JPWO2020038781A5 - - Google Patents

Claims (20)

It is an ultrasonic imaging system
An ultrasonic transducer configured to acquire an echo signal in response to an ultrasonic pulse transmitted towards the patient's target area,
A graphical user interface configured to display a biometric tool widget for obtaining measurements of anatomical features within the target area from at least one image frame generated from the ultrasound echo.
One or more processors that communicate with the ultrasonic transducer,
Determine a confidence metric that indicates the accuracy of the measurements.
An ultrasonic imaging system comprising a processor configured to display a graphical indicator corresponding to the reliability metric on the graphical user interface. The processor is configured to determine the reliability metric by inputting the at least one image frame into a first neural network trained with imaging data having the anatomical features. The ultrasonic imaging system according to 1. The processor includes patient statistics, pre-measurements of the anatomical features, measurements derived based on the pre-measurements, and anatomical landmarks in which the image frame is associated with the anatomical features. 2. The reliability metric is further configured to determine the reliability metric by inputting the probability, the quality level of the image frame, the setting of the ultrasonic transducer, or a combination thereof into the first neural network. The ultrasonic imaging system described in. The ultrasonic imaging system according to claim 3, wherein the probability that the image frame contains the anatomical landmark indicates whether a correct imaging surface has been obtained for measuring the anatomical feature. The ultrasonic imaging system according to claim 1, wherein the graphical user interface is not physically coupled to the ultrasonic transducer. The ultrasound imaging system according to claim 3, wherein the anatomical features are fetal or uterine related features and the derived measurements have an age-adjusted risk of pregnancy age or chromosomal abnormalities. The ultrasonic imaging system according to claim 3, wherein the patient statistics include the age of the mother, the weight of the patient, the height of the patient, or a combination thereof. The quality level of the image frame is the distance of the anatomical feature from the ultrasonic transducer, the orientation of the biometric tool widget with respect to the ultrasonic transducer, the distance of the beam focal region to the anatomical feature, and the frequency. The ultrasonic imaging system according to claim 3, based on noise estimates obtained through analysis, or a combination thereof. The processor
A threshold is applied to the confidence metric to determine if the measurement should be reacquired.
The ultrasonic imaging system according to claim 1, further configured to display in the graphical user interface an indication as to whether the measured value should be reacquired. The ultrasonic imaging system according to claim 1, wherein the biometric tool widget includes a caliper, a trace tool, an ellipse tool, a curve tool, an area tool, a volume tool, or a combination thereof. The ultrasonic imaging system according to claim 1, wherein the anatomical feature is a feature related to a fetus or a uterus. The ultrasonic imaging system according to claim 1, wherein the processor is further configured to determine a pregnancy age and / or a weight estimate based on the measurements. The first neural network produces a multi-layer perceptron network configured to perform supervised learning using stochastic dropouts, or a compressed representation of the image frame and the measurements, and the compressed representation. The ultrasonic imaging system according to claim 2, wherein the autoencoder network is configured to be compared with a manifold of population-based data. It is a method of ultrasonic imaging, and the above method is
The step of acquiring an echo signal in response to an ultrasonic pulse transmitted to the patient's target area by a transducer operably coupled to the ultrasonic system,
A step of displaying a biometric tool widget for obtaining measurements of anatomical features within the target area from at least one image frame generated from the ultrasound echo.
The step of determining the reliability metric indicating the accuracy of the measured value,
A method comprising the steps of displaying a graphical indicator corresponding to the reliability metric in a graphical user interface. 14. The method of claim 14, wherein the step of determining the confidence metric comprises inputting the at least one image frame into a first neural network trained with the imaging data having the anatomical features. Patient statistics, pre-measurements of the anatomical feature, measurements derived based on the pre-measurement, probability that the image frame contains anatomical landmarks associated with the anatomical feature, said image. 15. The method of claim 15, further comprising the step of inputting the quality level of the frame, the setting of the ultrasonic transducers, or a combination thereof into the first neural network. 16. The method of claim 16, wherein the patient statistics have the age of the mother, the weight of the patient, the height of the patient, or a combination thereof. 16. The method of claim 16, wherein the anatomical features are fetal or uterine related features and the derived measurements have an age-adjusted risk of pregnancy age or chromosomal abnormalities. 15. The method of claim 14, wherein the anatomical feature is a fetal or uterine-related feature, further comprising the step of determining a pregnancy age and / or body weight estimate based on the measurements. .. A non-transitory computer-readable medium having executable instructions that, when executed, causes the processor of the medical imaging system to perform the method of any one of claims 14-19. ..