Image processing apparatus, image processing method, and image processing program
The image processing apparatus includes: a sectional image acquisition unit that acquires a plurality of sectional images in a plurality of sectional directions of a test subject; a primary classification unit that performs a primary classification process of specifying, with respect to each of the plurality of sectional images, the type of a tissue or a lesion to which each pixel of each sectional image belongs; a secondary classification unit that performs a secondary classification process of evaluating results of the primary classification process with respect to each of the plurality of sectional images, with respect to a pixel that is common to the plurality of sectional images, to re-specify the type of a tissue or a lesion to which the pixel that is common to the plurality of sectional images belongs; and a correction unit that corrects a result of the secondary classification process on the basis of an anatomic feature of the tissue or the lesion, or an image feature value thereof.
1. An image processing apparatus comprising:
a sectional image acquisition unit that acquires a plurality of sectional images in a plurality of different sectional directions of a test subject;
a primary classification unit that performs a primary classification process of specifying, with respect to each of the plurality of sectional images, the type of a tissue or a lesion to which each pixel of each sectional image belongs;
a secondary classification unit that performs a secondary classification process of evaluating results of the primary classification process with respect to each of the plurality of sectional images, with respect to a pixel that is common to the plurality of sectional images, to re-specify the type of a tissue or a lesion to which the pixel that is common to the plurality of sectional images belongs; and
a correction unit that corrects a result of the secondary classification process on the basis of an anatomic feature of the tissue or the lesion, or an image feature value thereof.
2. The image processing apparatus according to claim 1 ,
wherein the correction unit corrects the result of the secondary classification process with respect to each pixel using a sectional image in a specific sectional direction.
3. The image processing apparatus according to claim 2 ,
wherein the specific sectional direction is a slicing direction in imaging of the test subject.
4. The image processing apparatus according to claim 2 ,
wherein the sectional image in the specific sectional direction is a sectional image with the highest resolution among the sectional images in the plurality of sectional directions.
5. The image processing apparatus according to claim 2 ,
wherein the correction unit corrects the result of the secondary classification process on the basis of a signal value of each pixel of the sectional image in the specific sectional direction.
6. The image processing apparatus according to claim 1 ,
wherein the correction unit corrects the result of the secondary classification process on the basis of an anatomic feature of the shape or the position of the tissue or the lesion.
7. The image processing apparatus according to claim 1 ,
wherein the correction unit corrects, in a case where there is an abnormality in continuity in a three-dimensional space of an edge or a centroid position of a tissue or a lesion specified by each pixel classified by the secondary classification process, the result of the secondary classification process with respect to each pixel.
8. The image processing apparatus according to claim 1 ,
wherein in a case where the secondary classification unit performs the second classification process, the secondary classification unit adds a weight based on each resolution of each of the sectional images to the result of the primary classification process with respect to each sectional image for the evaluation.
9. The image processing apparatus according to claim 1 ,
wherein the primary classification unit performs the primary classification process using a discriminator generated through machine learning.
10. An image processing method comprising:
acquiring a plurality of sectional images in a plurality of different sectional directions of a test subject;
performing a primary classification process of specifying, with respect to each of the plurality of sectional images, the type of a tissue or a lesion to which each pixel of each sectional image belongs;
performing a secondary classification process of evaluating results of the primary classification process with respect to of the plurality of each sectional images, with respect to a pixel that is common to the plurality of sectional images, to re-specify the type of a tissue or a lesion to which the pixel that is common to the plurality of sectional images belongs; and
correcting a result of the secondary classification process on the basis of an anatomic feature of the tissue or the lesion, or an image feature value thereof.
11. A non-transitory computer-readable storage medium storing therein an image processing program that causes a computer to function as:
a sectional image acquisition unit that acquires a plurality of sectional images in a plurality of different sectional directions of a test subject;
a primary classification unit that performs a primary classification process of specifying, with respect to each of the plurality of sectional images, the type of a tissue or a lesion to which each pixel of each sectional image belongs;
a secondary classification unit that performs a secondary classification process of evaluating results of the primary classification process with respect to each of the plurality of sectional images, with respect to a pixel that is common to the plurality of sectional images, to re-specify the type of a tissue or a lesion to which the pixel that is common to the plurality of sectional images belongs; and
a correction unit that corrects a result of the secondary classification process on the basis of an anatomic feature of the tissue or the lesion, or an image feature value thereof.