58 results about "Target dose" patented technology

A solution for training a machine learning model (305) for use in medical imaging applications is presented. A corresponding method (400) includes providing (403-410) an incomplete sample set for each imaging process, each incomplete sample set including one (or more) sample target images and one (or more) sample baseline images for a sample target dose of contrast agent. One (411-445; 450-456) sample source images are simulated (411-445; 450-456) from each of the incomplete sample sets (or a portion thereof) to mimic contrast agent at a sample source dose that is lower than the sample target dose. One or more complete sample sets are generated (446; 457) for each imaging process by combining the incomplete sample sets with sample source images that have been simulated from other incomplete sample sets. The machine learning model (305) is then trained (458-473) using the complete set of samples. Further, a method of using a machine learning model in medical imaging applications is presented. A computer program (300) and a computer program product for implementing a method (400) are presented. Furthermore, a computing system (130) for executing the method (400) is presented. A corresponding medical method is also presented.

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.

The invention provides a radioactive source personal dose real-time monitoring device and a radioactive source personal dose real-time monitoring method based on a double-range self-adaptive mechanism. The radioactive source personal dose real-time monitoring device and method are suitable for intraoperative individual dose collection and dynamic evaluation in the tumor radiotherapy process. The device comprises a flexible attaching substrate, a first measuring range detection sub-module, a second measuring range detection sub-module, a self-adaptive scheduling unit, a temperature compensation module, a breathing synchronous correction module and a wireless communication module. The device can respond to different dose intensities in real time and adaptively switch or fuse channels; the collected dose projection is restored to a planned coordinate system through a breathing phase recognition and target region drift model, and dynamic target region dose tracking is achieved; temperature correction and wireless transmission functions are combined, and intraoperative data visualization and postoperative evaluation are supported. According to the invention, the precision and safety of radiotherapy dose monitoring are improved, and the method is especially suitable for radiotherapy management of areas with significant respiration-induced drift or adjacent key organs.

The invention provides a dose optimization method and device, equipment and a medium, and the method comprises the steps: obtaining a functional image of a target object and the initial dose information of a target part; the functional image comprises a target part, and the initial dose information comprises initial doses of different areas in the target part; determining a damage prediction result of the target part through a pre-trained damage prediction model based on the functional image and the initial dose information; the damage prediction result is used for indicating the probability of radioactive damage at each position in the target part; based on the damage prediction result, optimizing the initial dose information to obtain target dose information of the target part; the target dose information comprises target doses of different areas in the target part. By applying the embodiment of the invention, the dose optimization effect can be ensured, the risk of radioactive injury of the target part is reduced, and the protection effect on the target part is improved.

The present disclosure provides a radiotherapy plan generation method, comprising: obtaining object information of a target object, the object information comprising at least medical image information and a treatment target of the target object; calculating a field intensity distribution according to the object information, the field intensity distribution comprising a plurality of dose grids and beam information of a corresponding beam of each dose grid; selecting a target dose grid from each dose grid based on a difference between an actual dose of each dose grid and a target dose; constructing an inverse optimization problem according to each target dose grid; and solving the inverse optimization problem to generate a radiotherapy plan.

The invention discloses a radiopharmaceutical dose automatic calibration method, which comprises the following steps of: performing charge state analysis on an iodine-131 radiopharmaceutical solution to determine the polarity and the intensity of an electrostatic charge required to be applied by a needle; before injection, static charges are applied to the needle head through the micro-current generating device, so that medicine can be effectively separated from the needle head after injection is completed, and residues are reduced; a high-precision micro-injection pump is combined with a pressure sensor to control the injection speed and dose output, and the fluid flowing state is monitored in real time to avoid abnormal conditions; after injection, a laser scattering detection module and an image recognition algorithm are used for capturing and evaluating the volume of residual liquid drops at the tail end of a needle head in real time, the dose needing to be additionally supplemented is calculated according to the volume, and it is ensured that a patient receives the accurate target dose; no needle residue is confirmed again after dose supplementation, so that the accuracy of the final administration dose is ensured; the whole system is flexible and high in adaptability, and can be adjusted according to the characteristics of different types of radiopharmaceuticals.

