30 results about "Dose optimization" patented technology

The invention relates to the technical field of intelligent anesthesia precise regulation and control, and discloses an anesthetic dosage optimization method based on artificial intelligence. According to the method, a dynamic treatment interval is constructed, and the boundary of the dynamic treatment interval is adaptively adjusted according to the real-time sedation depth and the nociceptive stimulation level. And in the interval, performing pattern recognition on the continuous electroencephalogram signals and the hemodynamic parameters, and marking abnormal events deviating from a standard anesthesia state. And establishing a correlation network of the drug effect chamber concentration and the abnormal events, and generating a virtual drug response curve for predicting the trend of the abnormal events under different doses. Whether dose strategy reconstruction is started or not is determined by comparing the goodness of fit between the prediction curve and the actual physiological trajectory. During reconstruction, contribution weights of historical drug infusion points to abnormal events are backtracked and analyzed, and adjustment coefficients are distributed and integrated into a new infusion sequence. According to the invention, individualization and self-adaptive optimization of anesthesia administration are realized, and the accuracy and safety of anesthesia depth control are improved.

The invention relates to the field of medical health and artificial intelligence, and discloses a cancer patient low-molecular heparin individualized dose dynamic optimization method based on reinforcement learning, and the method comprises the steps: S1, collecting multi-dimensional clinical data of a cancer patient, carrying out the preprocessing, carrying out the enhancement of the preprocessed data, and generating time sequence synthesis data; s2, based on the multi-dimensional clinical data and the time sequence synthesis data, constructing a reinforcement learning environment, including defining a state space, an action space and a reward function; s3, constructing an environment adaptive deep reinforcement learning EA-DRL model as a dose optimization model; performing model training and optimization in the reinforcement learning environment until convergence and obtaining an optimal dose decision strategy; and S4, inputting real-time dynamic clinical data of a patient to be decided into the trained dosage optimization model, and outputting individualized low molecular heparin LMWH administration dosage recommendation. Individualized precise administration is realized, and the treatment effect and the clinical medication safety are improved.

The invention discloses a self-adaptive control method of an analgesia infusion system based on multi-modal feedback, and relates to the field of analgesia infusion automation control, and the method comprises the steps: inputting a feature vector into a multi-modal fusion decision-making layer, and calculating a comprehensive pain index PI by adopting a confidence-weighted self-adaptive fusion algorithm; taking the comprehensive pain index PI, the drug cumulant and the physiological stability index as state input, and inputting the state input into a self-adaptive controller based on reinforcement learning; the adaptive controller outputs a basic infusion rate adjustment amount, a pulse dose adjustment amount, and a locking time adjustment amount. According to the invention, through multi-source signal acquisition and confidence coefficient weighted adaptive fusion, the accuracy and robustness of pain assessment are improved; the hierarchical reinforcement learning controller realizes personalized dose optimization on the premise of safety priority, and gives consideration to both analgesic effect and physiological stability; and the safety monitoring module is combined with multi-modal cross validation and pharmacokinetic prediction, so that the safety risk is effectively reduced.

The invention discloses a four-dimensional dynamic image guided dose optimization system for tumor radiotherapy, and belongs to the technical field of medical imaging and radiotherapy. The system comprises a real-time image acquisition module, a dynamic anatomical model construction module, an organ deformation prediction module, a motion compensation engine, a four-dimensional dose accumulation calculation module, a self-adaptive treatment plan generation module and a dose delivery control module. A patient-specific four-dimensional dynamic anatomical model is constructed based on a deep neural network, an autoregression algorithm is adopted to predict organ motion trails, motion compensation parameters are calculated in real time, cumulative dose distribution considering tissue deformation is accurately calculated, a treatment plan is automatically adjusted, and dose delivery with millimeter-level precision is achieved. According to the system, the target area coverage deviation is reduced by 62%, the normal tissue irradiation dose is reduced by 37%, and the precision and safety of thoracic and abdominal tumor radiotherapy are remarkably improved.

