6 results about "Dose reduction" patented technology

The application discloses a fault scanning control method and device, a fault scanning equipment and a storage medium. The method comprises the following steps: identifying a key anatomical structure of an initial projection image based on a pre-trained trajectory planning model, generating a probability distribution map, determining a sparse scanning angle sequence and corresponding first scanning parameters, densely sampling and appropriately increasing a radiation dose in a high-weight area, and sparsely sampling and reducing a dose in a low-weight area; controlling the fault scanning equipment to perform scanning, obtaining first projection data and reconstructing the first projection data into a sparse reconstruction image; performing multi-modal fusion and scoring on the sparse reconstruction image and the current scanning parameters through an image quality evaluation model, adaptively optimizing scanning instructions according to the probability distribution map, a fusion feature vector, an image quality score, an equipment state and historical action data, generating second scanning parameters, making the scanning trajectory more continuous and smooth through an artificial intelligence technology, and realizing regional adaptive regulation and control of angles, doses and paths, so that the imaging resolution can be improved.

Methods, systems, and computer readable media are provided for reduced dose angiography using machine learning (e.g., deep learning) using consistency metrics, the consistency metric indicates a degree of similarity between an estimated segmentation of the angiographic image generated by the machine learning model and a reference angiographic image provided as input to the segmentation of the machine learning model. Briefly, the techniques described herein may use a neural network trained to preserve / maintain the quality of angiographic images by employing consistency metrics while reducing the dose of angiography of potentially harmful chemical contrast agents and / or X-ray radiation.

This invention discloses a method and system for effectively reducing X-ray radiation dose during electrocardiogram (ECG) scanning, relating to the field of artificial intelligence technology. The method includes: acquiring real-time ECG signals of the subject, identifying the R-wave and its occurrence time, and calculating the RR interval between adjacent R-waves; dividing the subject's cardiac cycle based on the RR interval and the R-wave occurrence time, and determining the intense cardiac motion phase and diastolic phase of each cardiac cycle; during the intense cardiac motion phase, controlling the X-ray tube mA value to decrease to a dose reduction mA value below the source mA value; when the current time enters the diastolic phase, controlling the X-ray tube mA value to recover from the dose reduction mA value back to the source mA value; after determining that the X-ray tube mA value has recovered and stabilized at the source mA value, a trigger signal is activated, and the acquisition of projection data is initiated based on the trigger signal. This method helps solve the problem that existing technologies cannot effectively reduce X-ray radiation dose during ECG scanning.

The invention discloses a tomography control method and device, tomography equipment and a storage medium, and the method comprises the steps: carrying out the key anatomical structure recognition of an initial projection image based on a pre-trained trajectory planning model, generating a probability distribution diagram, determining a sparse scanning angle sequence and a corresponding first scanning parameter, dense sampling is adopted in the high-weight area and the radiation dose is properly increased, and sparse sampling is adopted in the low-weight area and the radiation dose is reduced; controlling the tomography equipment to execute scanning, obtaining first projection data and reconstructing the first projection data into a sparse reconstructed image; and performing multi-modal fusion and scoring on the sparse reconstructed image and the current scanning parameter through an image quality evaluation model, adaptively optimizing a scanning instruction according to a probability distribution diagram, a fusion feature vector, an image quality score, an equipment state and historical action data, generating a second scanning parameter, enabling a scanning track to be more continuous and smoother through an artificial intelligence technology, and improving the scanning efficiency. Regional adaptive regulation and control of angles, doses and paths are realized, and the imaging resolution can be improved.

The application provides a dose calculation method, device, medium and product, and relates to the technical field of dose calculation. The method comprises the following steps: determining a dose calculation point and a cylinder string corresponding to the dose calculation point; calculating total dose contribution of the cylinder string to the dose calculation point according to a convolution kernel corresponding to the cylinder string and a line segment of the cylinder string, wherein parameters of the convolution kernel are obtained by fitting dose data calculated based on a Monte Carlo method; and calculating dose data of each dose calculation point based on the total dose contribution. In the application, the dose contribution of each cylinder string to the dose calculation point is directly calculated by using the convolution kernel and the line segment of the cylinder string, so that the introduction of errors can be effectively reduced, the calculation amount can be effectively reduced, the calculation precision can be improved, the time and the calculation resources required for dose calculation can be reduced, and the demand of clinical application can be effectively met.