95 results about "Dose prediction" patented technology

A machine learning-based method of generating a radiotherapy treatment plan for a patient, comprises dose prediction and dose mimicking, wherein the dose prediction step involves using a machine learning system that has been trained to consider at least one optimality criterion related to physical or technical restrictions that will affect the delivery of the treatment plan. Thus, at least one of the factors that are normally taken into account in the dose mimicking step is introduced in the dose prediction step. The invention also relates to a method of training such a machine learning system for use in radiotherapy treatment planning, a computer program product and a computer system.

The invention relates to the technical field of nasopharyngeal carcinoma radiotherapy, in particular to a nasopharyngeal carcinoma radiotherapy dose automatic prediction method based on deep learning, and the method comprises the following steps: S1, analyzing obtained original data; s2, writing a program to pre-process all the original data in batches; s3, calculating a corresponding dose volume histogram according to the anatomical contour and the patient dose distribution; and S4, inputting the preprocessed data into a designed deep learning model for dose distribution training and prediction, and comparing with an existing dose prediction method to verify the innovativeness and feasibility of the scheme. Dose prediction is automatically carried out through the deep learning model, manual rule design is not needed, high-quality dose distribution can be rapidly generated, batch preprocessing is carried out on all original data, dose distribution training and prediction are carried out by inputting the data into the designed deep learning model, the calculation performance is improved, and the method is suitable for large-scale popularization and application. And the training and reasoning efficiency is improved.

The invention discloses a multi-modal imaging system and method for a small animal living body. The system comprises a multi-modal fusion imaging module which is responsible for multi-modal image acquisition and primary processing; the real-time dynamic monitoring module is used for capturing bioluminescence / fluorescence signals in real time through a photon counting detector, receiving optical, nuclear medicine and magnetic resonance data, correcting motion artifacts based on a multi-scale space-time registration engine and adjusting scanning parameters through a real-time pharmacokinetic-physiological feedback mechanism; the low-radiation and biological compatible module is used for automatically optimizing the dosage of a tracer agent according to the weight of the animal, the scanning part and historical data by using a dosage prediction model; and the multi-modal data fusion module is used for performing non-rigid registration of multi-modal images based on a Transform cross-modal registration network, constructing a multi-species pharmacokinetic knowledge graph by utilizing multi-species metabolism chip data, integrating mouse, dog, primate and humanized liver chip data, and mining a cross-species metabolism rule through a graph neural network.

The invention proposes a voxel-level dose distribution prediction method, and the method comprises the steps: obtaining a detection image of a target object when each tracer is independently introduced under the condition that a plurality of tracers are independently introduced into the target object; performing image standardization processing on the detection image corresponding to each tracer agent to obtain a standardized image corresponding to each tracer agent; and taking the standardized images corresponding to the various tracers as input information of a deep learning model, and determining a comprehensive three-dimensional dose prediction result of the target object under the various tracers through the deep learning model. According to the technical scheme, the accuracy of dose prediction in nuclide therapy is improved, full-link automation from image acquisition to dose planning is realized, the generated dose distribution not only meets the clinical requirement of precise coverage of a target region, but also conforms to the radiotherapy principle of normal tissue protection, and reliable technical support is provided for personalized precise radiotherapy.

An external beam radiation therapy dose prediction system through a latent diffusion model is adapted to predict an external beam radiation therapy plan according to a clinical data of a patient and includes a storage unit adapted to store a training data and the clinical data and a processor signally connected to the storage unit. The training data includes a plurality of medical images, a plurality of dose distribution data, and a plurality of training prompts. The processor is adapted to input the training data to a latent diffusion training model to execute a latent diffusion model training and generate an external beam radiation therapy plan model and input the clinical data and at least one prompt to the external beam radiation therapy plan model to generate an external beam radiation therapy plan.

An automated adaptive radiotherapy system based on machine learning for designing and adapting personalized dosing plans and a corresponding system, the system comprising: • a data acquisition module to collect multimodal patient data such as anatomical images, genomics, physiological signals and electronic health records; • a preprocessing department that performs the normalization, alignment, segmentation and transformation of the acquired data into data structures suitable for predictive modeling; • a dose prediction engine containing at least one machine learning model trained to predict personalized three-dimensional radiotherapy dose distributions and dose-volume histograms from the preprocessed data; • an adaptation module to receive updated clinical data and automatically adapt the dosing schedule to intra-fraction and inter-fraction changes in patient anatomy and response to treatment; • a clinician dashboard that displays predicted dosing schedules, allows clinician interaction, and can make the model interpretable through explainable AI; • a data security and compliance layer that protects data through encryption, access control, and regulatory compliance.