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 invention relates to a functional partition dose optimization and dual-mode registration transcranial ultrasonic nerve regulation and control navigation system, which depends on a conventional CT (Computed Tomography) and MRI (Magnetic Resonance Imaging) medical image and optical positioning hardware platform. By establishing an equipment side source intensity calibration model, a subject specific transcranial space transfer function and a brain function partition driven multi-region dose optimization model, joint optimization and navigation control of the position, posture and driving parameters of the transcranial ultrasonic transducer are realized; on the premise that dose constraints of multiple functional risk areas are met, the stimulation dose of the target functional area is improved, and real-time evaluation and interlocking control are carried out on dose safety in the navigation execution process. Therefore, the problems that in existing transcranial focused ultrasound nerve regulation and control, due to skull differences, a sound field is uncontrollable, the dose of a target area and the dose of a risk area are unbalanced, and navigation registration precision is insufficient are solved, and high-precision, high-safety and individualized transcranial ultrasound nerve regulation and control are achieved.

The invention discloses a TCP and multi-NTCP combination optimal dose calculation method and system based on deep learning, relates to the technical field of radiotherapy, and aims to solve the problems of insufficient multi-source data integration, unbalanced multi-organ protection and low individualized precision in traditional dose optimization. The method comprises the following steps: acquiring a CT image of a target patient, a tumor and normal tissue dose-volume histogram (DVH), baseline clinical data and follow-up data after radiotherapy of a patient group; constructing a multi-modal feature data set and an annotation data set through spatial alignment and normalization processing, training a deep learning joint prediction model, synchronously outputting TCP values corresponding to candidate doses and NTCP values of at least three organs at risk, and constructing a fitting curve; and through a single-organ net income formula, a multi-organ comprehensive net income formula and an optimal dose screening formula, quantifying income-risk balance and screening an optimal dose for maximizing the comprehensive net income. According to the invention, through cooperation of deep learning and an exclusive formula system, dynamic quantitative balance of multi-organ unbiased protection and tumor control is realized, individualized precision and clinical landing of radiotherapy dose planning are improved, and the method is suitable for precise radiotherapy scenes of various solid tumors.

The application provides an execution data determination method, device and equipment of a treatment device and a storage medium, applied to the technical field of medical instruments, device parameters of a treatment device used for performing helical tomotherapy are acquired, and detection data corresponding to a target user is acquired; thread effect model data corresponding to the treatment device is determined; variable pitch trajectory data corresponding to the target user is determined according to the device parameters, the detection data and the thread effect model data; a reverse dose optimization operation is performed based on the variable pitch trajectory data corresponding to the target user, and current execution data of the treatment device for the target user is determined. The application provides a systematic and high-robustness execution data determination method, effectively reduces the thread effect, and guarantees the treatment process of the target user.

This invention discloses a swarm intelligence-driven radiotherapy planning optimization system, which relates to the field of radiotherapy system optimization technology. The invention employs a swarm intelligence-driven multi-agent collaborative optimization framework, mapping each structure to an independent agent. A communication graph is constructed using geometric and dose features to achieve precise interaction. Combining self-organizing coordination and conflict fusion mechanisms, dose conflicts are dynamically handled. Fuzzy logic decision-making is introduced to adapt to clinical needs, ensuring compatibility with existing TPS systems and improving dose optimization accuracy. Conflict regions are finely allocated to reduce the risk of underdose in the target area or overdose in the oral radiation area (OAR). The system improves optimization efficiency; the intelligent communication graph reduces redundant interactions; self-organizing collaboration accelerates convergence; and the system is easy to implement and robust.

The invention discloses a self-adaptive radiotherapy plan re-optimization method and system, an electronic device and a medium wherein the self-adaptive radiotherapy plan re-optimization system comprises a deformation registration module for performing deformation registration to obtain a deformation field; the multi-time plan data module is used for importing multi-time plan data which comprises an ROI (Region of Interest) sketching area; the multi-time plan creating module is used for creating multi-time plan parameters; the deformation identification module is used for carrying out deformation analysis on the deformation field mu and identifying a deformation area; the grid optimization module is used for adjusting the priority of the ROI sketching region and optimizing the dose grid resolution of the deformation region to obtain the optimized dose grid resolution and distribution thereof; the plan re-optimization module is used for performing re-optimization to obtain an optimized radiotherapy plan; according to the method and the device, the technical problem that the dose optimization speed is difficult to improve under the condition of relatively low dose error in the setting of the radiotherapy dose grid resolution in the prior art is solved.

