the control console, a first mounting hole is formed in the working end of the follow-up arm, a colposcope is mounted in the first mounting hole, a treatment arm is mounted at the working end of the follow-up arm, and the treatment arm is mounted on the control console. A second mounting hole and a third mounting hole are formed in the treatment arm, a treatment gun is mounted in the second mounting hole, a laser head is mounted in the third mounting hole, and the laser head, the treatment gun and the colposcope are all connected with the console. A colposcope image corresponds to coordinate information positioned by a laser head, so that accurate positioning and uniform movement of a treatment position are realized, non-uniform speed and inaccurate position of a treatment gun which is manually moved are avoided, and the treatment efficiency is improved; visualization of a real-time path and an ultrasonic dose when the treatment gun works is achieved, the condition of the treatment process is known in real time, the ultrasonic treatment dose is accurately mastered, the treatment position is accurately positioned, and the treatment mode is optimized.

The application provides a social media irony semantic recognition method, system, storage medium and electronic equipment, and relates to the field of irony semantic recognition.In the application, social media multi-modal data is first integrated, and then irony-specific features are activated based on a pre-constructed hierarchical irony semantic library;next, text guidance features, image guidance features, numerical guidance features and irony-specific features are spliced to obtain a global guidance vector, and the global guidance vector is used as an attention query matrix to obtain bidirectional interaction features between the text and the image by using bidirectional attention, to obtain irony perception features by using irony category attention, and to obtain multi-modal fusion features by using additive attention, and a fusion intermediate vector is obtained after splicing;finally, it is identified whether the social media multi-modal data is irony expression.The application realizes the collaborative work of multi-attention mechanism through the cascaded transmission of the global guidance vector combined with the irony-specific features, and significantly improves the recognition ability for complex social media irony scenarios.

A slip arc, which comprises a rotor and a stator with open circumferences, is provided for continuous signal and power transmission during unidirectional rotation. Signal and power are transmitted via arc channels that are disposed on the base of the rotor. Continuous signal and power transmission is achieved by introducing multiple contact groups such that arc channels are connected to at least one of the contact groups at any rotation angle of the rotor. X-ray imaging components can be installed on the rotor of the slip arc to form an x-ray imaging assembly. The x-ray imaging assembly can be further used to develop an x-ray imaging device for nondestructive testing or image guidance and assessment in medical applications.

The present application relates to the technical field of medical devices, in particular to a puncture guiding method, device and equipment based on image processing and a storage medium, the method comprising: acquiring a two-dimensional perspective image including a target tissue region in real time, the target tissue region including a portal vein region and a diaphragm region; identifying the diaphragm region in the two-dimensional perspective image to obtain first edge position information of the top of the diaphragm region; acquiring three-dimensional image information of the portal vein region and second edge position information of the top of the diaphragm region, the three-dimensional image information and the second edge position information being determined based on a three-dimensional reconstruction image including the target tissue region; superimposing the three-dimensional image information and the second edge position information into the two-dimensional perspective image to obtain a superimposed image; and displaying the superimposed image to guide puncture. The method can provide intraoperative image guidance for TIPS to improve puncture accuracy and shorten puncture time.

The invention relates to the technical field of radiotherapy systems, in particular to a three-dimensional conformal radiotherapy system which comprises a patient treatment unit, a treatment planning unit, a dose monitoring unit, an image guiding unit and a display unit. The patient treatment unit is used for fixing limbs of a patient, acquiring three-dimensional image data of shape, size and position information of a tumor of the patient, irradiating tumor tissues through high-energy rays, destroying cancer cell DNA (Deoxyribose Nucleic Acid) and healing the patient; the treatment planning unit formulates a personalized radiotherapy plan according to the image data, and simulates and optimizes a projection path, dose distribution and a treatment plan of radioactive rays by using a computer; the three-dimensional conformal radiotherapy system accurately controls the distribution of rays, realizes three-dimensional conformal radiotherapy, furthest concentrates a radiation dose agent into a human tumor area, kills tumor cells, reduces or prevents normal tissues and organs around a human tumor from being damaged by unnecessary irradiation, and reduces the pain of a patient and the risk of complications.

The invention relates to the technical field of laser welding, and discloses a laser welding seam tracking and quality real-time detection system and method based on OCT image guidance. According to the method, through system calibration and offline learning, a coordinate mapping and feature database is established; during welding, the coaxial OCT is used for synchronously scanning a front groove and a rear molten pool area; tracking and correcting a welding path in real time based on the front three-dimensional point cloud; meanwhile, a dynamic feature sequence of the molten pool is extracted and analyzed; inputting the features into a pre-training machine learning model, and judging quality and predicting defects in real time; according to the judgment result, parameters such as laser power and welding speed are adjusted in a self-adaptive mode, and closed-loop control is formed; and full-process data is fed back to optimize the model. According to the invention, synchronous closed-loop control of groove tracking and internal quality detection is realized, and the welding precision and the quality reliability are improved.