The invention discloses a patient historical state-based anesthetic dose simulation evaluation system, which is characterized by comprising a multi-source data integration and preoperative physiological feature quantification layer, a dose effect relationship simulation layer and a risk evaluation and recommendation output layer. The method has the following advantages and effects that the personalized pharmacokinetics-pharmacodynamics model is constructed by integrating multi-source historical data of a patient, vital sign change tracks under different anesthetic doses are simulated, the recommended dose interval is generated based on multi-objective optimization, the change from experience dependence to accurate quantification is realized, and the accuracy of the recommended dose interval is improved. The problem of inaccurate anesthetic dosage prediction caused by individual differences is effectively solved, and the safety and effectiveness of an anesthesia scheme are remarkably improved.

The invention discloses a machine learning-driven water body bacteria ultraviolet disinfection dosage prediction and optimization method, which comprises the following steps of: obtaining genetic information, environmental parameters and ultraviolet disinfection conditions of target bacteria, and numeralizing the genetic information into feature vectors; cleaning and coding the acquired data to form a feature matrix; based on the characteristic matrix, a machine learning algorithm is utilized to train an ultraviolet disinfection dosage prediction model, and the model takes the inactivation efficiency as a prediction target; according to bacterial genetic information, environmental parameters and ultraviolet conditions input by a user, utilizing the trained prediction model to predict the inactivation efficiency, scanning in a multi-dimensional parameter space, and determining an optimal ultraviolet disinfection condition combination meeting a target inactivation level; outputting an optimal ultraviolet disinfection condition combination; the method disclosed by the invention has cross-strain and cross-scene applicability.

The invention discloses a tumor radiotherapy dose prediction method based on a diffusion model. The implementation scheme is as follows: 1) data collection; 2) data preprocessing; 3) constructing a dose prediction model; 4) training a prediction model; and 5) dose prediction. According to the dose prediction model constructed by the invention, a three-branch encoder is adopted to efficiently extract key features of input information, and accurate fusion of multi-source input features is realized by means of a feature fusion module MFF; the designed full-scale jump connection based on deformable convolution can make full use of the feature distribution of input conditions on different scales, thereby significantly improving the accuracy and robustness of dose prediction. The method can quickly generate a dose distribution result rich in high-frequency information, and has important scientific value and application prospect in the field of precise tumor radiotherapy.

The invention relates to the technical field of medical image processing and radiotherapy, in particular to an OVH-based breast cancer automatic radiotherapy plan design method and system. Constructing a historical database, and integrating the image data of the patient, the delineation structure of the target region and the organ at risk and the dose information; calculating an OVH index, and quantifying a spatial geometrical relationship between the breast cancer tumor target region and the key endangered organ; and extracting a target area external expansion distance Lx corresponding to the specific volume x of the organ in the OVH curve and a dose value Dx corresponding to the volume point in the dose-volume histogram. And constructing a function model between Lx and Dx through linear regression analysis. And for a new patient, the system calculates the Lx value of the organ of interest of the new patient, inputs the value into the linear model, and predicts the corresponding radiotherapy dose Dx. According to the method provided by the invention, intelligent aided design of the breast cancer radiotherapy plan can be realized, and a scientific and acceptable dose prediction basis is provided.

The invention discloses a graded blasting construction method for a shallow-buried soft rock tunnel sensitive section. The method comprises the steps that measuring points are arranged in a tunnel chamber, a ground surface non-cavity section and a cavity section, and blasting vibration data are obtained; peak vibration velocity prediction models are established in a partitioned mode, an attenuation model is adopted in a chamber, a correction term is introduced into a non-cavity section of the earth surface to correct the attenuation model, and a multivariable model is established for the cavity section through dimensional analysis by integrating the horizontal distance, the elevation difference, the explosive quantity, the rock mass density and the tensile strength; determining a ground surface vibration velocity safety threshold, and quantifying a cavity vibration velocity amplification coefficient and an influence range thereof; based on the peak vibration velocity probability distribution and a preset safety level, establishing a safe dose prediction model and a safe range model; and dividing control areas according to the model, and implementing graded construction. According to the method, the vibration propagation law can be accurately described, the cavity amplification effect can be quantified, dynamic prediction of the blasting safety explosive quantity and range is achieved, and disturbance of blasting vibration to surrounding rock is effectively controlled through hierarchical management and control.

