Ultrasound method
A computer-implemented method of automatically identifying a reference vessel in an ultrasound image, the method comprising: segmenting the image to identify an organ; locating a predetermined anatomical landmark specific to the organ; identifying appropriate vasculature for the organ; and selecting a reference vessel from the vasculature that has a size within a predetermined size range and a location with a predetermined distance range from the predetermined interface.
1 . The computer-implemented method of automatically identifying a reference vessel in an ultrasound image, the method comprising:
segmenting the image to identify an organ;
locating a predetermined anatomical landmark specific to the organ;
identifying appropriate vasculature for the organ; and
selecting a reference vessel from the vasculature that has a size within a predetermined size range and a location with a predetermined distance range from the predetermined anatomical landmark.
2 . The method according to claim 1 wherein the predetermined size range is greater than 3 mm in diameter.
3 . The method according to claim 1 wherein segmenting comprises using a trained fully convolutional neural network.
4 . The method according to claim 1 wherein locating comprises using a multi-class transfer learning model.
5 . The method according to claim 4 wherein the multi-class transfer learning model comprises two independent pathways, a first pathway having parameters initialised using a segmentation model and a second pathway having parameters initialised using variance scaling.
6 . The method according to claim 1 wherein identifying comprises using an automated multi-seed region growing based process.
7 . The method according to claim 6 wherein identifying further comprises using a 3D medial axis based thinning process on the output of the growing based process.
8 . The method according to claim 1 wherein the organ is the placenta and preferably the anatomical landmark is the utero-placental interface.
9 . The method according to claim 8 wherein the predetermined distance range is from about 0.5 cm to about 1.5 cm.
10 . The computer-implemented method of mapping blood flow in a power Doppler image of an organ, the method comprising:
identifying a reference vessel in the power Doppler image using the method of claim 1 ;
determining a reference power Doppler value from the reference vessel; and
scaling power Doppler values in the power Doppler image based on the reference power Doppler value to obtain a standardised image of blood flow.
11 . The method according to claim 10 wherein determining comprises fitting a model vessel profile to the reference vessel and determining a standardization point not falling within the high shear vessel margins.
12 . The method according to claim 11 wherein fitting a model vessel profile comprises detecting a local maximum intensity point and using a region growing method to obtain an initial vessel region where all the interior intensities are greater than a threshold.
13 . The method according to claim 12 further comprising applying an iterative gradient descent technique is applied to minimize a cost function.
14 . A computer-implemented method of determining fractional moving blood volume in an organ, the method comprising:
obtaining a power Doppler image of the organ;
mapping blood flow in the power Doppler image to obtain a standardised image of blood flow using the method of claim 10 ; and
determining fractional moving blood volume using the standardised image of blood flow.
15 . A computer-implemented method of calculating a risk of adverse pregnancy outcomes comprising:
determining fractional moving blood volume in the placenta of a subject according to the method of claim 14 ;
measuring placental volume of the subject; and
calculating a risk score based at least in part on the fractional moving blood volume and the placental volume.
16 . A non-transitory computer readable medium comprising instructions that, when executed by a computer system, instruct the computer system to perform a method of automatically identifying a reference vessel in an ultrasound image, the method comprising:
segmenting image to identify an organ;
locating a predetermined anatomical landmark specific to the organ;
identifying appropriate vasculature for the organ; and
selecting a reference vessel from the vasculature that has a size within a predetermined size range and a location with a predetermined distance range from the determined anatomical landmark.
17 . An ultrasound scanner including a computer control system configured to perform a method of automatically identifying a reference vessel in an ultrasound image, the method comprising:
segmenting the image to identify an organ;
locating a predetermined anatomical landmark specific to the organ;
identifying appropriate vasculature for the organ; and
selecting a reference vessel from the vasculature that has a size within a predetermined size range and a location with a predetermined distance range from the predetermined anatomical landmark.