POURTAHMASI ROSHANDEH, Koosha,ZONOOBI, Dornoosh,RAKKUNEDETH, Abhilash,DEHGHAN, Masood,JAREMKO, Jacob
申请号:
SGSG2019/050564
公开号:
WO2020/106216A1
申请日:
2019.11.19
申请国别(地区):
SG
年份:
2020
代理人:
摘要:
There is provided a method for generating a three-dimensional (3D) ultrasound image of a tissue volume using at least one processor, including: generating a series of two-dimensional (2D) ultrasound images of the tissue volume associated with a plurality of positions, respectively, along a scanning direction of the tissue volume; estimating, for each pair of consecutive 2D ultrasound images of the series of 2D ultrasound images, a distance between the positions associated with the pair of consecutive 2D ultrasound images based on a classification of a difference image generated from the pair of consecutive 2D ultrasound images using a deep neural network to produce a plurality of estimated distances associated with the plurality of pairs of consecutive 2D ultrasound images, respectively; modifying the number of 2D ultrasound images in the series of 2D ultrasound images based on the plurality of estimated distances to produce a modified series of 2D ultrasound images; and rendering the 3D ultrasound image of the tissue volume based on the modified series of 2D ultrasound images. There is also provided a corresponding system for generating a 3D ultrasound image of a tissue volume.L'invention concerne un procédé de production d'une image ultrasonore tridimensionnelle (3D) d'un volume tissulaire en utilisant au moins un processeur, consistant à : produire une série d'images ultrasonores bidimensionnelles (2D) du volume tissulaire associées à une pluralité de positions, respectivement, le long d'une direction de balayage du volume tissulaire ; estimer, pour chaque paire d'images ultrasonores 2D consécutives de la série d'images ultrasonores 2D, une distance entre les positions associées à la paire d'images ultrasonores 2D consécutives en fonction d'une classification d'une image de différence produite à partir de la paire d'images ultrasonores 2D consécutives en utilisant un réseau neuronal profond pour produire une pluralité de distances estimées associées à la pluralit