7571 results about "Medical physics" patented technology

The invention discloses a multi-source heterogeneous medical data fusion and intelligent diagnosis method, and relates to the technical field of medical data processing and intelligent diagnosis, and the method comprises the specific steps: firstly, synchronously collecting medical images and clinical text data of a patient, and carrying out the correlation and integration to form a heterogeneous diagnosis data set; performing standardized feature extraction to obtain a feature set in a unified format; then constructing a parallel model, fusing features by using a cross-modal attention alignment technology, and guiding correction by means of a knowledge graph; and finally, the cross-modal diagnosis features are input into the reference model, automatic focus positioning is realized through processing, and a visual marker graph is output. Heterogeneous data of medical images and clinical texts are synchronously integrated, and the diagnosis feature reliability is improved through standardization processing, feature fusion and the like; a focus sensing mask is generated through comparison with a normal model, a multi-scale feature fusion technology is combined to realize automatic and accurate positioning of the focus, a large amount of labeled data is not needed, the process is simplified, and the diagnosis efficiency and accuracy are improved.

A system is disclosed including an ablation probe that includes an antenna, a display, and a controller in communication with the ablation probe and the display. The controller comprises a memory and is operable to receive first and second inputs indicative of an amount of time and a power level, respectively, to energize the ablation probe, retrieve, from the memory, a predicted ablation zone corresponding to the first and second inputs, display, on the display, an image representative of the ablation probe, and overlay, on the image, the predicted ablation zone, energize the ablation probe at the power level, and dynamically overlay, on the image, a progressive ablation zone based on the ablation probe being energized, wherein a size of the progressive ablation zone is retrieved from the memory based on the amount of time the ablation probe has been energized at the power level.

The invention relates to the technical field of medical instruments, and discloses a breast cancer sentinel lymph node positioning system and method, and the system comprises a data collection subsystem, a space positioning subsystem and a central processing subsystem. The method comprises the following steps: acquiring an anatomical structure image, a radioactivity counting rate and fluorescence intensity after performing primary fluorescence, radioactivity and secondary pulse type fluorescence tracer injection in sequence; establishing a global coordinate system and generating an anatomical region of interest; constructing a weighted directed topological graph based on the initial fluorescence data, and obtaining a baseline flow velocity; extracting radionuclide dynamic characteristics based on the radioactive data; a functional flow rate attenuation coefficient is calculated based on the second pulsed fluorescence data. And a multi-factor scoring model is applied, topological information, dynamic characteristics and functional flow velocity attenuation coefficients are fused, and a comprehensive score is calculated to identify the sentinel lymph node. According to the method, the lymphatic flow topological structure, nuclide dynamics and functional flow velocity information are combined, and the positioning accuracy and reliability are improved.

The invention discloses a digital slice scanning method and device, electronic equipment and a storage medium, which are used for solving the technical problem of low digital slice scanning speed. The method comprises the following steps: acquiring a to-be-scanned area of a preset tissue slice; determining a model point placement position of the to-be-scanned area, and placing a model point at the model point placement position; adjusting the model point through the macroscopic graph of the preset tissue slice to obtain an adjusted model point; generating a shortest scanning path of the adjustment model point; establishing a focal plane model by adopting all the adjustment model points; and scanning and splicing all the focal plane models according to the shortest scanning path to obtain a digital slice.

Example systems and techniques are disclosed that may determine at least one treatment strategy for a lesion. An example system may include memory configured to store clinical guidance and / or informatics for a PCI procedure and processing circuitry communicatively coupled to the memory. The processing circuitry may be configured to determine the plurality of treatment pathways. The processing circuitry may be configured to obtain angiogram imaging data of a coronary vasculature of a patient. The 2024 / 058837 processing circuitry may be configured to determine the clinical guidance and / or informatics based at least in part on the angiogram imaging data. The processing circuitry may be configured to output for display the angiogram imaging data and at least a portion of the clinical guidance and / or informatics, wherein the at least a portion of the clinical guidance and / or informatics is overlaid onto the angiogram imaging data.