The invention discloses a radiotherapy robustness optimization method and system, and the method comprises the steps: obtaining the clinical diagnosis and treatment information and anatomical feature information of a patient, and outputting unbiased scene dose three-dimensional distribution based on a dose prediction model; setting the maximum placement deviation of the patient, and obtaining deviation scene dose three-dimensional distribution corresponding to each placement deviation scene based on the dose three-dimensional distribution of the patient randomly moved in the maximum placement deviation range; for each round of circulation of robustness optimization, performing optimization calculation on the dose three-dimensional distribution of the unbiased scene to obtain optimized dose distribution, and calculating the sum of difference values between the optimized dose distribution and the dose three-dimensional distribution of each biased scene to obtain a target function value; when robustness optimization iteration reaches a preset number of times, optimization is ended, and a final optimization plan and corresponding final dose three-dimensional distribution are obtained; and for the final optimization plan, moving the final dose three-dimensional distribution in the maximum positioning deviation range, obtaining a deviation scene DVH curve, and evaluating the final optimization plan.

The invention provides a dose prediction method, which comprises the following steps: generating an initial vector based on initial prescription information and patient structure data; generating an initialization parameter based on the initial vector; generating initial dose distribution according to the initialization parameters; and adjusting the initial dose distribution based on a plurality of agents, and generating a target dose distribution, where a single agent is responsible for at least partial adjustment of the initial dose distribution. The invention further provides a device for executing the method and electronic equipment.

A dose prediction method and system, the method comprising: acquiring an original dose distribution of a radiotherapy object, original sign information and current sign information; obtaining a predicted Pareto optimization parameter through a dose prediction model according to the original dose distribution and the original sign information; and predicting a current dose distribution corresponding to the current sign information by using the dose prediction model according to the current sign information and the predicted Pareto optimization parameter.

The invention provides a flexible solar cell irradiation attenuation coefficient estimation method comprising the following steps: orbital parameters are combed, and spacecraft orbital parameters and space environment parameters are obtained; based on the orbit parameters and the space environment parameters, establishing an irradiation dose calculation model of the flexible solar cell; performing a ground equivalent test based on the irradiation dose calculated by the irradiation dose calculation model; and determining the irradiation attenuation coefficient of the solar cell in combination with test data and historical data. According to the method for estimating the irradiation attenuation coefficient of the flexible solar cell, the irradiation dose calculation model suitable for the flexible solar cell is constructed, the on-orbit performance attenuation coefficient of the solar cell array can be accurately obtained, and the accuracy of irradiation dose estimation is improved; scientific basis is provided for solar cell array design and on-orbit energy management, and reliability and design rationality of a spacecraft energy system are effectively improved.

The invention discloses a proton treatment plan verification and optimization device and method and related equipment, and relates to the technical field of radiotherapy. The device comprises an image acquisition module which is used for acquiring a PET image of a patient after completing at least one proton treatment irradiation; the dose prediction module is used for mapping the treated PET image into actual deposited dose distribution in the body of the patient based on the trained generative model so as to predict actual distribution dose distribution; and the adjustment and optimization module is used for generating an adjusted fractional treatment plan when the deviation between the predicted actual distribution dose distribution and the initial planned dose distribution is greater than a deviation threshold value. Based on in-vivo measurement information, the actual deposition dose is accurately verified and dynamically optimized, and accurate and safe proton therapy is achieved.

The application provides a kind of based on deep learning's absorbed dose prediction method, device, equipment and medium, it is related to medical image processing technical field, comprising: obtaining the treatment of patient's pre-test multi-modal data;According to clinical examination data and the mask map of the target tumor region and normal key organ region of pre-set drug, space coding is carried out, and the biomarker feature map of the patient to be tested is constructed;According to the pre-treatment medical image and biomarker feature map, a preset first deep learning model is used for prediction, to generate the simulated treatment initial medical image of the patient to be tested;According to the simulated treatment initial medical image, a preset second deep learning model is used for prediction, to generate the post-treatment predicted dosimetry parameter map of the patient to be tested.The application can improve the accuracy of nuclide absorbed dose prediction evaluation.

