Medical image processing device and method

Patent metadata

Field	Value
Publication number	US-10993700-B2
Application number	US-201515314327-A
Country	US
Kind code	B2
Filing date	Jun 9, 2015
Priority date	Jun 12, 2014
Publication date	May 4, 2021
Grant date	May 4, 2021

Abstract

The present invention relates to a medical image processing device ( 10 ), comprising: —a receiving unit ( 60 ) for receiving a first and a second medical image ( 72, 74 ) of an anatomical object of interest ( 84 ), wherein each of the first and the second medical images ( 72, 74 ) comprises a different field of view of the anatomical object of interest ( 84 ), and wherein the first medical image and the second medical image ( 72, 74 ) show a same or similar anatomical state of the anatomical object of interest ( 84 ); —a registration unit ( 64 ) that is configured to determine a transformation from an image space of the second medical image ( 74 ) to an image space of the first medical image ( 72 ); —a transformation unit ( 66 ) that is configured to transform the second medical image ( 74 ) into the image space of the first medical image ( 72 ) based on said transformation in order to receive a transformed second medical image ( 74 ′); and —a segmentation unit ( 68 ) that is configured to perform an overall segmentation that makes use of both the first medical image ( 72 ) and the transformed second medical image ( 74 ′) without fusing the first medical image ( 72 ) and the transformed second medical image ( 74 ′), wherein one and the same segmentation model ( 92 ) is simultaneously adapted to both the first medical image ( 72 ) and the transformed second medical image ( 74 ′) by identifying a first set of feature points ( 80 ) of the anatomical object of interest ( 84 ) within the first medical image ( 72 ), by identifying a second set of feature points ( 82 ) of the anatomical object of interest ( 84 ) within the transformed second medical image ( 74 ′), and by adapting the segmentation model ( 92 ) to both the first and the second set of feature points ( 80, 82 ).

First claim

The invention claimed is:

1. A medical image processing device, comprising: one or more processors configured to:
receive a first and a second medical image of an anatomical object of interest, wherein each of the first and the second medical images comprises a different field of view of the anatomical object of interest, and wherein the first medical image and the second medical image show a same or similar anatomical state of the anatomical object of interest;
perform an individual segmentation of the first medical image in order to receive a first segmentation mesh;
perform a second individual segmentation of the second medical image in order to receive a second segmentation mesh;
determine a transformation from an image space of the second medical image to an image space of the first medical image, wherein the transformation is determined by applying a point-based registration of the second segmentation mesh onto the first segmentation mesh;
transform the second medical image into the image space of the first medical image based on said transformation in order to receive a transformed second medical image; and
perform an overall segmentation that makes a separate use of both the first medical image and the transformed second medical image by identifying a first set of feature points of the anatomical object of interest within the first medical image and by identifying a second set of feature points of the anatomical object of interest within the transformed second medical image;
wherein one and the same segmentation model is simultaneously adapted to both the first medical image and the transformed second medical image by adapting the segmentation model to both the first and the second set of feature points.

2. The medical image processing device according to claim 1 , wherein the one or more processors are configured to identify the first and the second set of feature points of the anatomical object of interest by identifying within each of the first medical image and the transformed second medical image points having the highest brightness gradients within each of the first medical image and the transformed second medical image, respectively.

3. The medical image processing device according to claim 1 , wherein the one or more processors are configured to apply the same segmentation model for the individual segmentation of the first medical image and the second medical image.

4. The medical image processing device according to claim 1 , wherein the one or more processors are configured to receive a first medical image sequence including the first medical image and a second medical image sequence including the second medical image, and wherein the one or more processors are further configured for selecting the first and the second medical image in order to identify corresponding images of the same or similar anatomical state of the anatomical object of interest.

5. The medical image processing device according to claim 4 , wherein the one or more processors are configured to individually segment all images of the first and the second medical image sequence, and wherein the one or more processors are configured to automatically select the first and the second medical image based on the segmentation of all images of the first and the second medical image sequence.

6. The medical image processing device according to claim 1 , wherein the one or more processors are configured to reconstruct a fused image by fusing the first medical image and the transformed second medical image.

7. The medical image processing device according to claim 1 , wherein the first medical image and the second medical image are three-dimensional transthoracic echocardiographic images, 3D transesophageal echocardiographic images or three-dimensional fetal ultrasound images.

8. An ultrasound system, comprising:
an ultrasound transducer for transmitting and receiving ultrasound waves to and from the anatomical object of interest;
one or more processors configured for reconstructing the first medical image and the second medical image from the ultrasound waves received from the anatomical object of interest; and
the medical image processing device claimed in claim 1 .

9. A medical image processing method, wherein the method comprises the steps of:
receiving a first medical image and a second medical image of an anatomical object of interest, wherein each of the first and the second medical images comprises a different field of view of the anatomical object of interest, and wherein the first medical image and the second medical image show a same or similar anatomical state of the anatomical object of interest;
performing an individual segmentation of the first medical image in order to receive a first segmentation mesh;
performing an individual segmentation of the second medical image in order to receive a second segmentation mesh;
applying a point-based registration of the second segmentation mesh onto the first segmentation mesh to determine a transformation from an image space of the second medical image to an image space of the first medical image;
transforming the second medical image into the image space of the first medical image based on said transformation in order to receive a transformed second medical image; and
performing an overall segmentation that makes a separate use of both the first medical image and the transformed second medical image by identifying a first set of feature points of the anatomical object of interest within the first medical image and by identifying a second set of feature points of the anatomical object of interest within the transformed second medical image,
wherein one and the same segmentation model is simultaneously adapted to both the first medical image and the transformed second medical image by adapting the segmentation model to both the first and the second set of feature points.

10. A computer program product comprising a tangible computer-readable medium comprising executable instructions for causing a computer to carry out the steps of the method as claimed in claim 9 .

11. The medical image processing device of claim 1 , wherein the first segmentation mesh comprises a first sub-mesh corresponding to a first sub-structure of the anatomical object of interest, and the second segmentation mesh comprises a second sub-mesh corresponding to a different second sub-structure of the anatomical object of interest.

12. The medical image processing device according to claim 1 , wherein the one or more processors are configured to:
perform the individual segmentation of the first medical image using a first segmentation mesh-model;
perform the second individual segmentation of the second medical image using a second segmentation mesh-model; and
perform the overall segmentation using a third segmentation mesh-model.

13. The medical image processing device of claim 12 , wherein the first segmentation mesh-model is adapted to the first medical image to produce the first segmentation mesh, and the second segmentation mesh-model is adapted to the second medical image to produce the second segmentation mesh.

14. The medical image processing device of claim 12 , wherein:
performing the individual segmentation of the first medical image comprises adapting the first segmentation mesh-model to each of the first set of feature points to generate the first segmentation mesh; and
performing the individual segmentation of the second medical image comprises adapting the second segmentation mesh-model to each of the second set of feature points to generate the second segmentation mesh.

15. The medical image

Assignees

• Koninklijke Philips Nv

Inventors

• Buerger Christian
• Waechter-Stehle Irina
• Weber Frank Michael

Classifications

• G06T2207/20124

  Active shape model [ASM] · CPC title

• G06T2207/30048

  Heart; Cardiac · CPC title

• A61B8/0883 Primary

  for diagnosis of the heart · CPC title

• G06T7/149

  involving deformable models, e.g. active contour models · CPC title

• A61B8/5246 Primary

  combining images from the same or different imaging techniques, e.g. color Doppler and B-mode · CPC title