Image processing apparatus, image processing method, and recording medium recording same

Patent metadata

Field	Value
Publication number	US-2018368731-A1
Application number	US-201616061201-A
Country	US
Kind code	A1
Filing date	Dec 23, 2016
Priority date	Feb 15, 2016
Publication date	Dec 27, 2018
Grant date	—

Abstract

The present invention relates to an image processing apparatus, an image processing method, and a recording medium for recording the same, the image processing apparatus including a storage configured to comprise a standard database (DB) established based on information about a predetermined anatomical entity; and at least one processor configured to obtain a local motion vector by registration between a first medical image and a second medical image taken by scanning an object including the anatomical entity, use a predictive local motion vector generated from the standard DB to normalize the local motion vector according to a plurality of regions in the anatomical entity, and make information about conditions of the anatomical entity based on the normalized local motion vector be provided according to the plurality of regions. By the normalization according to the regions, it is possible to provide distinguishable information about difference between the local motion vector of a pulmonary disease patient to be subjected to a diagnosis and a predictive local motion vector of a normal person generated from the standard DB through the statistical modeling using bio-information of a patient.

First claim

1 . An image processing apparatus comprising:
a storage configured to comprise a standard database (DB) established based on information about a predetermined anatomical entity; and at least one processor configured to:
obtain a local motion vector by registration between a first medical image and a second medical image taken by scanning an object including the anatomical entity,
use a predictive local motion vector generated from the standard DB to normalize the local motion vector according to a plurality of regions in the anatomical entity, and
make information about conditions of the anatomical entity based on the normalized local motion vector be provided according to the plurality of regions.

2 . The image processing apparatus according to claim 1 , further comprising:
a display configured to display the information about the conditions of the anatomical entity distinguishable according to the plurality of regions.

3 . The image processing apparatus according to claim 1 , wherein the processor is further configured to:
extract a region corresponding to the anatomical entity from the first medical image and the second medical image, and obtain the local motion vector corresponding to a displacement vector derived by the registration between the first medical image and the second medical image from which the region of the anatomical entity is extracted.

4 . The image processing apparatus according to claim 3 , wherein the anatomical entity comprises a lung, and the first medical image corresponds to an inspiratory image and the second medical image corresponds to an expiratory image.

5 . The image processing apparatus according to claim 1 , wherein the standard DB is established by vectorizing a plurality of medical images collected with regard to the anatomical entity, and applying statistical modeling to vectorized data.

6 . The image processing apparatus according to claim 5 , wherein the processor is further configured to:
receive bio-information about a patient to be subjected to a diagnosis as a variable, and compute the predictive local vector by applying the received variable to a function corresponding to the standard DB.

7 . The image processing apparatus according to claim 5 ,
wherein the established standard DB further comprises local motion vector information corresponding to the plurality of medical images, and wherein the processor is further configured to:
search the local motion vector corresponding to bio-information about a patient to be subjected to a diagnosis from the standard DB, and
determine the predictive local motion vector based on results of the search.

8 . The image processing apparatus according to claim 7 , wherein the at least one processor is further configured to:
select two or more local motion vectors having similar bio-information to the patient, and compute the predictive local motion vector by applying interpolation to the two or more selected local motion vectors.

9 . The image processing apparatus according claim 1 , wherein the processor is further configured to:
register a predictive local motion vector generated from the standard DB to a third medical image generated by registration between the first medical image and the second medical image, and use the predictive local motion vector warped to the third medical image by the registration to normalize the local motion vector according to the plurality of regions.

10 . An image processing method comprising:
obtaining a local motion vector by registration between a first medical image and a second medical image taken by scanning an object including a predetermined anatomical entity; using a predictive local motion vector generated from a standard DB comprising information about the anatomical entity to normalize the local motion vector according to a plurality of regions in the anatomical entity; and making information about conditions of the anatomical entity based on the normalized local motion vector be provided according to the plurality of regions.

11 . The image processing method according to claim 10 ,
wherein the obtaining of the local motion vector comprises:
extracting a region corresponding to the anatomical entity from the first medical image and the second medical image, and
obtaining the local motion vector corresponding to a displacement vector derived by the registration between the first medical image and the second medical image from which the region of the anatomical entity is extracted, and
wherein the anatomical entity comprises a lung, and the first medical image corresponds to an inspiratory image and the second medical image corresponds to an expiratory image.

12 . The image processing method according to claim 10 , further comprising:
vectorizing a plurality of medical images collected with regard to the anatomical entity; and establishing the standard DB by applying statistical modeling to the vectorized data.

13 . The image processing method according to claim 12 , further comprising:
receiving bio-information about a patient to be subjected to a diagnosis as a variable; and computing the predictive local vector by applying the received variable to a function corresponding to the standard DB, wherein normalization according to the plurality of regions uses the computed predictive local vector.

14 . The image processing method according to claim 13 ,
wherein the established standard DB further comprises local motion vector information corresponding to the plurality of medical images, wherein the method further comprises:
searching the local motion vector corresponding to bio-information about a patient to be subjected to a diagnosis from the standard DB; and
determining the predictive local motion vector based on results of the search, and
wherein the normalization according to the plurality of regions uses the determined predictive local motion vector.

15 . The image processing method according to claim 10 , further comprising:
registering a predictive local motion vector generated from the standard DB to a third medical image generated by registration between the first medical image and the second medical image, wherein the normalization according to the plurality of regions uses the predictive local motion vector warped to the third medical image by the registration to normalize the local motion vector according to the plurality of regions.

Assignees

• Samsung Electronics Co Ltd

Inventors

• Oh Ji-Hun
• Nam Woo-Hyun
• Park Yong-Sup

Classifications

• G06T2207/10081

  Computed x-ray tomography [CT] · CPC title

• G06T2207/20021

  Dividing image into blocks, subimages or windows · CPC title

• A61B5/0035

  adapted for acquisition of images from more than one imaging mode, e.g. combining MRI and optical tomography · CPC title

• G16H50/20

  for computer-aided diagnosis, e.g. based on medical expert systems · CPC title

• A61B6/03

  Computed tomography [CT] · CPC title