US 11,657,480 B2
Method of improving quality of ultrasound image and related ultrasound detection system
Ssu-Hua Huang, Taichung (TW); and Jian-Guo Huang, Hualien County (TW)
Assigned to Qisda Corporation, Taoyuan (TW)
Filed by QISDA CORPORATION, Taoyuan (TW)
Filed on Dec. 23, 2020, as Appl. No. 17/133,552.
Claims priority of application No. 109104711 (TW), filed on Feb. 14, 2020.
Prior Publication US 2021/0256660 A1, Aug. 19, 2021
Int. Cl. G06T 5/00 (2006.01); G06T 5/10 (2006.01); G06K 9/00 (2022.01); G06T 3/40 (2006.01)
CPC G06T 5/002 (2013.01) [G06T 3/40 (2013.01); G06T 5/10 (2013.01); G06T 2207/10132 (2013.01); G06T 2207/20182 (2013.01)] 20 Claims
OG exemplary drawing
 
1. A method of improving quality of ultrasound images, comprising:
receiving an ultrasound sample image;
performing a noise reduction procedure on the ultrasound sample image for generating a noise-reduced ultrasound sample image;
performing an binarization procedure on the noise-reduced ultrasound image based on a first threshold value for generating a binary image, wherein the binary image includes at least one pixel with a grayscale equal to a foreground value and at least one pixel with a grayscale equal to a background value different from the foreground value;
performing a foreground expansion procedure on the binary image based on the ultrasound sample image and a second threshold value smaller than the first threshold value for generating an output image, wherein the foreground expansion procedure includes:
determining whether a grayscale of a first pixel located on a first location in the ultrasound sample image is larger than the second threshold value, whether a grayscale of a second pixel located on the first location in the binary image is equal to the foreground value, and whether at least one pixel with a grayscale equal to the foreground value exists within a neighboring region in the binary image, wherein the second pixel is located within the neighboring region;
setting a grayscale of a third pixel located on the first location in the output image to the foreground value when determining that the grayscale of the first pixel is larger than the second threshold value and that the at least one pixel with the grayscale equal to the foreground value exists within the neighboring region in the binary image; and
performing a post-processing procedure on the ultrasound sample image according to foreground and background information of the output image for generating an improved ultrasound sample image.