Techniques for estimating target radiation doses for medical imaging exams leveraging artificial intelligence (AI) are described. In an example, a method can comprise training an AI model to estimate target dose information for past medical imaging exams using historical exam reports for the past imaging exams and actual radiation dose information included in the historical exam reports indicating actual radiation dosages exposed to past patients as a result of the past imaging exams. Once trained, the AI model is applied to estimate the target dose information for new medical imaging exams prior to performance of the new exams. The target dose information is further provided to the corresponding imaging systems scheduled for the new exams. In some implementations, the target dose information can control the acquisition protocol used for the exams to ensure compliance with the target dose information.

Embodiments of this disclosure provide a method, apparatus, and storage medium for electron beam exposure correction. The method includes: determining a first dose distribution for electron beam exposure by performing electron beam proximity effect correction on a target pattern based on a predetermined dose distribution, the first dose distribution indicating a set of dose adjustment values ​​for compensating for scattering effects during electron beam exposure on the target pattern; determining a second dose distribution for electron beam exposure by performing electron beam haze effect correction on the target pattern based on the first dose distribution, the second dose distribution indicating a set of dose adjustment values ​​for compensating for haze effects during electron beam exposure on the target pattern; and determining a target dose distribution for electron beam exposure by performing electron beam proximity effect correction on the target pattern based on the first and second dose distributions.

The invention discloses an ion implantation method, medium and system for a semiconductor wafer, and the method comprises the following steps: S1, receiving dose ratio parameters of a plurality of concentric circle regions inputted by a user, and calculating the target dose of each region according to the total dose; s2, according to the calibration positions of the wafer target disc center and the beam current center, the beam current height and the radius parameter of each area, calculating the variable speed position coding value of each area in the vertical scanning direction; s3, based on the target dose, the injection speed of each region is calculated; s4, in a single vertical scanning process, dynamically adjusting the scanning speed of the wafer according to the variable-speed position coding value, and realizing variable-speed injection corresponding to different injection speeds in different areas; and S5, rotating the wafer to the next orientation, and repeating the step S4 until injection of all set orientations is completed, thereby realizing dose distribution of concentric circles or specific patterns. The method has the advantages that customizable dose distribution of specific graphs such as concentric circles can be realized, and the like.

This application relates to a statistical analysis method and apparatus. The method includes: acquiring multiple target dose reports; each target dose report including inspection object information, inspection item information, and inspection equipment information; performing statistical analysis on the multiple target dose reports to determine evaluation results; the evaluation results include at least one of an evaluation result on the inspection dose, an evaluation result on the inspection effect, and an evaluation result on the inspection equipment. The statistical analysis method provided in this application obtains evaluation results through statistical analysis of the target dose reports, thus achieving full utilization of the target dose reports.

To reduce an exposure dose to a subject in radiation imaging.SOLUTION: The radiation imaging apparatus includes a radiation detector configured to obtain a radiation image by causing radiation to be incident on the radiation detector, a unit configured to obtain dose information of the radiation incident on the radiation detector, a unit configured to obtain imaging condition information of radiation imaging for obtaining the radiation image by causing the radiation to be incident on the radiation detector up to a target dose, and a unit configured to issue a notification to stop radiation irradiation by a radiation generating apparatus so as to stop the radiation irradiation by the radiation generating apparatus before the radiation is incident up to the target dose after the start of the radiation imaging based on the imaging condition information.SELECTED DRAWING: Figure 5