This invention relates to the field of medical data-driven dose prediction technology, and discloses a method, system, device, and storage medium for individualized dose prediction of hypothyroidism based on medical data. The method includes: constructing a standardized feature vector based on the child's weight, age in days, corrected age in months, current L-T4 dose, TSH value, FT4 value, previous TSH value, TSH rate of change, feeding method, month of consultation, etiology of hypothyroidism, comorbidity status, previous dose adjustment magnitude, and age at which TSH first reached target levels; extracting TSH dynamic trajectory features from the child's TSH time-series data from previous follow-ups; obtaining a basic recommended dose using a gradient boosting decision tree model constructed with counterfactual filtering training data; and correcting the basic recommended dose to obtain an individualized recommended dose. This method improves the prediction accuracy of the gradient boosting decision tree model and allows the individualized recommended dose to simultaneously take into account multiple clinical confounding factors.

The embodiment of the present application relates to the technical field of imaging detection, in particular to a component irradiation dose prediction method, an imaging system and a storage medium, the prediction method is applied to the imaging system, and the imaging system comprises a ray source and a detector. Through obtaining the actually measured dose of the concerned component under the irradiation of the ray source, fitting the irradiation intensity distribution of the ray source and the actually measured dose, obtaining the ray intensity dose distribution, mapping the path of the relative position change of the concerned component to the path of the height layer of the detector based on the ray intensity dose distribution, obtaining the irradiation dose of the concerned component under the standard height and the standard current, and finally correcting the irradiation dose according to the actual situation of the concerned component, the predicted irradiation dose of the concerned component is obtained, in this way, the irradiation dose of the concerned component can be accurately predicted by combining the ray intensity distribution of the ray source and the actual situation of the concerned component, the accuracy of the irradiation dose prediction is improved, and the irradiation dose error is reduced.

The invention discloses a head and neck cancer radiotherapy dose prediction method based on cross perception fusion. The method comprises the following steps: (1) establishing a training data set containing a patient CT image, a planned target region, an organ at risk and real dose distribution; (2) constructing a generative adversarial network based on cross-aware fusion, introducing a cross-aware fusion module into a generator to realize deep interaction and fusion of local and global features, and introducing a multi-scale cross-window self-attention coding network to constrain the difference between generation and real dose on multiple scales; (3) constructing a hybrid loss function based on the discriminator and the multi-scale cross window self-attention coding network; (4) training the generative adversarial network by using the training data set; and (5) testing data to be tested by using the trained network, wherein the output of the generator is a dose prediction result. According to the invention, direct generation of head and neck cancer radiotherapy dose distribution can be realized, doctors can be assisted in making an accurate radiotherapy plan, and the radiotherapy curative effect is improved.

The invention discloses a radiotherapy plan automatic optimization design method based on machine learning, and relates to the technical field of radiotherapy, and the method comprises the steps: firstly collecting and preprocessing radiotherapy core data to generate a training set, training feature extraction, dose prediction and optimization adjustment of a model; processing to-be-processed data through a feature extraction model, screening three optimal similar cases in combination with cosine similarity, and extracting effective features; based on the feature vectors and the effective features, outputting an initial dose plan, constraint parameters and a deposition matrix by a dose prediction model; and finally, constructing a target function, and iteratively optimizing the radiation field parameters and the photon flux by adopting an improved ant colony algorithm and a conjugate gradient method. According to the method, clinical experience and individual differences are fused, the radiotherapy plan is efficiently and accurately generated, and the quality stability and clinical suitability of the plan are improved.

The present invention relates to a system for predicting and managing radiation dose and, more specifically, to a system for predicting and managing radiation dose, wherein a simulation can be implemented in advance by modeling a work site and a worker and reflecting the work site and the worker in a scenario so that the radiation dose of the worker during radiation work in a nuclear power plant can be predicted before the work is begun.

