42 results about "Intensity modulate radiotherapy" patented technology

In a method for sequentially generating segment fields for use in delivering intensity modulated radiotherapy an input continuous intensity map is generated. A segment field is generated directly from the input intensity map. A residual continuous intensity map is generated that is based on the respective photon fluence contributions from the input intensity map and a fractionally intensity map corresponding to the segment field. These steps are repeated for a number of iterations to generate a like number of additional segment fields and residual maps derived therefrom. In each iteration, the residual map generated in the previous iteration is used as the input intensity map.

The invention discloses a predication method for three-dimensional dose distribution in intensity modulated radiation therapy plans. The method includes steps of (1) collecting valid intensity modulated radiation therapy plan data and forming a case database; (2) dividing a PTV and different to-be-endangered organs of patients into a plurality of voxels according to the resolution ratio of CT images; (3) extracting anatomical characteristics of each patient in the database; (4) extracting dose characteristics of each patient in the database; (5) constructing an artificial neural network, inputting the anatomical characteristics and the dose characteristics of the patients, and learning the mapping relation between the anatomical characteristics and the dose characteristics by the aid of the artificial neural network, and obtaining a correlation model of the anatomical characteristics and the dose characteristics; (6) using the correlation model to predicate the three-dimensional dose distribution of a new patient. The application of said method is using the dose distribution predication method for dose prediction for to-be-endangered organs of patients and quality control is achieved. By adopting the above method, predication of three-dimensional dose distribution in intensity modulated radiation therapy plans can be realized and the method can be applied to a quality control link.

The invention discloses an image feature and smart regressive model-based method for optimizing an intensity modulated radiotherapy plan, which comprises the steps of: firstly, establishing a database of an expert-level intensity modulated radiotherapy plan, and storing a record of each intensity modulated radiotherapy case in the database; secondly, establishing a smart regressive model of medical image feature-based intensity modulated radiotherapy plan optimization parameters by supervised machine learning according to relevance information between the original medical image characteristics in the database of the expert-level intensity modulated radiotherapy plan and the intensity modulated radiotherapy plan optimization parameters; carrying out image analysis on a medical image of a specific intensity modulated radiotherapy object, and carrying out characteristic extraction; inputting the image characteristics into the smart regressive model, and outputting the intensity modulated radiotherapy plan optimization parameters; and setting the intensity modulated radiotherapy plan optimization parameters on a therapy plane system (TPS) according to the results, and operating a plan optimization function of the TPS to obtain an optimal therapy plane of intensity modulated radiotherapy.

The invention relates to an anti-collision control method for leaves of a multileaf collimator. The anti-collision control method for the leaves of the multileaf collimator includes the following steps that in static intensity modulated radiotherapy, the difference between the real-time positions and the target positions to which the leaves move is compared with the difference between the initial positions of the leaves and the target positions to which the leaves move to keep adjusting the operating speed of a motor for driving the leaves to move; the closer the real-time positions of the leaves are to the target positions, the lower the operating speed of the motor is, and then collision between the leaves caused when the two sets of leaves are closed can be effectively prevented; in dynamic intensity modulated radiotherapy, when whether the motor moves forward or backward is judged, the number of pulses emitted by an actual motor position coder and measured by the i sub-field in real time is compared with the upper limit value SlidePosH and the lower limit value SlidePosL to judge whether the motor brakes or keeps sliding forward due to inertia or keeps running at a certain speed of Vo[i]. Thus, the position actually reached by the motor in the operating process is basically identical to the target position, it is guaranteed that the error of the position is within +/-e, faults such as mechanical damage caused by leaf collision are prevented, and the end faces of the leaves are prevented from leaking rays.

