MEDICAL IMAGE PROCESSING APPARATUS AND METHOD THEREOF

• US 20140219524A1
• Filed: 05/11/2012
• Published: 08/07/2014
• Est. Priority Date: 05/11/2011
• Status: Active Grant

• Current Assignee: Toshiba Medical Systems Corporation (Canon Inc.)
• Original Assignee: Toshiba Medical Systems Corporation (Canon Inc.), Kabushiki Kaisha Toshiba (Toshiba Corporation)
• Inventors: Takeguchi, Tomoyuki, Nitta, Shuhei, Matsumoto, Nobuyuki, Sakata, Yukinobu, Okazaki, Tomoya, Sugiura, Takamasa, Fujisawa, Yasuko
• Granted Patent: US 9,153,033 B2
• Time in Patent Office: Days
• US Class Current: 382/128
• CPC Class Codes: A61B 6/032 Transmission computed tomography [CT]
• CPC Class Codes: A61B 6/463 characterised by displaying multiple images or images and diagnostic data on one display
• CPC Class Codes: A61B 6/466 adapted to display 3D data
• CPC Class Codes: A61B 6/503 for diagnosis of the heart
• CPC Class Codes: A61B 6/5211 involving processing of medical diagnostic data
• CPC Class Codes: A61B 6/5217 extracting a diagnostic or physiological parameter from medical diagnostic data
• CPC Class Codes: A61B 8/0883 for diagnosis of the heart
• CPC Class Codes: A61B 8/483 involving the acquisition of a 3D volume of data
• CPC Class Codes: A61B 8/5207 involving processing of raw data to produce diagnostic data, e.g. for generating an image reconstruction G06T11/00
• CPC Class Codes: G06T 2207/10072 Tomographic images
• CPC Class Codes: G06T 2207/30048 Heart; Cardiac
• CPC Class Codes: G06T 2207/30101 Blood vessel; Artery; Vein; Vascular
• CPC Class Codes: G06T 7/12 Edge-based segmentation
• CPC Class Codes: G06T 7/149 involving deformable models, e.g. active contour models
• CPC Class Codes: G16H 50/20 for computer-aided diagnosis, e.g. based on medical expert systems
• CPC Class Codes: G16H 50/30 for calculating health indices; for individual health risk assessment

Abstract

[Object] The invention is intended to provide a medical image processing apparatus in which improvement of accuracy of boundary detection of a heart is achieved.

[Solving Means] A medical image processing apparatus acquires volume data of a heat, detects a three-dimensional left ventricle coordinate system composed of three axes including at least a left ventricle long axis of the heart from the volume data; uses a boundary model expressed in the left ventricle coordinate system and detects a left ventricle boundary from the volume data, and displays a cross-sectional image orthogonal to at least one axis of the three axes of the left ventricle coordinate system together with the detected left ventricle boundary on the cross-sectional image.

Claims

1. A medical image processing apparatus comprising:

an acquiring unit configured to acquire volume data of a heart;

a coordinate system detecting unit configured to detect a three-dimensional left ventricle coordinate system composed of three axes including at least a left ventricle long axis of the heart from the volume data;

a boundary detecting unit configured to use a boundary model expressed in the left ventricle coordinate system to detect a left ventricle boundary from the volume data by deforming the boundary model so that an error between a boundary pattern obtained by applying the boundary model to the volume data and a predetermined boundary pattern model becomes small; and

a display unit configured to display the detected left ventricle boundary on a cross-sectional image together with the cross-sectional image orthogonal to at least one axis of the three axes of the left ventricle coordinate system.

2. The medical image processing apparatus according to claim 1, wherein the coordinate system detecting unit detects any one of axes which set the 4 chamber View, a 3 chamber View, or a 2 chamber View of the heart from the volume data as an axis of the left ventricle coordinate system in addition to the left ventricle long axis.

3. The medical image processing apparatus according to claim 1, wherein the coordinate system detecting unit detects the left ventricle coordinate system in which the directions of the three axes are orthogonal to each other and an original point thereof is located at the position of a center of a left ventricle of the heart from the volume data.

4. The medical image processing apparatus according to claim 1, wherein the coordinate system detecting unit detects the left ventricle coordinate system by performing matching between the volume data and a left ventricle cross-sectional image pattern created in advance.

5. The medical image processing apparatus according to claim 1, wherein the coordinate system detecting unit performs matching between the volume data with an image pattern in a surround of the position of a cardiac apex learned in advance and an image pattern in a surround of the position of a mitral valve to obtain the position of the cardiac apex and the position of the mitral valve of the heart respectively, and detects the left ventricle long axis from the position of the cardiac apex and the position of the mitral valve.

6. The medical image processing apparatus according to claim 5, wherein the coordinate system detecting unit detects the left ventricle coordinate system by using any one of the position of a right ventricle corner point, the position of a tricuspid valve, and the position of a left ventricle outflow tract of the heart after the detection of the left ventricle long axis.

7. The medical image processing apparatus according to claim 1, wherein the coordinate system detecting unit notifies a user the fact that the detection is not possible when the left ventricle coordinate system cannot be detected on the display unit.

8. The medical image processing apparatus according to claim 1, wherein the display unit displays the volume data on the basis of the coordinate system of the volume data when the coordinate system detecting unit cannot detect the left ventricle coordinate system.