This invention discloses a real-time imaging dynamic navigation system for interventional surgery of breast tumors, comprising an acousto-optic scanning device, a Redis client, a Redis server, a database, a modeling platform, a Three.js dynamic driving engine, and a display terminal. The acousto-optic scanning device is positioned above the breast tumor for non-contact scanning and data acquisition during surgery. The Redis client, Redis server, and database acquire, distribute, and store the acquired data, respectively. The modeling platform constructs a model from the received data. The Three.js dynamic driving engine, consisting of a breast tumor data input terminal, an initial data driving unit, an incremental data driving unit, a rendering unit, and a dynamic image output terminal, further processes the model in a data-driven manner. This invention's dynamic navigation system achieves real-time data acquisition, transmission, and processing, generating intuitive and dynamic navigation images that provide high-quality image guidance for surgery, improving the success rate and accuracy of the procedure.

This invention provides a novel medical device for performing precise urological procedures, specifically focusing on urological stone removal. The illustrative Stone Removal Robot leverages multiple subsystems to autonomously remove stones while using real-time image guidance for precise targeting and minimal collateral damage. This system is particularly suited for use in urology, though its applications can extend to other surgical fields. The key benefit of this invention lies in its ability to provide enhanced accuracy, reducing the potential for human error, while integrating multiple lithotripsy methods termed herein, Method1, Method2, Method3, which may incorporate cooling to protect surrounding tissues. The system can be adapted for autonomous operation.

The invention provides a fine semantic embedding-based multi-type audio guidance unmanned aerial vehicle remote sensing image segmentation method and system, and relates to the crossing field of remote sensing image intelligent processing and multi-mode artificial intelligence. Constructing a multi-type audio remote sensing image guidance segmentation data set; constructing a multi-type audio guidance remote sensing image segmentation model based on fine semantic embedding, wherein the model comprises a remote sensing image feature coding module, an audio feature coding module, a fine semantic embedding module, an audio semantic request module and a mask feature decoding module; and training the multi-type audio guidance remote sensing image segmentation model through the multi-type audio remote sensing image guidance segmentation data set until a training completion condition is satisfied. According to the segmentation method, the intelligent interaction processing capability of the remote sensing image is improved, and the coincidence degree of the remote sensing image and the audio semantics is improved through complete modeling and fine semantics embedding of the audio semantics.

The utility model discloses a data collection and fault prediction test system applied to an image seeker. The data collection and fault prediction test system comprises a high-precision two-axis turntable, a digital power meter, a direct-current power supply, a display, a target simulation unit, a control and data collection platform and a data collection circuit board. The test system provided by the utility model solves the problems that the infrared / visible light image platform seeker has a large number of parts and a complex structure, has high requirements on professional ability of inspection personnel during inspection, and is slow in fault positioning due to judgment mostly depending on artificial experience.

Compositions and methods are presented to improve the efficacy and reduce the side-effects of radiological cancer treatments. Nanoparticles of cerium oxide are dispersed within a biodegradable polymer matrix to form a biomaterial that can be implanted in a patient at a selected location and remain at that location for a period of time encompassing all or part of a radiation therapy course of treatment. Among other functions of the implanted biomaterial, it may act as a spacer such that organs at risk are moved away from tissues targeted by the radiation therapy. Another function of the implanted biomaterial is as a fiducial marker. The use of cerium oxide will assist in achieving both the fiducial marker and spacer functions, particularly in view of the catalytic activity of cerium oxide in reducing a number of reactive oxygen species to non-reactive compounds The composition may permit higher doses of radiation and improved survival rates resulting therefrom.

The invention discloses a non-paired low-light real image enhancement method based on multi-mode guidance. The method comprises the following steps: 1, acquiring a training set image; 2, constructing a multi-modal guide cyclic diffusion generative adversarial network; 3, extracting features of the low-light real image and the normal-light image; 4, establishing a total loss function in the process of performing feature extraction on the low-light real image and the normal light image; 5, training the multi-modal guided cyclic diffusion generative adversarial network based on the total loss function; and 6, carrying out enhancement processing on a single low-light image by utilizing the trained multi-mode guide cyclic diffusion generative adversarial network. The method provided by the invention is simple in steps, and the non-paired low-light real image and normal light image realize multi-modal guidance to train the network through illumination perception image guidance and text perception guidance, so that the intensified light image output by the trained multi-modal guidance cyclic diffusion generative adversarial network has better visual quality; and the illumination rationality and detail textures are improved.

A method and system for guiding renal stone removal. The method includes steps for facilitating or guiding three stages of the intervention: renal access, stone removal, and a stone-free check. This is facilitated by a method which includes three stages: an intra-operative image guidance phase for obtaining CT-based imagery of the renal area; a renal access guidance phase in which the aforementioned CT-based imagery is used to generate intervention guidance imagery to guide renal access, and a stone-free check phase in which further intra-operative CT images are acquired to check the stone-free status of the patient.

This invention discloses a visually controllable catheter endoscope, comprising an insertion tube module, an image acquisition module, an illumination module, a handle unit, and a display unit. The insertion tube module includes a tube body and a control mechanism for controlling the bending direction of the distal end of the tube body. The image acquisition module, located at the distal end of the tube body, is used to acquire real-time images of the urethra. The illumination module, located at the distal end of the tube body and surrounding the image acquisition module, provides illumination for the image acquisition module. The handle unit is connected to the proximal end of the insertion tube module. The display unit is located on the handle unit and displays the images transmitted by the image acquisition module. This invention provides a visually controllable catheter endoscope and its operating method. This device and operating method can provide real-time image guidance and precise directional control during catheter insertion, thereby avoiding tissue damage and complications caused by blind insertion, improving the success rate of the operation and patient comfort.