The invention relates to a small-dose automatic metering, subpackaging and storing device and a control method thereof, and relates to the technical field of medical medication configuration and intravenous infusion dosing assistance. The intelligent metering injection unit is arranged in the shell and is used for fixedly mounting a disposable syringe; the piston displacement detection assembly is used for detecting piston displacement in real time; the piston driving and locking mechanism is used for driving the piston of the disposable syringe to automatically shift and be locked at a target dose position; the main control module is used for calculating the actual dose according to the piston displacement; wherein the intelligent metering injection unit provides axial guidance for the disposable syringe, the main control module controls the piston driving and locking mechanism according to the actual dose calculated by the piston displacement detection assembly, and closed-loop metering is achieved. High-precision control over insulin small-dose intravenous dosing can be achieved, the pollution risk caused by pumpback or repeated puncture is avoided, and the actual use loss of insulin injection is reduced on the whole.

This application provides a radiation control method for a radiation device, wherein the radiation device has a fixed unit. The method includes: communicating with a portable unit carried by a target object through the fixed unit to determine the relative position information between the radiation device and the target object; determining a radiation strategy of the radiation device based on at least one of a first radiation dose emitted by the radiation device detected by the fixed unit and a second radiation dose received by the target object detected by the portable unit, and the relative position information; and adjusting the radiation dose to be emitted by the radiation device according to the target dose range indicated by the radiation strategy. This application also provides a radiation control system, device, storage medium, and program product.

The invention provides a dose prediction model training method and device, equipment and a storage medium, and belongs to the technical field of artificial intelligence. According to the method, the dose prediction model for determining the dose distribution based on the target imaging image is trained, so that when the dose distribution is determined, the dose distribution can be rapidly determined through the dose prediction model, multiple iterative calculations are not needed, the time consumption is obviously shortened, and the efficiency is improved. Moreover, training is performed based on a gradient of a model loss function with respect to a model parameter, and the model loss function is not only related to a difference between a predicted dose distribution and a target dose distribution, but also related to a difference between an imaging image predicted based on the predicted dose distribution and a target imaging image. In this way, after the dose prediction model is obtained through training, photoetching is carried out through the determined dose distribution, the quality of an imaging image can be improved, that is, the dose distribution is determined through the dose prediction model, efficiency is high, and accuracy is high.

The utility model relates to the technical field of nuclide protection, and provides a nuclear medicine split medicine injection fuming cupboard which comprises a split charging instrument, an activity meter, an injector and a shielding fuming cupboard. The shielding fuming cupboard is provided with an operation window and an injection window, the split charging instrument, the activity meter and the injector are all installed in the shielding fuming cupboard, and the split charging instrument is configured to split charging medicine and conduct activity detection through the activity meter, so that the dosage of the medicine is the target dosage, and the target dosage of the medicine is conveyed to the injector. The split charging instrument configures a target dose of medicine according to user requirements and delivers the prepared medicine to the injector, at the moment, an operator can stretch the hand into the shielding fuming cupboard through the operation window to pick up the injector, and meanwhile, the hand of a patient is placed close to the injection window, so that the patient can take the medicine out of the injection window. Therefore, an operator can inject the medicine in the injector into the body of a patient. In this way, the unnecessary radiation risk in the process is avoided while the split charging precision and efficiency are improved.

This invention discloses a method and system for re-optimizing radiotherapy plans based on target inheritance and photon flow reset, relating to the fields of medical physics and radiotherapy technology. The method includes obtaining the initial radiotherapy plan for a patient from a treatment planning system; extracting a patient-specific target set from the initial radiotherapy plan to form a configuration file independent of the initial radiotherapy plan; and prohibiting modification of the configuration file in subsequent optimizations to achieve target freezing, resulting in a frozen target set. This invention, through a strategy combining target inheritance, freezing, and photon flow reset, enables the optimizer to break free from the constraints of the initial plan's historical parameters and restart the global search from a blank state, under the same clinical intent. This fundamentally breaks the local optimum locking caused by path dependence in traditional inverse optimization, systematically and significantly reducing the dose to organs at risk while maintaining target dose compliance, thus achieving a deterministic improvement in plan quality.

