Quality indicators for collection of and automated measurement on ultrasound images
Aspects of the technology described herein relate to techniques for calculating, during imaging, a quality of a sequence of images collected during the imaging. Calculating the quality of the sequence of images may include calculating a probability that a medical professional would use a given image for clinical evaluation and a confidence that an automated analysis segmentation performed on the given image is correct. Techniques described herein also include receiving a trigger to perform an automatic measurement on a sequence of images, calculating a quality of the sequence of images, determining whether the quality of the sequence of images exceeds a threshold quality, and performing the automatic measurement on the sequence of images based on determining that the quality of the sequence of images exceeds the threshold quality.
1. A method comprising:
calculating, during imaging, using a computing device in communication with an ultrasound device, a quality of a sequence of images collected by the ultrasound device during the imaging;
generating for display, during the imaging, an indicator of the quality of the sequence of images;
receiving a newest image collected during the imaging;
removing an oldest image from the sequence of images and adding the newest image to the sequence of images to form a new sequence of images;
calculating, during the imaging, a quality of the new sequence of images; and
generating for display, during the imaging, at least one indicator of the quality of the new sequence of images to replace the indicator of the quality of the sequence of images, the at least one indicator of the quality of the new sequence comprising an indication of whether the quality of the new sequence of images exceeds a threshold quality for performing an automatic clinical measurement,
wherein calculating the quality of the sequence of images comprises:
calculating a quality of each respective image in the sequence of images; and
calculating an arithmetic mean of the quality of each respective image in the sequence of images to produce the quality of the sequence of images,
wherein calculating the quality of each respective image in the sequence of images comprises:
for each respective image in the sequence of images:
calculating a clinical use metric comprising a probability that a medical professional would use the respective image for clinical evaluation;
calculating an automated analysis metric comprising a quality of an automated analysis performed on the respective image; and
calculating a geometric mean of the clinical use metric and the automated analysis metric to produce the quality of the respective image.
2. The method of claim 1 , further comprising generating for display instructions for moving the ultrasound device performing the imaging.
3. The method of claim 2 , wherein generating for display the instructions for moving the ultrasound device performing the imaging comprises generating for display the instructions simultaneously with generating for display the indicator of the quality of the sequence of images.
4. The method of claim 1 , wherein the sequence of images comprises a sequence of images collected during a fixed period of time prior to calculating the quality of the sequence of the images.
5. The method of claim 1 , wherein the sequence of images comprises a fixed number of images collected prior to calculating the quality of the sequence of the images.
6. The method of claim 1 , wherein calculating the quality of the sequence of images comprises analyzing the sequence of images using deep learning techniques.
7. The method of claim 6 , wherein calculating the quality of the sequence of images comprises providing at least one image in the sequence of images as an input to a statistical model.
8. The method of claim 7 , wherein calculating the quality of the sequence of images comprises using the statistical model to obtain an output that is indicative of the quality of the at least one image.
9. The method of claim 1 , wherein the automatic clinical measurement comprises automatic measurement of an ejection fraction.