The application relates to the technical field of medical models, in particular to a manufacturing method and device of an individualized whole-body physical phantom, wherein the method comprises the following steps: obtaining body size parameters and physiological parameters of a target individual; then, based on the body size parameters and the physiological parameters, a digital human body surface element model of the target individual is established; based on a target tissue in the digital human body surface element model, an equivalent index of the target tissue is calculated; then, an equivalent material formula of the target tissue is determined according to the equivalent index; and finally, an additive manufacturing task of the target individual is performed according to the digital human body surface element model and the equivalent material formula, so as to manufacture a whole-body physical phantom of the target individual. Therefore, the problem that in the prior art, the whole-body phantom is usually based on fixed body size and standard posture, only covers limited body type and posture combinations, and is difficult to depict height, weight, age, gender, body fat distribution and external irradiation environment differences, thereby limiting the effectiveness of the phantom in individualized dose optimization and multi-scenario adaptation is solved.

The invention discloses a tumor patient individualized medication dose optimization method, which comprises the following steps: establishing a patient file, calculating an initial dose based on evidence-based knowledge, making a structured follow-up visit plan, integrating data from communities, families and patient reports, analyzing by using a fusion rule and an intelligent algorithm, and generating a dose optimization suggestion. After doctor-patient auditing, a situational medication reminding and recording tool is automatically updated and pushed, and finally continuous loop feedback and iteration of a treatment scheme are achieved; according to the invention, long-term follow-up visit and dosage decision are bound, and medication reminding, patient education and clinical support are combined, so that real-time, accurate and individualized adjustment of the medication dosage is effectively realized in a basic scene, and the treatment safety and compliance are improved.

The invention relates to the field of medical images, and discloses a mobile DR intelligent dose control and automatic exposure system which comprises a pre-exposure anatomical modeling module, a dynamic exposure control module and a post-exposure self-optimization module. Before exposure, the system constructs a three-dimensional anatomical model by using multi-modal data, and generates an initial AEC target matrix containing a plurality of virtual regions of interest. At the moment of exposure, the system carries out one-time accurate correction on a matrix deviated from the movement of the patient. During exposure, the system monitors the dose in parallel according to the corrected matrix to terminate exposure. After exposure, the system evaluates image quality, and combines scores with patient sign parameters obtained before exposure to update an independent dose correction model instead of a standard database, so as to realize closed-loop self-optimization. According to the method, the problem of exposure misalignment caused by movement of the patient is solved, the image quality consistency is improved through a robust individualized learning mechanism, and accurate dose optimization is realized.

The invention discloses a group-like intelligent driving radiation treatment plan optimization system, and relates to the technical field of radiation system optimization. According to the method, a multi-Agent collaborative optimization framework driven by class group intelligence is adopted, each structure is mapped into an independent Agent, and a communication graph is constructed through geometric and dose characteristics to realize accurate interaction; a self-organizing coordination and conflict fusion mechanism is combined, dose conflicts are dynamically processed, a fuzzy logic decision is introduced to adapt to clinical requirements, an existing TPS system is compatible, dose optimization accuracy is improved, conflict areas are finely distributed, and risks of target area shortage or OAR excess are reduced; the optimization efficiency is improved, redundant interaction is reduced through an intelligent communication graph, self-organization collaborative acceleration convergence is achieved, and the method is easy to land and high in robustness.

The application discloses a FAPI PET image-based tumor treatment dose optimization method and system, and belongs to the technical field of tumor treatment dose optimization. The application aims at the problems of poor applicability of the existing targeted fibroblast activation protein biological image evaluation method, lagging evaluation of treatment sensitivity, and limitations of the FDG PET tumor dose-response matrix model, and through collecting baseline FAPI PET images of tumor patients or experimental animals and mid-treatment feedback images, image deformation registration and target delineation are carried out; the SUV value and volume of the image target region voxels are obtained, and the tumor treatment sensitivity is calculated; the tumor voxel control probability is calculated according to the sensitivity, and then the tumor treatment dose is obtained, so that the early and accurate monitoring of tumor sensitivity is realized, and the adjustment of the tumor treatment scheme and the optimization of the dose are effectively guided.