This invention relates to the field of transfer learning technology and discloses a method for predicting radiotherapy plan dose distribution based on domain adaptive transfer learning. The method includes: identifying source and target domain medical institutions; collecting radiotherapy plan data from the source domain medical institutions; extracting radiotherapy plan features from the radiotherapy plan data to train an initial dose distribution analysis model for the source domain medical institutions; constructing a federated learning network for the source and target domain medical institutions; outputting a dose distribution analysis map of the initial dose distribution analysis model; identifying domain differences between the source and target domain medical institutions; defining the optimization objective of the initial dose distribution analysis model; performing domain adaptive transfer learning on the initial dose distribution analysis model to obtain a local dose distribution analysis model; and generating the target dose distribution for patients in the target domain medical institutions. This invention can improve the efficiency and accuracy of radiotherapy plan dose distribution prediction.

The application provides a dose distribution generation method and device and electronic equipment, which can be applied to the technical field of medical image processing. The method comprises the following steps: determining an initial intensity distribution map according to a predicted dose distribution matched with target tissue contour data of a target object; optimizing the initial intensity distribution map by using a target optimization function and a target constraint condition to obtain a target intensity distribution map, the target optimization function is used to optimize the boundary beam intensity of the initial intensity distribution map in a boundary region, the target constraint condition is used to constrain the proportion of target voxels in the boundary region, which exceeds a preset boundary dose threshold, to be less than a preset proportion threshold, the boundary region represents the region of the boundary between the organ tissue region and the tumor tissue region, and the boundary conversion dose is obtained by converting the boundary beam intensity based on an intensity dose conversion factor; and determining a target dose distribution representing the deposition of simulated radiation irradiating the tumor tissue region and the organ tissue region according to the target intensity distribution map.

The invention provides a pelvic tumor multi-center, multi-tumor-species and multi-prescription dose prediction method and related equipment, and is applied to the technical field of data processing. The method comprises the following steps: preprocessing a training sample set to generate a training sample set with target feature data; processing a preset dose distribution processing model based on a SwinTransform network architecture based on the training sample set with the target feature data, and generating a target dose distribution processing model; performing feature extraction processing on the CT image information of the target user to generate a target feature vector; processing the physiological state information of the target user to generate a dose limiting factor of the target user; processing the physiological parameter information of the target user to generate a dynamic dose influence factor of the target user; and processing the target feature vector, the dose limiting factor of the target user and the dynamic dose influence factor of the target user based on a target dose distribution processing model to generate target dose distribution information.

The application discloses an airway sterilization treatment device and method, and relates to the technical field of medical devices; the airway sterilization treatment device comprises an irradiation module, a dose monitoring unit and a control unit, the irradiation module is used for emitting blue light for sterilization to an airway target position; the dose monitoring unit is arranged on the irradiation module, and the dose monitoring unit is used for monitoring an actual light dose received by a mucous membrane surface of the airway target position; the control unit is electrically connected with the dose monitoring unit and the irradiation module, and the control unit is used for closed-loop control of blue light output of the irradiation module according to the actual light dose fed back by the dose monitoring unit, so as to make the actual light dose reach a preset target dose. According to the application, the actual light dose received by the mucous membrane surface is monitored during blue light irradiation, and the blue light output of the irradiation module is closed-loop controlled according to the actual light dose, so that the final delivered light dose is consistent with the target dose, and the treatment effect and safety are guaranteed.

A method for incorporating an extended bolus signal is disclosed. The method includes determining a target dose amount of medicament to deliver for a control cycle. The method also includes obtaining data related to an extended bolus. The method further includes determining an additional medicament amount to deliver during the control cycle corresponding to the extended bolus. The method yet further includes determining a total medicament delivery amount for the control cycle corresponding to the target dose amount and the additional medicament amount. The method still further includes sending a command to a delivery mechanism to cause delivery of the total medicament delivery amount for the control cycle.

