Image processing method, image processing program, and image processing device for partitioning a 3D object at narrow parts of shape

Patent metadata

Field	Value
Publication number	US-12462389-B2
Application number	US-202017917934-A
Country	US
Kind code	B2
Filing date	Nov 6, 2020
Priority date	Apr 10, 2020
Publication date	Nov 4, 2025
Grant date	Nov 4, 2025

Abstract

The present invention provides an image processing method capable of intuitively recognizing the three-dimensional shape of an organ by limiting the inspection range to the vicinity of the diagnostic target organ in image diagnosis. Given binary three-dimensional data representing an object in three-dimensional space, the image processing method partitions the object into individual segments with boundaries on narrow parts of the object's shape. A series of organs with no numerical differences in the boundaries on the image data can be segmented into individual organs at geometrically constricted locations because the connected organs can be identified by their shape. As a result, it is possible to examine a limited area specific to the target organ during image diagnosis, and to perform the examination while viewing the intuitive 3D shape of the organ during image interpretation.

First claim

The invention claimed is:

1 . An image processing method executed by a computer for partitioning a 3D object comprising:
receiving 3D image data; and generating segmented image data comprising: calculating a distance value between each of foreground voxels and boundary of foreground and background regions from binary 3D data that distinguishes the foreground region from the background region; generating hierarchical layers each of which is composed of the foreground voxels having a layer-value that is the same integer value by converting the distance value to an integer value; identifying layers each of which has a larger integer value than layers surrounding the layer as local maximum layers; defining each of the local maximum layers distinguished by a unique number as a core; generating a segment by adding the foreground voxels in a surrounding layer with an integer variable to the core, the surrounding layer being the layer surrounding the core, wherein the generating the segment includes starting with an integer variable that is one less than the largest integer value from the layer-value of the local maximum layers, and repeats until the integer value is 1, and wherein while adding the foreground voxels in a layer with an integer variable to the core, the foreground voxels in the layer with the integer variable are added to the core in order of surface contact with the voxel of the core, line contact with the voxel of the core, and point contact with the voxel of the core.

2 . An image processing device configured to be executed by a computer for partitioning a 3D object, the image processing device comprising:
an input unit for receiving information; a memory device for storing the received information; a processor; and a display device for displaying the processing results; wherein the processing of the processor includes: calculating a distance value between each of foreground voxels and boundary of foreground and background regions from binary 3D data that distinguishes the foreground region from the background region; generating hierarchical layers each of which is composed of the foreground voxels having a layer-value that is the same integer value by converting the distance value to an integer value; identifying layers each of which has a larger integer value than layers surrounding the layer as local maximum layers; defining each of the local maximum layers distinguished by a unique number as a core; and generating a segment by adding the foreground voxels in a surrounding layer with an integer variable to the core, the surrounding layer being the layer surrounding the core, wherein the generating the segment includes starting with an integer variable that is one less than the largest integer value from the layer-value of the local maximum layers, and repeats until the integer value is 1, and wherein while adding the foreground voxels in a layer with an integer variable to the core, the foreground voxels in the layer with the integer variable are added to the core in order of surface contact with the voxel of the core, line contact with the voxel of the core, and point contact with the voxel of the core.

3 . An image processing device according to claim 2 , further comprising:
generating binary 3D data corresponding to a series of organs from 3D data received from a medical computed tomography device; and generating a segment of an individual organ by merging plurality of the segments.

4 . An image processing device according to claim 3 , further comprising:
generating a stereoscopic image capable of identifying an outer surface and internal structure of each organ from the segment of the individual organ.

5 . An image processing device according to claim 3 , further comprising:
cutting out a partial region corresponding to a segment of an individual organ from 3D data received from a medical computer tomographic device that generates partial tomographic images as axial, coronal and sagittal planes from the partial region.

Assignees

• Vocsis Corp
• Univ Tohoku

Inventors

• Kobayashi Koji
• Ito Koichi
• Aoki Takafumi

Classifications

• G06T2207/20016

  Hierarchical, coarse-to-fine, multiscale or multiresolution image processing; Pyramid transform · CPC title

• G06T2207/10081

  Computed x-ray tomography [CT] · CPC title

• G06T2207/10012

  Stereo images · CPC title

• G06T2200/04

  involving 3D image data · CPC title

• G06T7/194

  involving foreground-background segmentation · CPC title