| CPC A61B 8/5207 (2013.01) [A61B 8/0883 (2013.01); A61B 8/4427 (2013.01); A61B 8/54 (2013.01); G06N 3/08 (2013.01)] | 16 Claims |
|
1. A system, comprising:
an ultrasound sensing device having a depth configuration setting; and
a computing device, the computing device comprising:
a communication interface configured to directly receive ultrasound echo data sensed by the ultrasound sensing device from a person, the received ultrasound echo data comprising a sequence of one or more ultrasound images each captured by the ultrasound sensing device using a particular depth configuration setting value;
a memory configured to:
store a machine learning model for producing results each in response to an ultrasound image in the sequence, the machine learning model including one or more convolutional blocks, wherein each convolutional block is configured to perform at least one aspect of determining whether depth configuration settings of an ultrasound device that obtained data to generate the ultrasound image are within tolerance of optimal, too large, or too small;
a processor configured to:
for each ultrasound image of the sequence, in response to its receipt by the communications interface:
subject the ultrasound image to the machine learning model to produce a result, the result indicating whether the ultrasound image is more consistent with similar training images annotated as having been captured using depth configuration setting values that are:
within tolerance of optimal,
too large, or
too small;
where the result indicates that the ultrasound image is more consistent with similar training images annotated as having been captured using depth configuration setting values that are within tolerance of optimal than with training images annotated as having been captured using depth configuration setting values that are too large or training images annotated as having been captured using depth configuration setting values that are too small, automatically cause capture of the sequence of ultrasound images to be ended;
where the result indicates that the ultrasound image is more consistent with similar training images annotated as having been captured using depth configuration setting values that are too large than with training images annotated as having been captured using depth configuration setting values that are within tolerance of optimal or training images annotated as having been captured using depth configuration setting values that are too small, automatically cause the next ultrasound image of the sequence to be captured using a depth configuration setting value that is smaller than the depth configuration setting value used to capture the ultrasound image; and
where the result indicates that the ultrasound image is more consistent with similar training images annotated as having been captured using depth configuration setting values that are too small than with training images annotated as having been captured using depth configuration setting values that are within tolerance of optimal or training images annotated as having been captured using depth configuration setting values that are too large, automatically cause the next ultrasound image of the sequence to be captured using a depth configuration setting value that is larger than the depth configuration setting value used to capture the ultrasound image.
|