Medical image processing apparatus, medical imaging apparatus and medical image processing method

1. A medical image processing apparatus, comprising:

setting circuitry configured to set a region of interest (ROI) of each of a plurality of sagittal plane images of medical images resulting from scanning an examinee;

calculation circuitry configured to calculate an evaluation index based on a bipolarity feature of each block in the ROI related to change of pixel values and a similarity feature among the blocks; and

recognition circuitry configured to select the ROI according to the calculation result of the calculation circuitry and recognize a sagittal plane image in which the selected ROI is located as a target sagittal plane image of a median sagittal plane passing through a spine.

2. The medical image processing apparatus according to claim 1 , wherein the calculation circuitry comprises:

pixel energy calculation circuitry configured to calculate a weighted sum of the bipolarity feature value of a block where each pixel of the ROI is located and the similarity feature value of the block with respect to adjacent blocks as energy of the pixel; and

area energy calculation circuitry configured to calculate a mean or median of the energy of each pixel in the ROI as the energy of the ROI;

wherein the recognition circuitry selects a ROI having high energy and recognizes a sagittal plane image in which the selected ROI is located as the target sagittal plane image of the median sagittal plane passing through a spine.

3. The medical image processing apparatus according to claim 2 , wherein the calculation circuitry further comprises:

longitudinal band selection circuitry configured to determine a longitudinal band with the highest energy in each ROI, wherein the energy of the longitudinal band refers to the mean or median of the energy of respective pixels in the longitudinal band,

wherein, the area energy calculation circuitry takes the energy of the longitudinal band determined by the longitudinal band selection circuitry as energy of the corresponding ROI.

4. The medical image processing apparatus according to claim 1 , further comprising: false target recognition circuitry which comprises:

projection circuitry configured to obtain, for the ROI of each target sagittal plane image, horizontal projection of each size-specified area in the ROI; and

false target determination circuitry configured to determine a target sagittal plane image in which the horizontal projection of a predetermined number of areas in the ROIs thereof fail to meet the following distribution condition, as a false target sagittal plane image:

the peak values of a plurality of peaks in the horizontal projection are approximate, and

the intervals between the plurality of peaks in the horizontal projection are approximate.

5. The medical image processing apparatus according to claim 1 , wherein the setting circuitry comprises:

projection circuitry configured to obtain horizontal projection of a plurality of candidate ROIs in each sagittal plane image; and

ROI determination circuitry configured to select, from the plurality of candidate ROIs in each sagittal plane image, a candidate ROI the horizontal projection of which most meets the following distribution condition as the ROI of the sagittal plane image:

the peak values of a plurality of peaks in the horizontal projection are approximate, and

the intervals between the plurality of peaks in the horizontal projection are approximate.

6. The medical image processing apparatus according to claim 1 , further comprising: post-processing circuitry which comprises:

spine ROI recognition circuitry configured to determine a spine ROI in the target sagittal plane image; and

intervertebral disk detection circuitry configured to detect an intervertebral disk in each spine ROI.

7. The medical image processing apparatus according to claim 6 , further comprising: injury recognition circuitry which comprises:

projection circuitry configured to obtain horizontal projection of each spine ROI; and

injury determination circuitry configured to determine one of the intervertebral disks detected in the spine ROIs being injured, if the peak value of the peak of the horizontal projection corresponding to this intervertebral disk is lower than the peak values of the peaks of the horizontal projection corresponding to adjacent intervertebral disks by a preset level.

8. The medical image processing apparatus according to claim 6 , further comprising: false intervertebral disk recognition circuitry which comprises:

projection circuitry, configured to obtain horizontal projection of each spine ROI; and

false intervertebral disk determination circuitry, configured to determine one of the intervertebral disks detected in the spine ROIs as a false intervertebral disk, if an interval between the peak of the horizontal projection corresponding to this intervertebral disk and the peak of the horizontal projection corresponding to adjacent intervertebral disks is lower or higher than a mean of the intervals between the peaks of the horizontal projection corresponding to each of the intervertebral disks by a preset level.