The embodiment of the invention provides an image processing and computer-aided diagnosis method, electronic equipment, a storage medium and a program product, and the image processing method comprises the steps: obtaining a to-be-processed medical image which comprises the information of a plurality of target parts; performing first feature extraction on the medical image to obtain medical image features of the medical image; performing second feature extraction on the medical image features to obtain part identification information of each target part corresponding to the plurality of target parts in the medical image features; taking the part identification information of each target part as guidance, performing part feature extraction based on the medical image features, and obtaining part features of each target part; and predicting text features of the text based on the part features of the target parts and the detection results corresponding to the target parts to obtain prediction detection results of the multiple target parts. Therefore, the target part in the medical image can be accurately positioned and detected without depending on an external mask.

The invention discloses a radiotherapy laser positioning system and method, the system comprises at least three laser lamp systems, corresponding optical cameras and a computer control system, the laser lamp systems form cross cursors through two linear emitters installed in a T shape, the cross cursors are respectively arranged on the left side, the right side and the upper side of a treatment device, and a three-dimensional space positioning coordinate system is constructed. The optical camera automatically collects images of the body surface mark points of the patient and the laser cursor, and the computer control system carries out image processing, feature extraction and three-dimensional deviation calculation and feeds back deviation information to the treatment bed or the laser lamp system; and the electric control system drives the fine adjustment mechanism to perform three-degree-of-freedom accurate adjustment of translation, rotation and inclination until the mark point coincides with the cursor. According to the invention, optical automatic identification is adopted to replace manual naked eye positioning, personal errors are eliminated, rapid and automatic correction is realized, and the accuracy and efficiency of radiotherapy positioning are significantly improved.

The invention discloses a multidisciplinary intelligent consultation method for fundus diseases based on structured memory and dynamic reflection. The method comprises the following steps: acquiring medical records of patients and various examination result reports; creating a multidisciplinary consultation hall and deploying a consultation intelligent center; initializing, and synchronously storing the preliminary diagnosis data to a structured memory unit; the secretary-memory agent dynamically screens and directionally calls expert agents with matched specialities and role positioning from an agent expert pool to enter a multidisciplinary consultation hall based on the preliminary diagnosis data, and establishes interactive connection between the expert agents and a consultation intelligent center; driving each expert agent to execute a dynamic reflection algorithm, and obtaining a diagnosis reference scheme through multiple rounds of interaction debate; consultation process evaluation is carried out through a multi-dimensional quantitative evaluation mechanism; and carrying out clinical judgment on the diagnosis reference scheme based on clinical expert experience. According to the method, high efficiency, low cost and standardization of fundus disease multidisciplinary consultation can be realized, and multidisciplinary comprehensive diagnosis opinions formed by fundus diseases can be accurately obtained.

The invention relates to the technical field of medical image information processing, discloses an ICG fluorescence image and MRCP three-dimensional model registration fusion display method and system, effectively solves the problems of deep biliary tract structure blurring and form distortion caused by liver tissue scattering effect in intraoperative fluorescence imaging, uses a preoperative model as anatomical prior, and improves the accuracy of the intraoperative fluorescence imaging. A viewpoint correlation optical path depth field is constructed through reverse ray tracing, a spatial variation point spread function is generated accordingly, physical reverse recovery of scattering halo in a fluorescence image is achieved, non-specific background noise such as vascular leakage is effectively inhibited in combination with topological gravitational constraint of a central skeleton, and the detection accuracy is improved. The real pipe diameter and the center line position of the deep bile duct are accurately recovered, non-rigid registration correction is performed on the three-dimensional model based on the recovered high-fidelity image, and projection errors caused by respiratory movement and soft tissue deformation are eliminated.

The invention relates to the technical field of medical instrument detection, discloses a medical whole basket instrument multi-parameter detection system and method, and aims to solve the problem that in an existing CCD image detection technology, a high-brightness reflection area interferes with a detection result due to tiny bloodstain or superposition on the surface of an instrument. The system comprises an imaging module, a light source control module, a data processing module and a carrying platform. According to the method, reflection is reduced through combination of multispectral imaging and an adjustable light source, a reflection area is accurately identified and removed by using an algorithm of combining gradient amplitude and gradient direction entropy, and finally geometric parameters and cleanliness indexes of the instrument are synchronously calculated.