The invention discloses a thrombus extraction stent system and a preparation method and application thereof, and belongs to the technical field of medical instruments.The thrombus extraction stent system comprises an expansion stent, a micro catheter and a thrombolysis medicine, and the method comprises the steps that the target dosage of the thrombolysis medicine is determined according to angiography data of target thrombus; determining a first target printing parameter of the thrombolytic drug according to the target dose of the thrombolytic drug; according to the first target printing parameters, a medicine layer containing thrombolytic medicine is formed on the expansion stent through 3D printing, the expansion stent is placed in the micro-catheter, and the thrombectomy stent system is prepared. The technical problem that the thrombolysis medicine cannot be accurately released according to the actual condition of thrombus in the conventional thrombus extraction process is solved.

This application relates to the field of medical imaging, and in particular to a method for descattering breast images, a breast X-ray machine, a computer device, and a storage medium. The method includes: pre-exposing multiple equivalent phantoms based on a preset dose value to obtain pre-exposed images corresponding to each of the equivalent phantoms; performing descattering processing on each of the pre-exposed images based on the compression thickness and composition of each equivalent phantom to determine the coupling relationship between a target grayscale value and the compression thickness and composition; determining a target dose value based on the compression thickness, composition, and coupling relationship of the target breast; and performing formal exposure on the target breast based on the target dose value to obtain a formally exposed image. This invention employs a gridless descattering method to descatter the pre-exposed images, enabling more accurate determination of the target dose value.

The present application relates to the medical physics technical field, disclose a kind of radiotherapy dose prediction method, device, equipment and medium.The method comprises: obtaining the medical image of the radiotherapy region of patient, including the multiple two-dimensional slice images of radiotherapy region, planned target volume and organ at risk in radiotherapy region are region of interest;Each two-dimensional slice image and its adjacent two-dimensional slice image are input into conditional diffusion generation network, with the anatomical information of its region of interest as control condition, guide the process of gradually denoising of the noise map generated by diffusion model to the random dose distribution map of radiotherapy region, generate initial dose distribution map;Two-dimensional slice image is input into dose calibration network, and the dose of its region of interest is predicted, to calibrate the dose of region of interest in initial dose distribution map, generate target dose distribution map;The three-dimensional dose distribution of patient radiotherapy is determined in combination with the target dose distribution map of all two-dimensional slice images.

The application provides an exposure dose control method based on an exposure dose control system, which comprises the following steps: controlling a shutter to open; receiving an energy value collected by an energy sensor, determining an accumulated exposure dose value based on the energy value; determining whether the accumulated exposure dose value is not less than a target dose value; if the accumulated exposure dose value is not less than the target dose value, controlling the shutter to start to close; taking the accumulated exposure dose value corresponding to a shake delay end moment after the shutter is completely closed as an actual accumulated exposure dose value; determining an exposure dose error value based on the actual accumulated exposure dose value; determining whether the exposure dose error value meets a requirement; if the exposure dose error value does not meet the requirement, updating an equivalent dose value and returning to execute the first step; if the exposure dose error value meets the requirement, applying the equivalent dose value to an exposure system. Through the exposure dose control method based on the exposure dose control system, the problem of low exposure dose control precision is solved.

The invention discloses a dose control method for a human body X-ray security inspection device, and the method comprises the steps: obtaining a height value (H) and a weight value (W) of a detected person before scanning, and calculating a weight-height ratio (R) of the detected person; calculating a target dose value Dtarget according to a formula Dtarget = D0 + K * R; the target dose value is compared with preset dose upper and lower limits (Dmax, Dmin) to determine a final emission dose (final dose value Dfinal). Personalized adjustment of the scanning dose is carried out according to the obesity degree (quantified through the weight-height ratio) of the detected person, and unnecessary radiation irradiation on the detected person with a thin and small body shape can be reduced; meanwhile, compared with traditional X-ray scanning with a fixed dose value, an image with a higher signal-to-noise ratio and clearer details can be obtained for an obese detected person, so that a security check person can identify dangerous articles possibly existing in the image, and the accuracy and safety of security check are improved.