The clinical artificial trial and error method repetitively adjusts the dose constraint mode to optimize the plan because of the multi-objective performance of plan optimization and the unknown performance of dose constraint, which has the problems of low plan efficiency and quality uncertainty. The invention discloses an intensity modulated radiation therapy multi-objective optimization method based on voxel weight factor. The thinking mode in design of the plan designer is simulated and the constraint is automatically adjusted so as to guarantee the plan quality. According to the method, theconstraints are sorted and classified according to the clinical degree of importance for the area of interest dose constraints to form a constraint priority list, and then the dose constraints are adjusted according to the list. When the obtained solution does not meet the current constraint, the violation items are relaxed in turn according to the ascending order of priority; and when the obtained solution meets the current constraint, all the items are tightened (the violation dose constraints are tightened firstly) in turn according to the descending order of priority. The method is used for the cervical cancer patient and the result shows that the workload of the plan designer can be reduced and the plan quality can be improved.

The invention is applied to solve the deadlock fault of vanes and the zeroing position limit problems in intensity-modulated radiotherapy, while the prior art can only retune the vanes from the deadlock state and perform zeroing by dismantling. The invention realizes zeroing and position limit by adopting opposite type photoelectric detection; and adopts multistage switch to return the vanes from the deadlock state. The invention can return a system to the normal operation state under software control. In the opposite type photoelectric detection, a narrow far infrared ray beam is arranged at each end of a multi-vane grate. An infrared ray receiving terminal sets the tail end of each vane, which is positioned at the edge of the infrared ray, to be a zero point to limit the vane position, and codes the zero position of each vane corresponding to the encoder code of a motor at the same time. The multistage switch is realized through controlling a micro-motor with an encoder by an electric control element, and a system control unit detects the occurrence of deadlock according to the vane position information which is returned from the motor encoder. If the deadlock occurs, the system control unit sends a control signal to a motor driving unit to increase control voltage stage by stage, so as to gradually increase the driving force of a driving chip, and further allow the vanes to return from the deadlock state.

The invention discloses a method for predicting the average dose of organs at risk in intensity-modulated radiotherapy, comprising the following steps: 1) Obtaining the functional relationship formula between Vox/Vx and Dmx/Dp, wherein, Vx is the volume of organs at risk, and Vox is The intersection volume of the organ at risk and the planned target area, Dp is the prescribed dose, and Dmx is the average dose of the organ at risk; 2) The average dose of the organ at risk is predicted by the functional relationship formula. The specific application of this prediction method includes the following steps: A) determine Dp; B) obtain the average dose Dmx1 of the relevant organs at risk according to the functional relationship formula between Vox/Vx and Dmx/Dp obtained by the prediction method; C) carry out simulation adjustment Strong optimization, get the average dose Dmx2; D) Compare Dmx1 and Dmx2; E) When Dmx2≤Dmx1, meet the standard; Dmx2>Dmx1, continue to optimize the intensity modulation. The invention is easy to collect data, conveniently establishes an organ-at-risk prediction model suitable for corresponding departments' treatment planning systems and equipment, and reduces the influence of subjective factors in the optimization process of radiotherapy plans.

The invention discloses a dynamic intensity-modulated radiotherapy method based on a quadratic programming model suppressing total beam-out time. The method comprises: modeling according to a clinical dose target and constraints; mathematically describing a radiation field intensity pattern through front-drive and rear-drive blade movement matrixes, and on such basis, establishing convex programming conditions with upper and lower blade collision constraints and typical blade tongue-and-groove effect constraints; establishing corresponding convex programming conditions by analyzing a relation between blade movement speed and total beam-out time and the blade movement matrixes; finally, with respect to the defects that blade unidirectional movement modulation doses are limited and blades are abraded by random reciprocating motion, establishing a blade bidirectional movement mode. The dynamic intensity-modulated radiotherapy method that can meet most clinical implementation software-hardware constraints and needs is successfully obtained. The dynamic intensity-modulated radiotherapy method can be directly used for mathematical modeling and solving of volumetric modulated arc therapy after the radiation field angle is raised to a certain amount.

