31 results about "Dose estimation" patented technology

Supervised and unsupervised learning schemes may be used to automatically label medical images for use in deep learning applications. Large labeled datasets may be generated from a small initial training set using an iterative snowball sampling scheme. A machine learning powered automatic organ classifier for imaging datasets, such as CT datasets, with a deep convolutional neural network (CNN) followed by an organ dose calculation is also provided. This technique can be used for patient-specific organ dose estimation since the locations and sizes of organs for each patient can be calculated independently.

Techniques are disclosed for estimating patient radiation exposure during computerized tomography (CT) scans. More specifically, embodiments of the invention provide efficient approaches for generating a suitable patient model used to make such an estimate, to approaches for estimating patient dose by interpolating the results of multiple simulations, and to approaches for a service provider to host a dose estimation service made available to multiple CT scan providers.

Supervised and unsupervised learning schemes may be used to automatically label medical images for use in deep learning applications. Large labeled datasets may be generated from a small initial training set using an iterative snowball sampling scheme. A machine learning powered automatic organ classifier for imaging datasets, such as CT datasets, with a deep convolutional neural network (CNN) followed by an organ dose calculation is also provided. This technique can be used for patient-specific organ dose estimation since the locations and sizes of organs for each patient can be calculated independently.

The invention provides a gamma energy spectrum dose automatic measuring device and a measuring method. The measuring device comprises a gamma spectrometer and secondary instrument. The gamma spectrometer and the secondary instrument are connected through a communication interface. The secondary instrument comprises a computer provided with a gamma energy spectrum dose automatic estimation program, a printer and a mobile power supply. The computer is connected with the printer and the mobile power supply through a communication interface. The gamma energy spectrum dose automatic measuring method which uses the gamma energy spectrum dose automatic measuring device comprises the steps that gamma energy spectrum is measured by the gamma spectrometer, and the measurement software of the gamma spectrometer can automatically control the measurement process; the communication interface of the gamma spectrometer is used to automatically save an energy spectrum file into the secondary instrument; the gamma energy spectrum dose automatic estimation program in the secondary instrument is turned on, wherein the program can automatically read and analyze the gamma energy spectrum file to acquire gamma energy spectrum information; and finally gamma energy spectrum dose automatic measuring is realized according to a dose result calculated by the gamma energy spectrum dose estimation program.

The invention discloses a low-dose double-tracer PET (positron emission tomography) reconstruction method based on an attention mechanism, namely, a low-dose double-tracer PET image reconstruction problem is solved by utilizing a convolutional network model based on the attention mechanism, and standard dose estimation and double-tracer PET signal separation are realized in a sinogram. According to the method, by means of a powerful feature extraction tool of deep learning, a single tracer PET image of a standard dose can be reconstructed from a low-dose double-tracer PET sinogram, and the method has robustness for individual differences, tracer combinations and sampling protocols.

The invention discloses a dose estimation method and system based on maximum food consumption of residents. The method comprises the following steps: S1) carrying out diet survey on the residents within a preset radius range of a nuclear power station to obtain weekly consumption for various foods of the residents, and calculating annual consumption for various foods of the residents; S2) rankingthe annual food consumption of individuals in an ascending order, then, taking the annual food consumption of a person ranked in the 90% percentile, and reallocating the annual food consumption of theindividuals according to share of average consumption of each kind of food to obtain annual maximum consumption of each kind of food; and S3) substituting the annual maximum consumption of each kindof food into an internal irradiation dose calculation formula to obtain internal irradiation dose of each resident, and calculating the total dose of the nuclear power plant to the residents accordingto the internal irradiation dose. The provided method and system calculate the maximum food consumption, consistent with the actual situation, of the residents by using a percentile method, thereby making the calculated resident dose more accurate.

The invention belongs to the technical field of radiation dose estimation and analysis, and discloses an enamel radiation dose prediction method and system, a storage medium and a terminal. Sampling points which are the same as the prepared BGS substrate and the prepared RIS substrate are selected, and an EPR spectrogram value on a corresponding point of the to-be-predicted sample is obtained; performing noise reduction processing on the EPR spectrogram of the current to-be-predicted sample by using fast Fourier transform; solving the RIS intensity of the to-be-predicted sample through the improved matrix; and according to the linear dose response relationship, obtaining a radiation dose value of the to-be-predicted sample. According to the method, the calculated amount is equal to that of an original matrix method, new model parameters are not introduced, the number of the parameters is small, the fitting effect is good, the fitting error is smaller than 1%, EPR enamel dose estimation of a lower dose can be achieved, and in a low-dose area smaller than 0.3 Gy, the difference between the calculated irradiation dose value and a true value is smaller than or equal to 16%.

A method for extending initial image data of a subject for dose estimation includes obtaining first image data of the subject for dose calculation, wherein the first image data has a first field of view. The method further includes obtaining second image data for extending the field of view of the first image data. The second image data has a second field of view that is larger than the first field of view. The method further includes extending the first field of view based on the second image data, producing extended image data.

The invention discloses a nuclear emergency biological dose estimation mobile experiment platform which comprises a mobile chassis and an experiment cabin body, the experiment cabin body is installed on the mobile chassis, the experiment cabin body comprises a sampling room, a sterile culture room, a specimen preparation room and a film reading and biological dose estimation room which are connected in sequence, a first cabin door is arranged on the sampling room, a first workbench is installed in the sampling room, a cell culture box, a super clean bench and an ultraviolet disinfection device are installed in the sterile culture room, an experiment table, a water pool and a centrifugal machine are installed in the specimen preparation room, and a second workbench and a seat are installed in the specimen reading and biological dose estimation room. The experiment cabin body arrives at a nuclear accident place through the mobile chassis, working personnel in the sampling room carry out work such as blood sampling and information input on the detected personnel; peripheral blood lymphocytes of examinees can be cultured in the sterile culture room; chromosome specimens of peripheral blood lymphocytes for analysis can be prepared in the specimen preparation room; and analysis and evaluation of chromosome specimens can be carried out between film reading and biological dose estimation.

In accordance with a method for dose estimation for the irradiation of an object, a model with a total number of spatial elements is provided on a memory element. For each spatial element, the model specifies a material composition of the object. A neighborhood material composition is determined for a neighborhood of spatial elements depending on the model by a computing unit. A radiation dose for the neighborhood with regard to an ionizing radiation is determined with aid of a simulation depending on the neighborhood material composition. A dose distribution for the object with regard to the ionizing radiation is determined based on the radiation dose for the neighborhood.