The invention provides a precise UV manicure curing method and system based on an AI deep self-learning algorithm. The method comprises the steps that a finger image is collected, and a fingernail and skin area is segmented; generating a target dose distribution based on the nail geometry, the coating type, and the target curing quality; establishing an optimization model with the constraints that the dose error is minimum, the dose of the skin area is lower than a threshold value and the temperature rise does not exceed the threshold value; the current, the duty ratio, the lighting duration and the optical axis posture of each light-emitting unit are jointly calculated through an optimization solving module, irradiation is executed, feedback is formed based on the temperature and a reflection signal, and a controller conducts online correction till target dose distribution is achieved; the system is composed of a nail positioning and segmentation module, a dose planning module, an optimization solving module, a light-emitting array execution module, a safety monitoring and linkage control module and a controller with reinforcement learning and federated learning functions, and accurate dose regulation and control are achieved. According to the invention, the consistency, the safety and the intelligent level of UV manicure curing can be obviously improved.

The invention relates to the technical field of medical physics, and discloses a radiotherapy dose prediction method and device, equipment and a medium. The method comprises the steps that a medical image of a radiotherapy area of a patient is acquired, the medical image comprises a plurality of two-dimensional slice images of the radiotherapy area, and a planned target area and an organ at risk in the radiotherapy area are areas of interest; inputting each two-dimensional slice image and the two-dimensional slice image adjacent to the two-dimensional slice image into a conditional diffusion generation network, and by taking anatomical information of a region of interest of the conditional diffusion generation network as a control condition, guiding a process of gradually denoising a noise graph generated by adding noise to a random dose distribution graph of a radiotherapy region by a diffusion model to generate an initial dose distribution graph; inputting the two-dimensional slice image into a dose calibration network, predicting the dose of the region of interest of the two-dimensional slice image, calibrating the dose of the region of interest in the initial dose distribution diagram, and generating a target dose distribution diagram; and determining the three-dimensional dose distribution of the radiotherapy of the patient by combining the target dose distribution diagrams of all the two-dimensional slice images.

The present application relates to the technical field of radiotherapy control, and discloses a treatment control method and system for AB-BNCT. The method comprises the following steps: sending a beam-out condition verification request and a beam-out safety verification request in response to a beam-out request; sending a beam-out button display instruction after receiving the pass results, so that the beam-out button is displayed based on a preset state; monitoring main real-time beam data in real time in response to a state change of the beam-out button; determining a main real-time neutron absorption dose based on the main real-time beam data; and sending a beam control instruction to an accelerator based on the main real-time neutron absorption dose and a target neutron absorption dose, so that the accelerator controls the beam in response to the beam control instruction. By comparing the real-time dose with the target dose, the treatment is continued or stopped, and the accuracy of the treatment and the safety of the patient are ensured. The present application solves the technical problems of low safety and dose verification lag in the existing AB-BNCT treatment, and improves the safety and efficiency of AB-BNCT treatment.

The invention provides a dose distribution generation method and device and electronic equipment, which can be applied to the technical field of medical image processing. The method comprises the following steps: determining an initial intensity distribution diagram according to estimated dose distribution matched with target tissue contour data of a target object; and optimizing the initial intensity distribution diagram by using a target optimization function and a target constraint condition to obtain a target intensity distribution diagram, the target optimization function being used for optimizing the boundary beam intensity of the initial intensity distribution diagram in the boundary region, the target constraint condition is used for constraining that a target voxel ratio of a boundary transformation dose exceeding a preset boundary dose threshold value in the boundary region is smaller than a preset ratio threshold value, and the boundary region represents a boundary region between the organ tissue region and the tumor tissue region; the boundary conversion dose is obtained by converting the boundary beam intensity based on an intensity dose conversion factor; and according to the target intensity distribution diagram, determining target dose distribution representing deposition of the tumor tissue area and the organ tissue area irradiated by the simulated rays.