The invention provides a rectal cancer radiotherapy plan automatic design method based on deep learning. The method comprises the steps: establishing a U-Net neural network used for deep learning, andestablishing a case database, wherein the case database is clinical intensity modulated radiotherapy plan data of rectal cancer; performing deep learning on the case database to train the U-Net neural network; transmitting a img file of the CT positioning data to the trained U-Net neural network to obtain a prediction target area and prediction dose distribution output by the U-Net neural network; obtaining a dose objective function according to the prediction target area and the prediction dose distribution; and designing a radiotherapy plan by using a Pinnacle planning system according to the prediction target area and the dose objective function. Therefore, the rectal cancer radiotherapy plan automatic design method based on deep learning integrates the target area sketching technology, the dose prediction technology and the automatic planning technology, and the full-automatic design process of the individualized radiotherapy plan is realized in combination with the Pinnacle plansystem.

The invention provides a dosage verification method and system based on artificial intelligence. The method comprises the steps of: acquiring the radiation field area, the radiation field modulation complexity and the blade motion and dosage characteristic parameters of an intensity modulated radiation therapy plan; establishing a regression model based on a machine learning model, taking the characteristic parameters as an input sample of the machine learning model, and setting a standard gamma passing rate as an output of the machine learning model; establishing a classification model basedon a machine learning model, taking feature parameters as an input sample of the machine learning model, and taking the standard gamma passing rate as an output of the machine learning model; performing sample training to obtain a regression model and a classification model for optimal prediction, predicting the gamma passing rate of the to-be-verified characteristic parameters according to the optimal prediction model, and predicting and classifying clinical intensity modulated radiation therapy plans. According to the invention, the problems of long consumed time and high labor cost of the existing radiotherapy dosage verification work can be solved, and the efficiency and the quality can be improved.

The invention provides a body position fixing device for spiral tomography of patient with large breasts after breast-conserving surgery of breast cancer. According to the body position fixing device,a prone design is adopted, and a 3D printed breast fixing cover and a breast tray are correspondingly and specially arranged for an affected side breast and a healthy side breast of the patient. According to the body position fixing device, the influence of respiratory movement on the breast position can be avoided, an arc holding claw is firstly used for gathering and locating the affected sidebreast, then the personalized breast fixing cover is installed to completely fix the whole affected side breast, when the spiral tomography is conducted, the phenomenon of breast swing can be avoided,it can be guaranteed that the affected side breast is consistent with positioning of a radiotherapy target area in height during each radiotherapy, thus the repeated positioning accuracy is high, andthe needs of intensity-modulated radiotherapy of a TomoTherapy system can be effectively met; the breast tray is directly installed on the healthy side breast, the healthy side breast is lifted and covered by the breast tray, and thus the healthy side breast can be prevented from entering the field of irradiation due to swing.

The invention discloses an in-beam high-energy radiotherapy device with a PET developing function. The in-beam high-energy radiotherapy device comprises radiotherapy equipment and open-loop PET developing equipment, wherein the radiotherapy equipment comprises a vertical fixed rack, an L-shaped rotary rack, a circular therapy head and an accelerator, a vertical portion of the L-shaped rotary rack is rotatably mounted to the vertical fixed rack through a fixed bearing, an open-loop portion of the open-loop PET developing equipment is opposite to the circular therapy head, and the accelerator is arranged in the rotary rack and is connected with the therapy head through a beam current pipeline; the open-loop PET developing equipment is mounted in the L-shaped rotary rack through a slide rail assembly and a support assembly. According to the device, accurate three-dimensional biological conformal intensity-modulated radiotherapy and verification are achieved really.

The embodiment of the invention provides a dose rate intensity modulation method and device, computer equipment and a storage medium, and relates to the field of intensity modulated radiotherapy. In the embodiment of the invention, firstly, a current actual dose, a current target dose and a current pulse frequency are obtained, and the current pulse frequency is used for representing a dose rate of a radiation beam emitted by a radiation source device; then determining an output pulse frequency according to the current actual dose, the current target dose and the current pulse frequency; and finally, the dose rate of the radiation beam emitted by the radiation source equipment is updated according to the output pulse frequency. According to the embodiment of the invention, the output pulse frequency is determined based on the current actual dose, the current target dose and the current pulse frequency, and the dose rate of the radiation beam emitted by the radiation source equipment is updated so as to continue to irradiate the target region; the degree of deviation between the actual radiotherapy effect and the result specified by the treatment plan is within an acceptance range.

