147 results about "Radiotherapy treatment planning" patented technology

Disclosed are a method and an apparatus for manufacturing a radiation intensity bolus. The method comprises the steps of: (a) calculating, by a radiotherapy treatment planning unit, a received 3D radiation dose distribution, planning a bolus to be manufactured, and outputting radiation intensity modulation information; (b) receiving, by a bolus design unit, the radiation intensity modulation information, generating a conversion file for manufacturing bolus, and outputting information about a 3D structure of the bolus to be manufactured; (c) receiving, by a bolus manufacturing unit, the conversion file for manufacturing bolus, verifying a type, location, and size of the bolus to be manufactured, sending the verified data to a 3D printer, and manufacturing the bolus; and (d) obtaining, by an accuracy verification unit, information about a 3D structure of the manufactured bolus and evaluating manufacturing accuracy by comparing the information about the 3D structure of the manufactured bolus with the information about the planned bolus.

The present invention belongs to the technical field of medical images and computer, and relates to a target region automatic drawing method in radiotherapy treatment planning based on deep learning.The method comprises the following steps of: (1) performing preprocessing of patient's image data; (2) inputting the image data through preprocessing to a trained convolutional neural network model for prediction of the target region; and (3) performing edge extraction of the predicted target region to obtain an automatically drawing target region. The method provided by the invention can achieverapid target drawing and has high precision, for the same organ, doctors manually draw the organ for 5-10 min, the target region automatic drawing algorithm only needs 15 seconds, and therefore, compared to manual drawing, the time is reduced about 95%, the working efficiency of doctors can be greatly improved, and valuable time is provided for patients for timely treatment.

Method and system that allows patient dose response functions to be calculated, prior to treatment planning, for external photon beam radiotherapy. In one embodiment, for each location where a separate dose value is desired, referred to as a dose region, adjoint calculations are performed to calculate the adjoint solution fields associated with that dose region. Once potential beam directions are specified, a ray tracing process is performed to transport the adjoint solution fields out of the patient and to locations where treatment plan parameters may be specified. The output of this process is the dose response at each dose region resulting from a prescribed photon fluence, at a given location, direction, and energy.

The invention discloses a radiotherapy planning system, a determining device and a storage medium. The system includes one or more processors, and a storage device for storing one or more programs; the one or more programs are executed by one or more processors, and the one or more processors perform the following steps: acquiring image sequences distributed with time, wherein the image sequencesincluding sample points corresponding to the same location of an interest region; establishing an optimization model based on the sampling points and the weight of each image in the image sequences; and solving the optimization model to determine the radiation therapy plan. The above technical scheme solves the problem that in the prior art, a tumor target area generates periodic movements due tobreathing, heartbeat, and the like, so that the actual exposure dose of the target area and surrounding endangered organs is different from the target dose, the system provides a more precise radiotherapy plan for the movement target area, facilitates more precise treatment, effectively protects the surrounding endangered organs of the target area, and is suitable for use with most existing radiotherapy equipment that implements radiotherapy plans.

The invention relates to the field of radiotherapy and provides an image sampling method used in radiotherapy plan optimization. The sampling method comprises the steps that an image to be obtained is obtained, wherein the image to be obtained includes at least one interested area, the upper limit of the total number of sampling points and the number of sampling points included in subareas in the interested area are obtained, the interested area is divided into multiple subareas according to the upper limit of the total number of the sampling points and the number of the sampling points included in subareas in the interested area, a clustering analysis algorithm is utilized to conduct downsampling on the subareas to obtain the sampling points in the interested area. The sampling method can retain shape characteristics of organs or target section while decreasing the number of the sampling points and is conductive to improvement of radiotherapy plan effectiveness and accuracy of dosage distribution calculation.

A method for generating a robust radiotherapy treatment plan for a treatment volume of a subject. An adjusted voxel-specific dose objective is determined by “smearing” an initial voxel-specific dose objective a specified distance in at least one direction. A treatment plan based on such adjusted dose objective will be more robust with respect to setup uncertainties and organ movements. Smearing of the dose objective corresponds to adjusting the dose objective dose value of a voxel in accordance with dose objective dose values of voxels within the specified distance.

The present disclosure relates to systems, methods, and computer-readable storage devices for radiotherapy treatment planning. For example, a method may generate a treatment plan for a patient. The method may receive training data reflecting radiotherapy treatment data. The training data may include a feature vector and a target vector. The method may further determine a training model based on the feature vector and the target vector. The method may further receive testing data associated with the patient. The testing data may include a descriptive feature vector. The method may further determine a therapy model based on the descriptive feature vector and the training model. The therapy model may be used to generate the treatment plan.

