US 12,329,570 B2
Ultrasound system with an artificial neural network for guided liver imaging
Hua Xie, Cambridge, MA (US); Christine Menking Swisher, San Diego, CA (US); Claudia Errico, Cambridge, MA (US); Vijay Thakur Shamdasani, Kenmore, WA (US); and Yinhui Deng, Shanghai (CN)
Assigned to KONINKLIJKE PHILIPS N.V., Eindhoven (NL)
Appl. No. 17/263,172
Filed by KONINKLIJKE PHILIPS N.V., Eindhoven (NL)
PCT Filed Jul. 22, 2019, PCT No. PCT/EP2019/069637
§ 371(c)(1), (2) Date Jan. 26, 2021,
PCT Pub. No. WO2020/020809, PCT Pub. Date Jan. 30, 2020.
Claims priority of provisional application 62/711,974, filed on Jul. 30, 2018.
Claims priority of application No. PCT/CN2018/097194 (WO), filed on Jul. 26, 2018.
Prior Publication US 2021/0177373 A1, Jun. 17, 2021
Int. Cl. A61B 8/08 (2006.01); A61B 8/00 (2006.01); A61B 8/14 (2006.01); G06N 3/04 (2023.01); G06N 3/08 (2023.01); G06T 7/10 (2017.01); G16H 30/40 (2018.01); G16H 50/20 (2018.01)
CPC A61B 8/085 (2013.01) [A61B 8/14 (2013.01); A61B 8/463 (2013.01); A61B 8/469 (2013.01); G06N 3/04 (2013.01); G06N 3/08 (2013.01); G06T 7/10 (2017.01); G16H 30/40 (2018.01); G16H 50/20 (2018.01); G06T 2207/10132 (2013.01); G06T 2207/20081 (2013.01); G06T 2207/20084 (2013.01); G06T 2207/30056 (2013.01); G06T 2207/30084 (2013.01)] 22 Claims
OG exemplary drawing
 
1. An ultrasound imaging system comprising:
a probe configured to transmit ultrasound toward a subject for generating an image of biological tissue of the subject;
a display; and
a processor configured to receive the image and to output, using at least one neural network, a confidence metric that indicates a probability of the image visualizing the biological tissue in accordance with a target image view, wherein the processor is further configured to generate a graphical indicator comprising a color bar representative of a current value of the confidence metric, and cause the graphical indicator to be displayed on the display and be dynamically updated on the display responsive to each new confidence metric output by the at least one neural network, and wherein the processor is further configured, in response to a value of the confidence metric exceeding a threshold value, to:
select the image;
segment the image to identify regions of the image associated with at least two different types of biological tissue;
determine locations of first and second regions of interest (ROIs) in the image by identifying first and second plurality of pixels, respectively, each associated with one of the at least two different types of biological tissue; and
compute a ratio of echo-intensity values of the first and second ROIs.