The present application provides a method, device and computer system for determining beamlet intensity in a radiotherapy system. The method according to the present application is based on the compressive sensing theory by introducing the position of the radiation field and the sub-beam into the traditional objective function to obtain the objective function. Then the objective function is optimized to select a backup field from multiple fields. Based on the spare fields, the sub-beam intensity is obtained by optimizing the traditional intensity-modulated radiotherapy plan.

The invention discloses a method for computer-assisted designing noncoplanar volumetric rotational intensity modulated radiotherapy plan. The content of the method includes the steps that medical images of a diseased area and a peripheral human tissue of a patient are collected through an imaging device, three-dimensional contour data of a region of interest are collected through a software assembly, the total hop count is collected through a user input device, a target and a constraint condition are optimized, the hop count of a treating device is taken as a time unit, the total hop count isequally divided, a group of machine parameters are selected randomly for all equal diversion points, a group of machine parameters with the equal diversion points of any adjacent hop count meeting theconstraint condition are screened and retained, a group of initial VMAT plan is generated on the basis of the machine parameter, on the premise of the constraint condition is met, the plan is updatedby using a direct optimizing algorithm, dosage gridding is built according to patient data, dosage distribution is calculated based on the dosage gridding, an objective function value is calculated,the plan is updated by repeatedly using the direct optimizing algorithm until a suspensive condition is met, and an optimized plan is output.

The invention provides a method for setting a tolerance limit value for monitoring an intensity modulated radiation therapy dose verification process, and belongs to the field of intensity modulated radiation therapy dose verification. The method is insensitive to the distribution of the gamma passing rate in the intensity modulated radiation therapy dose verification process, so that the influence of non-normality on control limit value calculation is reduced. Therefore, the tolerance limit value obtained through the method is more stable and reliable. The tolerance limit value obtained based on the method has good performance in monitoring the intensity modulated radiation therapy dose verification process; an intensity modulated radiation therapy plan with the out-of-control problem can be effectively detected, and in addition, the workload of a radiation therapy physicist for investigating the "problem" plan is reduced.

The invention relates to a high-energy electron line multi-degree-of-freedom intensity modulated radiation therapy system based on longitudinal magnetic confinement. The system comprises longitudinal magnetic confinement high-energy electron line radiation therapy equipment and a multi-degree-of-freedom integrated optimization method for high-energy electron line intensity modulated radiation therapy. The equipment comprises a radiotherapy machine and a magnetic confinement device. The radiotherapy machine comprises a linear accelerator or a cyclotron for accelerating electrons and a multi-stage electron beam collimator, the magnetic confinement device comprises a three-stage split perforated coil, and the central axis of the coil coincides with the central axis of a high-energy electron beam. The optimization method comprises the following steps: 1, optimizing the head angle of the radiotherapy machine, and determining a beam arc section; 2, optimizing the angle of a collimator, and determining a beam dynamic track; and 3, synchronously optimizing the electron line energy and the beam intensity, and determining an optimal electron line multi-degree-of-freedom intensity modulated radiotherapy plan. Lateral scattering of high-energy electron rays in the air and in the body of a patient can be effectively reduced, multi-degree-of-freedom intensity modulated radiotherapy of the magnetic confinement high-energy electron rays is realized, and the curative effect of the patient is improved.

The invention discloses a method used for direct segment optimization in intensity-modulated radiotherapy. The method comprises steps of acquiring basic information of a patient; calculating a targetfunction gradient matrix, and using a fuzzifier to eliminate noise; using an adaptive threshold segmentation principle to generate a new segment shape; optimizing the segment weight and optimizing allexisting segment weights; optimizing the segment shape and optimizing all existing segment shapes; and outputting information of three-dimensional dosage distribution, DVH curves, the number of the segments, the segment shapes and the segment weights. The invention also discloses a system including the method used for direct segment optimization in intensity-modulated radiotherapy. The system comprises an information acquisition module, a preprocessing module, a segment generation module, a segment weight optimization module, a segment shape optimization module and an information outputting module. According to the invention, problems of low accuracy and low optimization efficiency of segment shapes in the current optimization methods and optimization systems are solved.