The embodiment of the invention provides a head and neck lymph node and drainage area automatic sketching method based on deep learning. The method utilizes the symmetry of a human body structure to divide a head area into a left part and a right part for training and prediction, thereby indirectly increasing the data volume of model training, and reducing the scale of a deep learning model at thesame time. According to the method, a step-by-step processing optimized sketching strategy is used, the lymphatic drainage area easy to segment is achieved through the deep learning model, then the lymphatic drainage area is optimized and lymph nodes are segmented through the multi-task deep learning model, the relevance between the lymphatic drainage area and the lymph nodes is fully utilized, and the segmentation accuracy of the lymphatic drainage area and the lymph nodes is improved. According to the invention, an AI (artificial intelligence)-assisted contour sketching method is implemented in a radiotherapy plan work flow, so that the sketching consistency of the work efficiency of medical workers can be effectively improved, and the head and neck tumor radiotherapy precision is improved.

The invention discloses a method for calculating dose of a radiotherapy ray plane detector and a matched system. The method comprises the content of calibrating parameters of a depth deviation model of a measurement plane; receiving a three-dimensional external irradiation treatment plan for a patient and a depth position of the measurement plane from a radiotherapy treatment planning system (TPS); calculating a depth deviation of the measurement plane of each beam according to a therapy apparatus head angle of the beam and the depth deviation model of the measurement plane; calculating a dosedistribution on the measurement plane after the depth position shifts according to the treatment plan and the depth deviation of each beam; superposing the dose distribution of each beam on the measurement plane after shifting, and generating the dose on the calibrated measurement plane of the detector.

The invention discloses a method for calculating the invasion probability of a tumor clinical target area based on a hidden Markov model. The frequency of joint appearance of grid points in the three-dimensional tumor area is used to obtain the corresponding correlation rules; the primary tumor data of the new patient is read in, and the distance transformation is used to obtain the spatial distance from each voxel point to the primary tumor area; The probability of the primary tumor area is set as 1, and the invasion probability of each voxel point is related to the probability of adjacent voxels and the probability of the last observed state, and iteratively calculates outward from the primary tumor area; finally, all voxels are calculated The probability of a point being invaded by a tumor. The invention can assist the formulation of clinical radiotherapy plans, realize the automatic determination of the range of clinical radiotherapy target areas with different emission doses, reach the delineation standard for clinical application, and improve the working efficiency of doctors.

The invention discloses a computed tomography (CT) image reconstruction method based on magnetic resonance imaging (MRI). The CT image reconstruction method comprises the following steps: 1) reconstructing MRI by using a deep learning network, training the deep learning network, acquiring undersampling k spatial data of a to-be-detected object, and inputting the undersampling k spatial data of theto-be-detected object in the trained deep learning network to acquire online MRI of the to-be-detected object; and 2) using a bidirectional generative adversarial network to reconstruct a CT image through MRI. The CT image reconstruction method has the following advantages: (1) the MRI imaging speed is high; (2) the method has wide application ranges and can be applied to imaging of other parts of a human body as well as imaging of the lung; (3) the CT image is obtained through MRI reconstruction, and ionizing radiation of CT examination is avoided; and (4) the CT image obtained through reconstruction can also be used for radiotherapy plan formulation and PET attenuation correction.

The invention discloses a method for quickly realizing a Gamma analysis method in the posology verification of the radiotherapy treatment planning. Compared with the common method, the method disclosed by the invention has the differences that a GPU (graphic processing unit) is combined to read data, carry out logic processing and output; the GPU is adopted for processing volume element refining existing in the Gamma analysis method process in the posology verification of the radiotherapy treatment planning and processing the process of calculating the Gamma factor based on the refined volume element; and the whole process has the characteristics of large data volume, low data correlation, high degree of parallelism, high computing density and the like, and data have the same executive program. More calculating units simultaneously execute in parallel by the GPU, the operation time is shortened, the efficiency of the Gamma analysis method is higher, and the posology verification speed is improved.

The application discloses a system and a method for adaptive radiation therapy. The method may include: obtaining an initial treatment plan of a region of interest, wherein the initial treatment planincludes a first initial treatment fraction and a second initial treatment fraction; causing a radiation treatment device to deliver the first initial treatment fraction; obtaining a treatment fraction based on the second initial treatment fraction and the treatment record.

Embodiments of the present invention provide an integrated solution to radiotherapy treatment planning that enables accurate recording and accumulation of physical parameters as input (e.g., dose, dose rate, irradiation time per voxel, etc.). User-defined functions are evaluated to correlate the input parameters with 4D biological outcomes. The resulting biological parameters can be visualized as a biological outcome map to evaluate decisions, support decisions, and optimize decisions regarding the parameters of the radiotherapy treatment plan, for example, for supporting clinical trials and related clinical research.