Image processing apparatus, magnetic resonance imaging apparatus, image processing method, and storage medium

• US 10,401,457 B2
• Filed: 02/26/2015
• Issued: 09/03/2019
• Est. Priority Date: 03/05/2014
• Status: Active Grant

• Current Assignee: Kyoto University
• Original Assignee: Kyoto University
• Inventors: Le Bihan, Denis, Iima, Mami, Yano, Kojiro
• Primary Examiner(s): Hollington, Jermele M
• Assistant Examiner(s): Rodriguez, Douglas X
• Application Number:
  US15/122,601
• Publication Number:
  US 20170067978A1
• Time in Patent Office: 1,650 Days
• Field of Search: None
• CPC Class Codes: G01R 33/5608 Data processing and visualization specially adapted for MR, e.g. for feature analysis and pattern recognition on the basis of measured MR data, segmentation of measured MR data, edge contour detection on the basis of measured MR data, for enhancing measured MR data in terms of signal-to-noise ratio by means of noise filtering or apodization, for enhancing measured MR data in terms of resolution by means for deblurring, windowing, zero filling, or generation of gray-scaled images, colour-coded images or images displaying vectors instead of pixels image data processing or generation, in general G06T
• CPC Class Codes: G01R 33/56341 Diffusion imaging
• CPC Class Codes: G06T 2207/10088 Magnetic resonance imaging [MRI]
• CPC Class Codes: G06T 2207/30004 Biomedical image processing
• CPC Class Codes: G06T 7/0002 Inspection of images, e.g. flaw detection
• CPC Class Codes: G06T 7/0012 Biomedical image inspection

Abstract

Conventionally, it has been impossible to output an image that allows for an easy and accurate diagnosis as to whether or not a malignant tumor is present and that allows for correctly indicating a part with a high or low grade of malignancy in the tumor. With an image processing apparatus that includes: a receiving unit configured to receive diffusion weighted images; a parameter acquisition unit configured to acquire parameters of two or more types for each of one or more units of processing that constitute the diffusion weighted images, by using the diffusion weighted images; a diagnostic image composition unit configured to acquire, for each of the one or more units of processing, a score that corresponds to the parameters of two or more types, by using the parameters of two or more types, and to compose a diagnostic image that is an image having, for each of the one or more units of processing, a pixel value that corresponds to the acquired score that corresponds to the unit of processing; and an output unit configured to output the diagnostic image, it is possible to output an image that allows for an easy and accurate diagnosis as to whether or not a malignant tumor is present and that allows for correctly indicating a part with a high or low grade of malignancy in the tumor.

Claims

1. An image processing apparatus comprising:

a score acquisition management information storage unit in which pieces of score acquisition management information are stored, wherein;

type information and score acquisition information are associated with each other in the score acquisition management information,

the type information indicates parameter types, and

the score acquisition information includes parameter conditions having thresholds for parameter values;

a receiving unit configured to receive diffusion weighted images, wherein the diffusion weighted images are constituted by units of processing;

a parameter acquisition unit configured to acquire, from the diffusion weighted images, parameter maps of the diffusion weighted images for the parameter types, respectively,

wherein each of the parameter maps of the diffusion weighted images includes a parameter value of a corresponding parameter type per each of the units of processing;

a score acquisition information acquisition unit configured to acquire, from the score acquisition management information storage unit, score acquisition information that corresponds to the parameter maps of the diffusion weighted images, respectively;

a score acquisition unit configured to acquire, from the acquired score acquisition information, for each of the units of processing, scores that correspond to the parameter maps, respectively, by using parameter values that the parameter maps have and the parameter conditions, wherein the score acquisition unit acquires the scores according to whether or not parameter values of the unit of processing satisfy the parameter conditions, respectively, for the parameter maps;

a diagnostic image composition unit configured to total, for each of the units of processing, the acquired scores of the parameter maps, to calculate a diagnostic score of each of the units of processing, and to compose a diagnostic image that is an image having, for each of the units of processing, a pixel value that corresponds to the diagnostic score of each of the units of processing; and

an output unit configured to output the diagnostic image.

2. The image processing apparatus according to claim 1, wherein:

the score acquisition information includes two parameter conditions for each of the parameter types associated with different scores,

and

the score acquisition unit is configured to acquire the scores based on which one of the two parameter conditions the parameter values satisfy.

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

a score coefficient management information storage unit in which pieces of score coefficient management information are stored, the score coefficient management information being information in which the parameter types and score coefficients that are weights assigned to scores are associated with each other; and

a score coefficient acquisition unit configured to acquire, from the score coefficient management information, score coefficients that correspond to the parameter types, respectively,

wherein the diagnostic image composition unit is configured to multiply, for each of the units of processing, the scores acquired by the score acquisition unit, by the score coefficients acquired by the score coefficient acquisition unit for the parameter maps, respectively, to total the scores obtained by the multiplication, for each of the units of processing, to calculate the diagnostic score, for each of the units of processing, and to compose the diagnostic image that has, for each of the units of processing, the pixel value that corresponds to the diagnostic score for each of the units of processing thus calculated.