The invention discloses a fan abnormity monitoring method, device and equipment based on image recognition and a medium, relates to the technical field of image recognition, is applied to a wind turbine generator cabin, and comprises the following steps: acquiring an original image sequence in the wind turbine generator cabin in a first candidate image area in real time, eliminating environmental interference factors in the original image sequence of the first candidate image region to obtain a target image sequence; extracting visual features in the target image sequence of the first candidate image area, and identifying visual anomalies in the target image sequence of the first candidate image area based on the visual features of the first candidate image area; and when the visual anomaly is identified in the target image sequence of the first candidate image area, outputting alarm information containing the visual anomaly of the first candidate image area. The technical problem that a current fan monitoring scheme is poor in monitoring effect is solved.

A computer-implemented system for improving radiation dose reconstruction in adaptive real-time radiotherapy, comprising a data acquisition module for capturing treatment data in real time during radiotherapy, a preprocessing module for preprocessing the captured data, a deep-learning dose reconstruction engine for reconstructing the delivered radiation dose distribution using a trained deep-learning model, a dose evaluation and comparison module for comparing the reconstructed dose distribution with a planned dose distribution, and an adaptive decision support module to assist in adjusting radiotherapy treatment parameters based on the comparison results.

The embodiment of the application belongs to the technical field of medical instrument equipment, and relates to a trailing end of an interventional robot, which is used for delivering an elongated medical instrument, the elongated medical instrument comprising a guide wire and at least two catheters, the latter catheter being at least partially arranged in the former catheter, and the guide wire being partially arranged in the latter catheter; wherein the trailing end of the interventional robot comprises a driving device, a power device, a sensing device and a control device, the driving device, the power device and the sensing device are connected with the control device, and in an initial state, any catheter is clamped on two adjacent driving devices in a curved state. The technical scheme provided by the application can shorten the distance between adjacent driving devices through the curved arrangement of the catheter, reduce the overall size of the equipment, reduce the product cost, and be beneficial to product installation.

The invention provides a three-dimensional science popularization animation generation method and system based on an AIGC technology, and relates to the technical field of animation generation. The method comprises the following steps: firstly, fusing structured knowledge such as an anatomy term library, a diagnosis and treatment process guide and a drug specification with electronic medical records and CT / MRI volume data, and generating a split script and a medical term list through a large language model; then reconstructing an organ or focus grid by using a script-image combined driven text-three-dimensional diffusion model, and executing anatomical consistency correction according to the medical knowledge graph; automatically arranging a time axis, a camera track and a skeleton action, and synchronously synthesizing multilingual parastyle subtitles; and finally, frame-level rendering and compression packaging are completed in a real-time rendering engine, and efficient, professional and iterable medical animation generation is realized by means of an expert feedback closed-loop fine tuning model.

A medical system is disclosed that includes a medical device having an optical fiber, and an interchangeable connection component configured to provide a fiber optic connection between the medical device and capital equipment. The connection component is configured to facilitate cleaning and / or polishing of fiber optic interfaces include therewith. The connection component is also configured for replacement by a medical technician while the capital equipment is operational. The capital equipment may include one or more of an optical interrogator, a patch cable, a medical probe, an ultrasound machine, a display, a magnet sensor, or an electro-cardiogram (ECG) machine. The medical device may include an elongate member configured for insertion within the patient body, where the optical fiber core extends along a length of the elongate member.

The invention discloses a medical image diagnosis auxiliary system based on deep learning, and relates to the technical field of medical image processing. According to the method, through integrity verification, exclusive noise suppression and space standardization processing, dynamic changes of focus characteristics are captured through a time sequence attention mechanism, meanwhile, a medical pathology professional knowledge graph is called to achieve accurate matching of the time sequence focus characteristics, an anatomical structure and pathology type nodes, and the risk of missed diagnosis and misdiagnosis is greatly reduced; the confidence coefficient of a diagnosis assistance conclusion is evaluated through a multi-dimensional factor, manual review is automatically prompted for a low-confidence-coefficient result, dual management and control of system assistance and manual check are formed, meanwhile, standardized focus positioning, pathological type candidate and diagnosis basis can be provided for basic-level or inexperienced doctors, and the diagnosis accuracy is improved. Repeated work such as data arrangement can be reduced for experienced doctors, the doctors are assisted to focus on complex case judgment, the diagnosis and treatment level of a medical team is integrally improved, medical risks are effectively reduced, and the diagnosis and treatment quality and efficiency are improved.

