Medical image data processing apparatus and method
A medical image data processing apparatus comprising processing circuitry configured to: receive medical image data; segment a body part included in the medical image data into multiple regions; refine or constrain the segmentation based on at least one plane to obtain a segmentation that includes at least one boundary or other feature having a desired property.
1. A medical image data processing apparatus comprising processing circuitry configured to:
receive medical image data;
segment a body part included in the medical image data into multiple regions; and
refine or constrain the segmentation based on at least one plane to obtain a segmentation that includes at least one boundary or other feature having a desired property,
wherein the refining or constraining of the segmentation comprises preserving a desired geometry of the at least one boundary or other feature to be flat or non-curved after obtaining the segmentation.
2. The apparatus of claim 1 , wherein the processing circuitry is configured to segment the body part based on a non-rigid registration between the medical image data and atlas data.
3. The apparatus of claim 2 , wherein the processing circuitry is configured to transform in accordance with the non-rigid registration at least one point or other feature that is not distorted by the non-rigid registration, and to determine the at least one plane from said at least one point or other feature.
4. The apparatus of claim 1 , wherein the processing circuitry is configured to determine a plurality of points on at least one boundary between regions and to apply a fitting process to the points to determine the at least one plane.
5. The apparatus of claim 4 , wherein the processing circuitry is configured to determine the plurality of points from atlas data, to transform the plurality of points in accordance with a registration between the atlas data and the medical image data, and to apply the fitting process to the points after the transformation.
6. The apparatus of claim 1 , wherein the processing circuitry is configured to form a composite region and the refining of the segmentation comprises dividing the composite region into the multiple regions.
7. The apparatus of claim 6 , wherein the processing circuitry is configured to:
form the composite region based on atlas data; and
transform the composite region in accordance with a registration between the atlas data and the medical image data, wherein
the dividing of the composite region into the multiple regions is performed on the transformed composite region.
8. The apparatus of claim 6 , wherein the dividing of the composite region comprises dividing the composite region using the at least one plane.
9. The apparatus of claim 2 , wherein the processing circuitry is configured to:
decompose a registration transform obtained from the non-rigid registration into an affine or rigid component and a non-affine component; and
use the affine or rigid component to transform a boundary between regions.
10. The apparatus of claim 1 , wherein the at least one plane includes an axial plane and the processing circuitry is configured to determine the axial plane based on a position of a basal ganglia.
11. The apparatus of claim 1 , wherein the processing circuitry is configured to apply a convolutional neural network (CNN) or other trained model to the medical image data to segment the body part, and the constraining of the segmentation comprises including a loss function or other constraint based on the at least one plane in the CNN or other trained model.
12. The apparatus of claim 11 , wherein the at least one plane comprises or represents at least one boundary between or of the regions.
13. The apparatus of claim 1 , wherein the at least one desired property of the boundary or other feature comprises a a flat or non-curved shape.
14. The apparatus of claim 1 , wherein the body part comprises a brain or at least one hemisphere or other part of a brain.
15. The apparatus of claim 1 , wherein the regions comprises any or all of M 1 to M 6 regions, or M 1 to M 10 regions, or other regions of the Alberta Stroke Program Early CT score (ASPECTS) scheme.
16. The apparatus of claim 6 , wherein the composite region comprises some or all of M 1 to M 6 regions of the ASPECTS scheme.
17. The apparatus of claim 1 , wherein the processing circuitry is configured to:
a) determine an orbitomeatal line from the medical image data and aligning the medical image data using the orbitomeatal line; and/or
b) align the medical image data contralaterally.
18. The apparatus of claim 1 , wherein the medical image data comprises at least one of magnetic resonance imaging (MRI) data, computed tomography (CT) data, cone-beam CT data, non-contrast CT (NCCT) data, computed tomography perfusion (CTP) data, X-ray data, ultrasound data, positron emission tomography (PET) data or single photon emission computed tomography (SPECT) data.
19. A medical image data processing method comprising:
receiving medical image data;
segmenting a body part included in the medical image data into multiple regions; and
refining or constraining the segmentation based on at least one plane to obtain a segmentation that includes at least one boundary or other feature having a desired property,
wherein the refining or constraining of the segmentation comprises preserving a desired geometry of the at least one boundary or other feature to be flat or non-curved after obtaining the segmentation.
20. A non-transitory computer-readable medium storing instructions that are executable to:
receive medical image data;
segment a body part included in the medical image data into multiple regions; and
refine or constrain the segmentation based on at least one plane to obtain a segmentation that includes at least one boundary or other feature having a desired property,
wherein the refining or constraining of the segmentation comprises preserving a desired geometry of the at least one boundary or other feature to be flat or non-curved after obtaining the segmentation.