FIELD: data processing.
SUBSTANCE: present invention relates to image segmentation. In one embodiment, a three-dimensional image segmentation method implemented by a computer is provided. Method may include receiving a three-dimensional image obtained by an image forming apparatus and creating a first stack of 2D images from a first plane of a three-dimensional image and a second stack of two-dimensional images from a second plane of a three-dimensional image. Method may further include segmentation by a first stack processor and a second stack of 2D images using at least one neural network model. Method may also include determining, by the card processor, marks for the three-dimensional image by aggregating the segmentation results from the first stack and the second stack.
EFFECT: technical result consists in improvement of accuracy of automatic segmentation of images.
30 cl, 8 dwg