This invention relates to the fields of medical health and artificial intelligence, and discloses a method for dynamic optimization of individualized low molecular weight heparin (LMWH) dosage for cancer patients based on reinforcement learning. The method includes: S1, collecting and preprocessing multi-dimensional clinical data from cancer patients, and enhancing the preprocessed data to generate time-series synthetic data; S2, constructing a reinforcement learning environment based on the multi-dimensional clinical data and time-series synthetic data, including defining a state space, action space, and reward function; S3, constructing an environment-adaptive deep reinforcement learning (EA-DRL) model as the dosage optimization model; training and optimizing the model in the reinforcement learning environment until it converges and obtains the optimal dosage decision strategy; S4, inputting the real-time dynamic clinical data of the patient to be decided into the trained dosage optimization model, and outputting an individualized LMWH dosage recommendation. This invention achieves individualized and precise drug administration, improving treatment efficacy and clinical drug safety.

The application relates to the technical field of intelligent anesthesia precise regulation and control, and discloses an anesthetic drug dose optimization method based on artificial intelligence. The method constructs a dynamic treatment interval, the boundary of which is self-adaptively adjusted according to real-time sedation depth and nociceptive stimulation level. Within the interval, pattern recognition is performed on continuous electroencephalogram signals and hemodynamic parameters to mark abnormal events deviating from the standard anesthesia state. An association network is established between drug effect chamber concentration and abnormal events, and a virtual drug response curve is generated to predict the trend of abnormal events under different doses. By comparing the coincidence degree of the predicted curve and the actual physiological trajectory, it is determined whether to start dose strategy reconstruction. When reconstruction is performed, the historical drug infusion points are analyzed to obtain the contribution weight of the abnormal events, an adjustment coefficient is allocated, and a new infusion sequence is integrated. The application realizes individualization and adaptive optimization of anesthetic administration, and improves the precision and safety of anesthesia depth control.

The invention relates to the technical field of medical operations, in particular to a multi-modal data fusion anesthesia postoperative complication intelligent prediction and dose optimization system which comprises a system body. The system body comprises a multi-modal data acquisition module, a dynamic hierarchical fusion module, a multi-stage hybrid prediction model, a closed-loop dose optimization module, an end-side cloud collaborative decision module and a clinical decision interpretation module. The system has the advantage that the anesthesia postoperative complication incidence prediction precision is improved, and in the actual use process, the system body, the multi-modal data acquisition module, the dynamic hierarchical fusion module, the multi-stage hybrid prediction model, the closed-loop dose optimization module, the end-side cloud collaborative decision module and the clinical decision interpretation module are used in cooperation; according to the method, the prediction accuracy of the postoperative complications can be greatly improved, the prediction accuracy of the postoperative complications can reach or exceed 92% through multi-modal data fusion and innovative design of the hybrid model, and the prediction reliability is improved.

The application discloses an alpha-nucleus drug in-vitro cell reaction prediction method and system based on multi-module mathematical modeling and a medium, the method comprises four sequentially connected modules of basic parameter input, pharmacokinetic prediction, cell absorption dose calculation and biological effect prediction, integrates a three-compartment kinetic model, a microdose point kernel convolution and a DNA damage repair kinetic model, and realizes quantitative simulation of a whole chain from drug distribution, microscopic energy deposition to cell survival. The application overcomes defects of an existing experience model, such as inability to accurately reflect high LET characteristics of alpha particles, neglecting bystander effects and repair kinetics, and significantly improves prediction accuracy. The method can quickly simulate the curative effect of different drugs, cell lines and dose schemes on a computer, greatly reduces research and development cost and period, and provides an efficient theoretical tool for new drug screening and dose optimization.

The present application discloses a radiotherapy positioning and dose optimization system based on deep learning and multimodal image fusion, including a multimodal image acquisition and fusion module, a tumor positioning module, an organ motion tracking module, a dose optimization calculation module, and a quality assurance and verification module; the multimodal image acquisition and fusion module is configured to compatibly and integratively integrate data generated by a plurality of medical imaging devices, and accurately match and fuse different modal images in three-dimensional space through an advanced image alignment algorithm, to form a high-precision fusion image containing information on anatomical structure, functional metabolism, and physiological activities.

