Image analysis apparatus, image processing apparatus, image analysis program storage medium, image processing program storage medium, image analysis method and image processing method

• US 8,265,368 B2
• Filed: 09/12/2008
• Issued: 09/11/2012
• Est. Priority Date: 09/28/2007
• Status: Active Grant

• Current Assignee: Fujifilm Corporation (Fujifilm Holdings Corporation)
• Original Assignee: Fujifilm Corporation (Fujifilm Holdings Corporation)
• Inventors: Ihara, Satoshi
• Primary Examiner(s): Ho, Allen C.
• Application Number:
  US12/209,332
• Publication Number:
  US 20090087058A1
• Time in Patent Office: 1,460 Days
• Field of Search: 382/131, 382/132, 378/57
• US Class Current: 382/131
• CPC Class Codes: G06V 10/457 by analysing connectivity, e.g. edge linking, connected component analysis or slices
• CPC Class Codes: G06V 2201/03 Recognition of patterns in medical or anatomical images
• CPC Class Codes: G06V 40/10 Human or animal bodies, e.g. vehicle occupants or pedestrians; Body parts, e.g. hands

Abstract

Plural sectional images are acquired at a plurality of slice positions arranged in a predetermined direction in a subject. Each of the plural sectional images acquired by the image acquisition section is binarized based on a predetermined reference image density. Each image included in the sectional images binarized by the binarizing section is classified into a first image group having the images inside the subject and a second image group having the images outside the subject, based on the relative position of the each image from the other images in the same sectional image and also the relative position of the each image from other images contained in another sectional images.

Claims

1. An image analysis apparatus comprising:

an image acquisition section that acquires a plurality of sectional images obtained by photographing a subject;

a density classification section that classifies pixels in each of the plurality of sectional images into high density pixels and low density pixels;

a two-dimensional labeling section that attaches label numbers to high density image portions each of which is constituted by the high density pixels on each of the plurality of sectional images;

a three-dimensional labeling section that couples label data between the plurality of sectional images; and

a classification section that classifies image portions of each of the plurality of sectional images into a first image group formed by image portions inside the subject and a second image group formed by image portions outside the subject, based on the coupled label data,

wherein the classification section calculates, when two three-dimensional images formed by two high-density image portion groups respectively are extracted in the classification section, volume of each of the two three-dimensional images, and

the classification section determines that both of the two high-density image portion groups are parts of a subject image group if volume of one or the two three-dimensional images is not less than a half of volume of the other of the two three-dimensional images.

2. The image analysis apparatus according to claim 1,

wherein the classification section classifies a series of image portions continuous over a plurality of sectional images into the same image group.

3. The image analysis apparatus according to claim 1,

wherein in the case where an image portion in one sectional image surrounds another image portion, the classification section classifies these image portions into the same image group.

4. An image analysis apparatus comprising:

an image acquisition section that acquires a plurality of sectional images obtained by photographing a subject;

a density classification section that classifies pixels in each of the plurality of sectional images into high density pixels and low density pixels;

a two-dimensional labeling section that attaches label numbers to high density image portions each of which is constituted by the high density pixels on each of the plurality of sectional images;

a three-dimensional labeling section that couples label data between the plurality of sectional images; and

a classification section that classifies image portions of each of the plurality of sectional images into a first image group formed by image portions inside the subject and a second image group formed by image portions outside the subject, based on the coupled label data,

wherein the image acquisition section acquires, as the plurality of sectional images, a plurality of sectional images at each of a plurality of slice positions arranged in a predetermined direction in the subject and the classification section reclassifies, among the image portions having been classified into the second image group, an image portion that is inserted between the image portions classified into the first image group in a sectional image containing the image portion and that is sandwiched as well in the predetermined direction by the image portions classified into the first image group, as the first image group.

5. An image processing apparatus comprising:

an image acquisition section that acquires a plurality of sectional images obtained by photographing a subject;

a density classification section that classifies pixels in each of the plurality of sectional images into high density pixels and low density pixels;

a two-dimensional labeling section that attaches label numbers to high density image portions each of which is constituted by the high density pixels on each of the plurality of sectional images;

a three-dimensional labeling section that couples label data between the plurality of sectional images; and

a classification section that classifies image portions of each of the plurality of sectional images into a first image group formed by image portions inside the subject and a second image group formed by image portions outside the subject, based on the coupled label data; and

an image processing section that removes the second image group included in each of the plurality of the sectional images,

wherein the classification section calculates, when two three-dimensional images formed by two high-density image portion groups respectively are extracted in the classification section, volume of each of the two three-dimensional images, and

the classification section determines that both of the two high-density image portion groups are parts of a subject image group if volume of one or the two three-dimensional images is not less than a half of volume of the other of the two three-dimensional images.

6. A non-transitory computer-readable medium that stores an image analysis program which is executed in a computer, and which constructs on the computer,

an image acquisition section that acquires a plurality of sectional images obtained by photographing a subject;

a density classification section that classifies pixels in each of the plurality of sectional images into high density pixels and low density pixels;

a two-dimensional labeling section that attaches label numbers to high density image portions each of which is constituted by the high density pixels on each of the plurality of sectional images;

a three-dimensional labeling section that couples label data between the plurality of sectional images; and

a classification section that classifies image portions of each of the plurality of sectional images into a first image group formed by image portions inside the subject and a second image group formed by image portions outside the subject, based on the coupled label data,

wherein the classification section calculates, when two three-dimensional images formed by two high-density image portion groups respectively are extracted in the classification section, volume of each of the two three-dimensional images, and

the classification section determines that both of the two high-density image portion groups are parts of a subject image group if volume of one or the two three-dimensional images is not less than a half of volume of the other of the two three-dimensional images.

7. A non-transitory computer-readable medium that stores an image processing program which is executed in a computer, and which constructs on the computer,

an image acquisition section that acquires a plurality of sectional images obtained by photographing a subject;

a density classification section that classifies pixels in each of the plurality of sectional images into high density pixels and low density pixels;

a two-dimensional labeling section that attaches label numbers to high density image portions each of which is constituted by the high density pixels on each of the plurality of sectional images;

a three-dimensional labeling section that couples label data between the plurality of sectional images; and

a classification section that classifies image portions of each of the plurality of sectional images into a first image group formed by image portions inside the subject and a second image group formed by image portions outside the subject, based on the coupled label data; and

an image processing section that removes the second image group covered in each of the plurality of the sectional images,

wherein the classification section calculates, when two three-dimensional images formed by two high-density image portion groups respectively are extracted in the classification section, volume of each of the two three-dimensional images, and

the classification section determines that both of the two high-density image portion groups are parts of a subject image group if volume of one or the two three-dimensional images is not less than a half of volume of the other of the two three-dimensional images.