4. The image processing apparatus according to claim 1,

wherein the diagnostic image composition unit is configured to compose the diagnostic image that has, for each of the units of processing, color indicating the pixel value that corresponds to the score of the unit of processing.

5. The image processing apparatus according to claim 1, wherein:

the receiving unit is configured to receive two-dimensional diffusion weighted images of different image-captured positions,

the parameter acquisition unit is configured to acquire two-dimensional parameter maps for each of the two-dimensional diffusion weighted images, and

the diagnostic image composition unit is configured to acquire the diagnostic score for each of the units of processing for the two-dimensional diffusion weighted images, to compose diagnostic images, each of which has, for each of the units of processing, the pixel value that corresponds to the diagnostic score thus acquired, and to compose a three-dimensional diagnostic image by compositing the diagnostic images thus composed.

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

a diagnostic result management information storage unit in which diagnostic result management information is stored, wherein, in the diagnostic result management information, score conditions regarding the scores that the diagnostic image has and diagnostic result information that indicates diagnostic results that correspond to the scores are associated with each other; and

a diagnostic result information acquisition unit configured to acquire one or more pieces of the diagnostic result information that correspond to the score conditions satisfied by the diagnostic scores of the diagnostic image,

wherein the output unit outputs the diagnostic image, together with the one or more pieces of diagnostic result.

7. The image processing apparatus according to claim 1,

wherein the parameter types are two or more selected from the group consisting of:

an ADC value that is calculated using the diffusion weighted images;

an IVIM that is calculated using the diffusion weighted images; and

a K value that is calculated using the diffusion weighted images.

8. The image processing apparatus according to claim 1,

wherein each of the units of processing is one pixel of the diffusion weighted images.

9. A magnetic resonance imaging apparatus that is provided with the image processing apparatus according to claim 1.

10. An image processing method performed by using a receiving unit, a parameter acquisition unit, a score acquisition information acquisition unit, a score acquisition unit, a diagnostic image composition unit, and an output unit, wherein a storage medium is provided with a score acquisition management information storage unit in which pieces of score acquisition management information are stored, type information and score acquisition information are associated with each other in the score acquisition management information, the type information indicates parameter types, and the score acquisition information includes parameter conditions having thresholds for parameter values, the image processing method comprising:

a receiving step in which the receiving unit receives diffusion weighted images, wherein the diffusion weighted images are constituted by units of processing;

a parameter acquisition step in which the parameter acquisition unit acquires, from the diffusion weighted images, parameter maps of the diffusion weighted images for the parameter types, respectively, wherein each of the parameter maps of the diffusion weighted images includes a parameter value of a corresponding parameter type per each of the units of processing;

a score acquisition information acquisition step in which the score acquisition information acquisition unit acquires, from the score acquisition management information storage unit, score acquisition information that corresponds to the parameter maps of the diffusion weighted images, respectively;

a score acquisition step in which the score acquisition unit acquires, from the acquired score acquisition information, for each of the units of processing, scores that correspond to the parameter maps, respectively, by using parameter values that the parameter maps have and the parameter conditions, wherein the score acquisition unit acquires the scores according to whether or not parameter values of the unit of processing satisfy the parameter conditions, respectively, for the parameter maps;

a diagnostic image composition step in which the diagnostic image composition unit totals, for each of the units of processing, the acquired scores of the parameter maps, calculates a diagnostic score of each of the units of processing, and composes a diagnostic image that is an image having, for each of the units of processing, a pixel value that corresponds to the diagnostic score of each of the units of processing; and

an output step in which the output unit outputs the diagnostic image.

11. A non-transitory storage medium, in which a program is stored, which is accessible by a computer, and which is provided with a score acquisition management information storage unit in which pieces of score acquisition management information are stored, wherein type information and score acquisition information are associated with each other in the score acquisition management information, the type information indicates parameter types, and the score acquisition information includes parameter conditions having thresholds for parameter values, the program causing a computer to function as:

a receiving unit configured to receive diffusion weighted images, wherein the diffusion weighted images are constituted by a plurality of units of processing;

a parameter acquisition unit configured to acquire, from the diffusion weighted images, parameter maps of the diffusion weighted images for the parameter types, respectively, wherein each of the parameter maps of the diffusion weighted images includes a parameter value of a corresponding parameter type per each of the units of processing;

a score acquisition information acquisition unit configured to acquire, from the score acquisition management information storage unit, score acquisition information that corresponds to the parameter maps of the diffusion weighted images, respectively;

a score acquisition unit configured to acquire, from the acquired score acquisition information, for each of the units of processing, scores that correspond to the parameter maps, respectively by using parameter values that the parameter maps have and the parameter conditions, wherein the score acquisition unit acquires the scores according to whether or not parameter values of the unit of processing satisfy the parameter conditions, respectively, for the parameter maps;

a diagnostic image composition unit configured to total, for each of the units of processing, the acquired scores of the parameter maps, to calculate a diagnostic score of each of the units of processing, and to compose a diagnostic image that is an image having, for each of the units of processing, a pixel value that corresponds to the diagnostic score of each of the units of processing; and

an output unit configured to output the diagnostic image.