The invention relates to the technical field of nuclear medicine imaging, in particular to a diagnosis device and method based on radionuclide distribution imaging, and the device comprises a detection module, a data processing module, an image reconstruction module, a dose optimization module and a fusion diagnosis module. According to the device, the image reconstruction quality is improved through multi-physical modeling and a self-adaptive iteration strategy, scanning parameters are dynamically adjusted to achieve low-dose efficient collection, and a comprehensive diagnosis result is generated in combination with anatomical images. Noise, scattering and equipment response nonlinear influence can be effectively reduced, imaging precision and quantitative analysis capacity under the low-dose condition are remarkably improved, and high-resolution functional images and accurate focus analysis support are provided for clinical diagnosis.

The invention discloses a radiographic image examination radiation dose optimization system and method based on intelligent perception. The method comprises the following steps: S1, generating an examination data set; s2, forming equipment state feature data in combination with historical operation data of the equipment; s3, generating an anatomical structure segmentation map of the target examination area; s4, generating a preliminary radiation dose distribution optimization scheme through the multi-modal data fusion model; s5, forming a radiation dose distribution scheme; s6, generating an image quality evaluation result; and S7, comparing the image quality evaluation result with the radiation dose distribution scheme, and if the image quality evaluation result does not meet the preset diagnosis requirement, dynamically adjusting the radiation dose distribution scheme, and updating the operation parameters of the image inspection equipment to form a new radiation dose distribution scheme. A safer and more efficient radiographic image examination scheme is provided for the patient, and meanwhile the diagnosis efficiency of a medical institution is remarkably improved.

A computer-implemented method for determining scan parameters includes receiving a set of input parameters. An average per piece of a nuclear imaging scanner having a predetermined field of view (FOV) is determined based on the input parameters, and at least one scan parameter is determined based on the average per piece of the nuclear imaging scanner.

The invention belongs to the technical field of biological medicine and molecular diagnosis, and particularly relates to a primer group for individualized medication detection of indobufen based on drug gene polymorphism and application of the primer group. Through analysis of 106 cases of thrombotic disease patient samples, screening and clinical verification are carried out from multiple literatures and databases, and finally 27 key SNP loci are determined. Aiming at the peak pattern overlapping problem in mass spectrometric detection, an adenine polynucleotide tail sequence is introduced to the 5'end of a single-base extension primer, peak pattern separation is remarkably improved, and parallel detection of multiple sites in the same system is realized. Clinical application shows that the system can carry out high-response type, normal-response type and low-response type layering on patients, and the consistency of a prediction result and follow-up visit exceeds 90%. Compared with traditional PCR + Sanger sequencing, the method has the advantages that the detection efficiency is high, the coverage is comprehensive, the interpretation is accurate, and a basis can be provided for individualized dosage optimization and risk assessment of indobufen.

The application provides a non-equidistant lattice distribution optimization method based on local dose constraints, comprising generating an initial lattice based on patient images and a delineated target region; pre-calculating and storing dose kernels based on a Monte Carlo algorithm; calling the dose kernels to perform fast dose optimization and calculation; establishing an independent peripheral subspace dose evaluation region and a local dose constraint condition for each lattice target region; establishing a multi-objective function for lattice target region position optimization; dynamically adjusting the lattice position and interval by using a fast simulated annealing method or a gradient descent method until a target region position distribution and a dose distribution satisfying the dose multi-objective function and the constraint condition are generated; and the application realizes accurate control of the peripheral valley dose of each lattice by dynamically adjusting the lattice interval and position and combining patient-specific anatomical structures, thereby solving the problems of uneven target region dose distribution and insufficient valley dose control in traditional equidistant lattice radiotherapy.