The invention is suitable for the technical field of beauty instruments, and provides a control method of an ultrasonic beauty instrument, the ultrasonic beauty instrument and a medium. According to the control method of the ultrasonic beauty instrument, when the ultrasonic beauty instrument makes contact with the skin, whether a contact medium exists or not is judged, or the type of the contact medium is judged, the specific condition that the skin is coated with the contact medium when a user uses the ultrasonic beauty instrument can be determined, and then the ultrasonic beauty instrument can be controlled to work according to the judgment result; therefore, the working state of the ultrasonic beauty instrument can adapt to whether the contact medium is applied to the skin or not, or adapt to the type of the contact medium applied to the skin, the situation that the working mode of the beauty instrument is not matched with the condition of the contact medium applied to the skin when the ultrasonic beauty instrument is used can be avoided, the user experience is improved, and the use viscosity of the user is enhanced.

The utility model provides a precise delivery device for delivering drug aerosol. Wherein the precise delivery device for delivering a drug aerosol comprises: a housing sized and shaped to be graspable in a hand of a user; the medicine bomb assembly can atomize a set dose of medicine into aerosol, and an aerosol channel used for conveying the aerosol is formed in the medicine bomb assembly; a flow generator for generating a positive pressure gas flow that delivers the aerosol to the respiratory tract; the control unit is used for receiving an operation instruction and driving the medicine bomb assembly to output aerosol of medicine and the flow generator to generate positive pressure airflow; wherein the cartridge assembly, the flow generator and the control unit are all received in the shell. The utility model has the beneficial effects of small and exquisite structure, easiness in carrying, convenience in use and capability of accurately dosing.

A system configured to reduce scatter radiation around a surgical table during a medical procedure that may include at least one radiation shield configured to be connected to a surgical table with an attachment mechanism, wherein the at least one radiation shield includes one or more adjustable radiation shield segments coupled or releasably coupled to the at least one radiation shield. A device may include a pump in fluid communication with the one or more adjustable radiation shield segments comprising a pneumatic channel that is configured to at least partially inflate the pneumatic channel such that at least a first portion of the at least one radiation shield extends vertically above at least a portion of the surgical table, wherein a second portion of radiation shield is configured to extend below the surgical table. A device may include a controller configured to activate the pump.

The invention discloses a progressive multi-modal medical image fusion method based on multiple scales. Relates to the technical field of multi-modal medical image fusion, in particular to a progressive multi-modal medical image fusion method based on multiple scales. Through the integrated design of multi-scale extraction, hierarchical coding, layer-by-layer fusion and adaptive modeling, efficient and accurate fusion of multi-modal medical images is realized, and reliable technical support is provided for clinical application. The method comprises the following steps: acquiring images of a mode A and a mode B, and preprocessing the images; performing multi-modal parallel coding on the preprocessed image, wherein the multi-modal parallel coding comprises four coding stages; the input of each coding stage passes through a self-adaptive visual RWKV module, an efficient cross-modal module and a progressive fusion module in sequence to obtain the output of multi-modal parallel coding; and carrying out image conversion to obtain an RGB fusion image.

Provided is a medicine feeding apparatus including a receiving member including a plurality of receiving parts in which medicine can be received, and an apparatus main body that feeds the medicine received in the plurality of receiving parts to a target device. The plurality of receiving parts are open upward and configured to allow an operator to manually place the medicine from above thereinto. The receiving member includes a plurality of position indicators that indicate which of the plurality of receiving parts the medicine should be placed thereinto. The receiving member is configured to be attachable to and detachable from the apparatus main body.

The invention belongs to the technical field of medical robots and minimally invasive surgery, and provides a robot control system and method for blue laser vaporization surgery of prostatic hyperplasia. Mapping the nuclear magnetic image volume data to a deformation field under an ultrasonic acquisition coordinate system, and deforming the preoperative nuclear magnetic image to an intra-operative ultrasonic space by using the deformation field to complete image registration; fusing the registered image with a stereoscopic vision system; the spatial depth of the surface of the target tissue is obtained from the endoscopic image so as to supplement navigation information; according to the utility model, the prostate deformation and probe posture change adaptive capacity in an operation is improved, the real-time visual closed-loop regulation and control capacity is improved, and the characteristics of small light spots, shallow heat diffusion, excellent hemostasis and the like of blue laser are combined, so that the vaporization and hemostasis precision in a tiny blood vessel dense area is ensured, and the problems of large tissue trauma and the like are avoided.