The present invention relates to the technical field of PCBA board detection and discloses a method for setting a dose threshold for X-ray short circuit detection of PCBA boards for a fixed time. The method comprises the following steps: taking U PCBA multilayer boards with the same substrate thickness and short circuit defects as a sample set and dividing the sample set into a training sample set m, a test sample set n, and a verification sample set q; performing short circuit detection at different doses on the PCBA multilayer boards in the training sample set m to obtain a lower dose prediction threshold and an upper dose prediction threshold; further obtaining a lower dose transition threshold, a lower dose final threshold, an upper dose transition threshold, and an upper dose final threshold through a machine learning system; and finally generating a lower dose threshold and an upper dose threshold respectively through weighted combination. The present invention generates the lower dose threshold and the upper dose threshold through weighted combination, which can reduce the influence of the specificity of the PCBA boards in the training sample set m, the test sample set n, and the verification sample set q on the final threshold, thereby making the final threshold more accurate.

This invention discloses an intelligent adaptive dose verification calculation method and system. The intelligent adaptive dose verification calculation method includes: obtaining preliminary dose distribution data for a patient based on a deep learning-based dose prediction model; dynamically assigning variance reduction parameters to particles in a Monte Carlo simulation based on the high and low dose distribution information in the preliminary dose distribution data, wherein the variance reduction parameters include simulation weights, with simulation weights assigned to particles predicted to be in high-dose regions being less than those assigned to particles predicted to be in low-dose regions; and using a Monte Carlo dose calculation engine, simulating the planned beam based on the dynamically assigned variance reduction parameters to obtain high-precision verification dose distribution data. This invention's intelligent adaptive dose verification calculation method ensures the physical authenticity of the final verification dose distribution and the credibility of the "gold standard."

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 application discloses a three-dimensional radiotherapy dose prediction method based on distance prior and local ranking loss. In view of the target boundary leakage and optimization instability problems existing in the traditional model, the method adopts a SwinUNETR network, and a continuous spatial distance map is injected at the input end to assist the model in establishing the physical law of radiation attenuation. At the same time, a boundary-aware local ranking loss is proposed, which accurately applies a one-way topological penalty to the 3mm high-risk area at the junction of the target area and the organ at risk, truncates the dose leakage and promotes the energy to gather in the target area. Experiments prove that the method makes the core target area coverage index D95 jump to 42.798Gy, and the irradiated volume V50 of the organ at risk is reduced to below 0.005%, realizing high-precision and high-safety radiotherapy dose distribution prediction.

Systems and methods for determining multi-field doses for radiation therapy are provided. 1) one or more medical images of a patient and 2) a fluence map for each of a plurality of fields for radiation therapy of the patient are received. Fluence-related information is determined for each of the plurality of fields based on the fluence map. Fluence-related information for the plurality of fields is aggregated. A multi-field dose of the patient is determined based on the one or more medical images and the aggregated fluence-related information using a machine learning-based dose prediction network. And outputting the multi-field dose.

The application discloses a head and neck cancer radiotherapy dose prediction method based on cross perception fusion, comprising the following steps: (1) establishing a training data set containing a patient CT image, a planning target volume, an organ at risk and a real dose distribution; (2) constructing a generative adversarial network based on cross perception fusion, introducing a cross perception fusion module in the generator, realizing the deep interaction and fusion of local and global features, and introducing a multi-scale cross window self-attention coding network to constrain the difference between the generated and real doses at multiple scales; (3) constructing a hybrid loss function based on the discriminator and the multi-scale cross window self-attention coding network; (4) training the generative adversarial network by using the training data set; and (5) testing the data to be tested by using the trained network, and the output of the generator is the dose prediction result. The application can realize the direct generation of the head and neck cancer radiotherapy dose distribution, assist doctors in formulating accurate radiotherapy plans, and improve the radiotherapy effect.

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 relates to the technical field of medical image processing, and discloses a nasopharyngeal carcinoma radiotherapy dose prediction system and method of a cascade network, which solves the technical problem that nasopharyngeal carcinoma radiotherapy dose prediction lacks global-local structure collaborative modeling and adaptive cross-stage feature interaction in the prior art. A first-stage three-dimensional U-Net network captures anatomical global features, a second-stage improved MedNeXt network performs dose fine prediction through residual learning, explicit division avoids the multi-scale feature extraction limitation of a single network, and the overall dose score and the DVH score are respectively improved; through instance normalization, the first-stage feature activation distribution is stabilized, after being spliced with original input, the convolution adaptive layer is seamlessly integrated into the second stage, the dimension mismatch and the gradient saturation problem are solved, and flexible multi-stage feature reuse is supported.