9. A medical imaging apparatus, comprising a medical image processing apparatus which comprises:

setting circuitry configured to set a region of interest (ROI) of each of a plurality of sagittal plane images of medical images resulting from scanning an examinee;

calculation circuitry configured to calculate an evaluation index based on a bipolarity feature of each block in the ROI related to change of pixel values and a similarity feature among the blocks; and

recognition circuitry configured to select the ROI according to the calculation result of the calculation circuitry and recognize a sagittal plane image in which the selected ROI is located as a target sagittal plane image of a median sagittal plane passing through a spine.

10. A medical image processing method, comprising:

setting a ROI of each of a plurality of sagittal plane images of medical images resulting from scanning an examinee;

calculating an evaluation index based on a bipolarity feature of each block in the ROI related to change of pixel values and a similarity feature among the blocks;

selecting the ROI according to the calculation result; and

recognizing a sagittal plane image in which the selected ROI is located as a target sagittal plane image of a median sagittal plane passing through a spine.

11. The medical image processing method according to claim 10 , wherein calculating the evaluation index comprises:

calculating a weighted sum of the bipolarity feature value of a block where each pixel of the ROI is located and the similarity feature value of the block with respect to adjacent blocks as energy of the pixel; and

calculating a mean or median of the energy of each pixel in the ROI as the energy of the ROI;

wherein a ROI having high energy is selected, and a sagittal plane image in which the selected ROI is located is recognized as the target sagittal plane image of the median sagittal plane passing through a spine.

12. The medical image processing method according to claim 11 , further comprising:

determining a longitudinal band with the highest energy in each ROI, wherein the energy of the longitudinal band refers to the mean or median of the energy of respective pixels in the longitudinal band,

wherein, the energy of the longitudinal band is taken as energy of the corresponding ROI.

13. The medical image processing method according to claim 10 , further comprising:

obtaining, for the ROI of each target sagittal plane image, horizontal projection of each size-specified area in the ROI; and

determining a target sagittal plane image in which the horizontal projection of a predetermined number of areas in the ROIs thereof fail to meet the following distribution condition, as a false target sagittal plane image:

the peak values of a plurality of peaks in the horizontal projection are approximate, and

the intervals between the plurality of peaks in the horizontal projection are approximate.

14. The medical image processing method according to claim 10 , wherein determining the ROI of each sagittal plane image comprises:

obtaining the horizontal projection of a plurality of candidate ROIs in each sagittal plane image; and

selecting, from the plurality of candidate ROIs in each sagittal plane image, a candidate ROI the horizontal projection of which most meets the following distribution condition as the ROI of the sagittal plane image:

the peak values of a plurality of peaks in the horizontal projection are approximate, and

the intervals between the plurality of peaks in the horizontal projection are approximate.

15. The medical image processing method according to claim 10 , further comprising:

determining a spine ROI in the target sagittal plane image; and

detecting an intervertebral disk in each spine ROI.

16. The medical image processing method according to claim 15 , further comprising:

obtaining horizontal projection of each spine ROI; and

determining one of the intervertebral disks detected in the spine ROIs being injured, if the peak value of the peak of the horizontal projection corresponding to this intervertebral disk is lower than the peak values of the peaks of the horizontal projection corresponding to adjacent intervertebral disks by a preset level.

17. The medical image processing method according to claim 15 , further comprising:

obtaining horizontal projection of each spine ROI; and

determining one of the intervertebral disks detected in the spine ROIs as a false intervertebral disk, if an interval between the peak of the horizontal projection corresponding to this intervertebral disk and the peaks of the horizontal projection corresponding to adjacent intervertebral disks is lower or higher than a mean of the intervals between the peaks of the horizontal projection corresponding to each of the intervertebral disks by a preset level.