The present invention relates to an AI-based system and method for generating enhanced radiology reports. The system comprises a database for storing multimodal patient data, a natural language processing (NLP) module for extracting clinical information, and a machine learning module for correlating the clinical information with radiology images to identify diagnostic insights. An AI-based report generation module analyzes the images and clinical information to generate a preliminary report, which is refined based on radiologist input. The generated report is then integrated into the patient's electronic health record. The system employs techniques such as multimodal deep learning, active learning, explainable AI, and federated learning to enhance diagnostic accuracy, capture expert feedback, provide transparency, and enable multi-institutional collaboration. The invention aims to improve the accuracy, efficiency, and value of radiology reporting in patient care.

The invention discloses a scanning type exposure method and system adopting a parallel digital micromirror array, and relates to the technical field of photoetching exposure and maskless direct writing of mask.The scanning type exposure method comprises the steps that parallel digital micromirror initial mapping is established through a reference target exposure detection registration method; generating a block distortion field parameter table according to the initial mapping of the parallel digital micromirror, determining a micro-mark insertion position based on the block distortion field parameter table, and generating an expected coordinate; performing micro-mark exposure on the expected coordinate position, acquiring imaging data of the inserted micro-mark position, extracting an actual measurement coordinate from the imaging data of the micro-mark position, calculating a residual error by taking the expected coordinate and the actual measurement coordinate as an input difference, and writing the residual error into a residual error set; incremental fitting is carried out according to the residual set, the block distortion field parameter table is updated, and the exposure controller controls the parallel digital micromirror array to remap the pattern according to the updated block distortion field parameter table and triggers exposure. The method provided by the invention has better effects in coordinate mapping consistency and block parameter manageability.

The invention provides a radiotherapy plan generation method and device, equipment and a medium, and the method comprises the steps: obtaining a target function image of a target object; the target function image comprises a target region, an organ at risk and a target part; determining target dose information of the target part based on the target function image, the target function partitioning result, the target region segmentation result and the endangered organ segmentation result; the target function partitioning result is used for indicating spatial distribution of a plurality of functional regions of the target part divided according to the functional state, and the target dose information comprises doses of different regions of the target part; and generating a radiotherapy plan based on the target dose information. By applying the embodiment of the invention, the set dose information of the target part is more reasonable, so that the radiotherapy plan generated based on the target dose information can ensure the accuracy of tumor control, reduce the risk of radioactive injury and realize targeted protection of the target part.

Pulmonary treatment devices, systems and methods of use are provided which take into account the vast tissue damage of advanced COPD sufferers and provide treatments designed specifically to treat the particularly compromised lung tissues that are present in these patients. These treatments reduce trapped air volume, tension lung tissue and enhance lung elastic recoil. In particular, a variety of embodiments of pulmonary treatment devices are provided. The devices are comprised of a shape memory material wherein the devices are able to be expanded under tension, and then are able to recoil back toward an original relaxed or resting shape as the devices are deployed into the tissue. This action causes the pulmonary treatment devices to corkscrew into damaged tissue, becoming sufficiently entwined to allow pulling of the tissue by retraction of the device. This in turn re-tensions the lung causing lung volume reduction.

The invention discloses an inference intervention method and device for relieving large visual language model illusion, a medium and equipment, and relates to the technical field of artificial intelligence, intelligent medical treatment and intelligent finance. The method comprises the following steps: aiming at a current to-be-generated output token, constructing a multi-modal input stream containing an image token and a text token and a plain text input stream only containing the text token; in the forward reasoning process of the language decoder, attention enhancement processing is carried out on an image token in the multi-modal input stream, forward reasoning calculation is carried out on the multi-modal input stream and the plain text input stream after attention enhancement, and multi-modal confidence distribution and plain text confidence distribution are obtained; carrying out suppression processing on the plain text confidence distribution on the basis of the multi-modal confidence distribution to obtain probability distribution of a current to-be-generated output token; and decoding to generate a current output token so as to update the autoregressive text of the language decoder. The method can reduce the probability of occurrence of model illusion.