The invention discloses a particle radiotherapy adaptive plan optimization method and related equipment, and relates to the technical field of radiotherapy, and the method comprises the steps: constructing a fusion state representation reflecting the anatomical state and the treatment execution state of a patient at the same time according to the dynamic treatment log data generated by the patient in the particle radiotherapy execution process; inputting the fusion state representation into a pre-trained dose optimization model; the dose optimization model is configured to directly output a quantitative evaluation value of dose distribution generated by the executed part of the current treatment fraction according to the fusion state characterization; and based on the quantitative evaluation value, applying a preset decision rule, automatically generating and executing a self-adaptive dose adjustment instruction used for guiding the non-executed part of the current fractional treatment or the subsequent fractional treatment, thereby being capable of efficiently and accurately evaluating the dose distribution under the actual treatment condition, and improving the accuracy and safety of radiotherapy.

The invention discloses a multi-energy-level multi-machine-head dose optimization method, device and equipment and a storage medium, and the method comprises the steps: setting a machine head included angle and an irradiation mode based on target region distribution, and determining a radiation field set; aiming at each radiation field, based on ray path organization characteristics of the radiation field, by calculating correlation between a percentage depth dose curve and ideal dose distribution, screening an optimal irradiation energy level; calculating a dose deposition matrix based on the optimal energy level of each radiation field, and constructing an optimization model to perform joint optimization on all radiation field intensity graphs; segmenting the optimized intensity distribution, calculating an actual delivery dose, reducing the difference between the actual delivery dose and an ideal dose through iterative optimization, and finally outputting a dose optimization parameter. According to the invention, through combination of multi-machine-head cooperative irradiation and multi-energy-level adaptive selection, the treatment efficiency is significantly improved, and the dose distribution is optimized.

The invention discloses a bio-guided adaptive radiotherapy plan design method and system, and the method comprises the steps: constructing a fractional dose optimization model based on a biological equivalent dose; respectively collecting CBCT parameters of each fractional treatment, analyzing to obtain a change value, and evaluating according to the change value to obtain a cell related biological factor corresponding to the current fractional treatment; obtaining a segmented dose corresponding to the current fractional treatment by utilizing the fractional dose optimization model and combining the cell related biological factors corresponding to the current fractional treatment; the steps are repeatedly executed, and dynamic self-adaptive distribution of fractional doses is achieved until the radiotherapy plan is completed; according to the method, the technical problem that the risk of damage to normal tissues in late response may be underestimated due to the fact that the actual biological tolerance degree is not considered and the fractional dose is not adjusted and optimized according to the actual biological tolerance degree when a physical dose equipartition mode is adopted in the existing fractional treatment is solved.

The invention discloses an irradiation unit selection method for a proton arc treatment plan and related equipment, and relates to the technical field of radiotherapy, and the method comprises the steps: constructing at least one arc radiation field based on a medical image of a patient and delineated target region and endangered organ information, and carrying out the ray tracing of each radiation field angle, generating an initial set comprising a plurality of irradiation units; in the ray tracing process, coverage relation information and additional item information are generated and recorded; screening out an irradiation unit subset for subsequent dose optimization from the initial set based on the coverage relation information and the additional item information; performing dose optimization based on the screened irradiation unit subset, and generating a proton arc treatment plan; by introducing a target space unit concept and combining a dual-objective optimization model and a coverage constraint mechanism, precise screening of irradiation units is completed, and on the basis that existing hardware and processes do not need to be transformed and manual dependence is reduced, plan generation efficiency, stability and clinical adaptation expansibility are improved.

The invention relates to the field of medical image processing and radiotherapy, in particular to an intelligent delineation and dose optimization system for a gastrointestinal tumor radiotherapy target region, and solves the problems that traditional manual delineation of the target region is high in subjectivity, dose optimization is difficult to balance target region coverage and organ protection, accurate boundary control is lacked and the like. The system comprises a medical image acquisition module, a target region intelligent sketching module, a dose optimization module based on functional analysis and a treatment plan generation module, collects CT, MRI and PET multi-modal medical images of a patient, identifies tumors and organs at risk by using a machine learning algorithm, converts discrete data into continuous function representation in a Hilbert space, and generates a treatment plan according to the continuous function representation. A multi-objective optimization function is constructed, optimization is realized through variational iteration and adaptive weight adjustment, a Sobolev space regularization technology is used to control a dose gradient, an executable treatment plan is finally generated, and target region sketching accuracy and dose optimization quality are improved.