9. The medical image processing apparatus according to claim 1, further comprising:

an evaluating unit configured to evaluate an error between the predetermined boundary pattern model and the boundary pattern relating to the detected left ventricle boundary, wherein

the display unit displays a result of evaluation of the error evaluated by the evaluating unit.

10. The medical image processing apparatus according to claim 9, wherein the evaluating unit evaluates whether or not the error is smaller than a threshold value.

11. The medical image processing apparatus according to claim 10, wherein when the error is smaller than the threshold value in the evaluating unit, the display unit displays the left ventricle boundary on the cross-sectional image together with the cross-sectional image.

12. The medical image processing apparatus according to claim 10, wherein when the error is larger than the threshold value in the evaluating unit, the display unit displays the fact that the left ventricle boundary cannot be detected.

13. The medical image processing apparatus according to claim 10, wherein when the error is larger than the threshold value in the evaluating unit, the display unit displays the volume data except for the left ventricle boundary.

14. The medical image processing apparatus according to claim 10, wherein when the error is larger than the threshold value in the evaluating unit, the coordinate system detecting unit detects the left ventricle coordinate system again under predetermined different conditions.

15. The medical image processing apparatus according to claim 10, wherein when the error is larger than the threshold value in the evaluating unit, a user inputs the left ventricle coordinate system with respect to the coordinate system detecting unit.

16. The medical image processing apparatus according to claim 1, wherein the boundary model is a boundary model including a myocardial inner boundary and a myocardial outer boundary of the left ventricle combined with each other.

17. The medical image processing apparatus according to claim 1, wherein the boundary model is a boundary model on the inner side of the myocardium of the left ventricle or a boundary model on the outside of the myocardium thereof.

18. The medical image processing apparatus according to claim 1, wherein the volume data is volume data imaged by a CT apparatus or an MR apparatus.

19. The medical image processing apparatus according to claim 1, wherein the boundary pattern model is obtained by modeling a pattern of brightness values in a myocardium and a surround of the myocardial boundary in an image enhanced by a contrast agent by learning,

a calculating unit configured to calculate a degree of staining indicating a concentration of the contrast agent of a predetermined regional area in the volume data on the basis of the left ventricle coordinate system, and

a correcting unit configured to use a degree of staining of the regional area to perform a correction to cause the brightness values of the volume data and the brightness values of the boundary pattern model to go close to each other in the corresponding regional area are provided, and

the boundary detecting unit detects a myocardial boundary in the volume data by using the data after the correction by the correcting unit.

20. The medical image processing apparatus according to claim 19, further comprising a regional area detecting unit configured to detect the regional area in the volume data by using the left ventricle coordinate system, wherein

the calculating unit performs a staining degree calculating process by using the regional area detected by the regional area detecting unit.

21. The medical image processing apparatus according to claim 19 wherein the correcting unit performs a correcting process by using the degree of staining on the boundary pattern model and creates a corrected boundary pattern model, and

the boundary detecting unit detects the boundary of the myocardium in the volume data by using the corrected boundary pattern model.

22. The medical image processing apparatus according to claim 19, wherein the correcting unit performs a correcting process by using the degree of staining on the volume data and creates the corrected volume data, and

the boundary detecting unit detects the boundary of the myocardium in the corrected volume data by using the boundary pattern model.

23. The medical image processing apparatus according to claim 19, wherein the correcting unit performs the correcting process by using the degree of staining by a combination of an adding process, a subtracting process, a multiplying process, a dividing process, or a rounding process.

24. The medical image processing apparatus according to claim 19, wherein the calculating unit calculates a statistic representative value in the brightness value row of a plurality of pixels which constitute the regional area as a staining degree of the corresponding regional area.

25. The medical image processing apparatus according to claim 20, wherein the regional area detecting unit detects a plurality of the regional areas as the predetermined regional area, and

the calculating unit calculates the degrees of staining of the respective plurality of regional areas.

26. The medical image processing apparatus according to claim 20, wherein the regional area detecting unit detects an area including at least one of the ventricles, atriums, the left ventricle outflow tract, a valve ring, a papillary muscle, the myocardium, and a coronary artery as the predetermined regional area.

27. The medical image processing apparatus according to claim 20, wherein the regional area detecting unit detects a predetermine range determined by a long axis included in the left ventricle coordinate system as the regional area in the volume data.

28. The medical image processing apparatus according to claim 20, wherein the coordinate system detecting unit further detects a short axis of the heart in the volume data as the left ventricle coordinate system, and

the regional area detecting unit detects a predetermined range determined by the direction of the long axis and the direction of the short axis as the regional area in the volume data.

29. A medical image processing method comprising:

acquiring volume data of a heart;

detecting a three-dimensional left ventricle coordinate system composed of three axes including at least a left ventricle long axis of the heart from the volume data;

using a boundary model expressed in the left ventricle coordinate system to deform the boundary model so that an error between a boundary pattern obtained by applying the boundary model to the volume data and a predetermined boundary pattern model becomes small, thereby detecting a left ventricle boundary from the volume data; and

displaying a cross-sectional image orthogonal to at least one axis of the three axes of the left ventricle coordinate system together with the detected left ventricle boundary on the cross-sectional image.