Automatic, dynamic, and adaptive slice planning for cardiac MRI acquisition
Systems and methods for predicting a location for acquiring a target view of an anatomical object of interest in an input image are provided. An input image of an anatomical object of interest of a patient is received. An output image is generated using a machine learning based network. The output image depicts a projection of a 3D image plane for acquiring a target view of the anatomical object of interest identified on the input image. The output image is output.
1. A method comprising:
receiving an input image of an anatomical object of interest of a patient;
generating an output image using a machine learning based network, the machine learning based network receiving as input the input image and generating as output the output image depicting a projection of a 3D image plane representing a location for acquiring a target view of the anatomical object of interest in the input image, the projection of the 3D image plane determined based on an intersection of an imaging plane of the input image and an imaging plane of the target view; and
outputting the output image.
2. The method of claim 1 , wherein the projection of the 3D image plane for acquiring the target view of the anatomical object of interest is represented as a continuous region defined by a pair of boundary lines in the input image, the continuous region determined by computing a distance transform based on a distance between the intersection and points extending away from the intersection.
3. The method of claim 1 , wherein the projection of the 3D image plane for acquiring the target view of the anatomical object of interest comprises a line in the input image representing the intersection.
4. The method of claim 1 , further comprising receiving one or more additional input images of the anatomical object of interest, wherein generating an output image using a machine learning based network comprises:
generating the output image using the machine learning based network based on the one or more additional input images.
5. The method of claim 1 , wherein the input image comprises a localizer image.
6. The method of claim 1 , wherein the input image comprises a previously acquired target view of the anatomical object of interest.
7. The method of claim 1 , wherein the anatomical object of interest is a heart of the patient.
8. The method of claim 7 , wherein the target view comprises one of a short axis view, a 2-chamberview, a 3-chamberview, or a 4-chamberview of the heart.
9. The method of claim 1 , further comprising:
acquiring the target view of the anatomical object of interest based on the output image.
10. An apparatus comprising:
means for receiving an input image of an anatomical object of interest of a patient;
means for generating an output image using a machine learning based network, the machine learning based network receiving as input the input image and generating as output the output image depicting a projection of a 3D image plane representing a location for acquiring a target view of the anatomical object of interest in the input image, the projection of the 3D image plane determined based on an intersection of an imaging plane of the input image and an imaging plane of the target view; and
means for outputting the output image.
11. The apparatus of claim 10 , wherein the projection of the 3D image plane for acquiring the target view of the anatomical object of interest is represented as a continuous region defined by a pair of boundary lines in the input image, the continuous region determined by computing a distance transform based on a distance between the intersection and points extending away from the intersection.
12. The apparatus of claim 10 , wherein the projection of the 3D image plane for acquiring the target view of the anatomical object of interest comprises a line in the input image representing the intersection.
13. A non-transitory computer readable medium storing computer program instructions, the computer program instructions when executed by a processor cause the processor to perform operations comprising:
receiving an input image of an anatomical object of interest of a patient;
generating an output image using a machine learning based network, the machine learning based network receiving as input the input image and generating as output the output image depicting a projection of a 3D image plane representing a location for acquiring a target view of the anatomical object of interest in the input image, the projection of the 3D image plane determined based on an intersection of an imaging plane of the input image and an imaging plane of the target view; and
outputting the output image.
14. The non-transitory computer readable medium of claim 13 , the operations further comprising receiving one or more additional input images of the anatomical object of interest, wherein generating an output image using a machine learning based network comprises:
generating the output image using the machine learning based network based on the one or more additional input images.
15. The non-transitory computer readable medium of claim 13 , wherein the input image comprises a localizer image.
16. The non-transitory computer readable medium of claim 13 , wherein the input image comprises a previously acquired target view of the anatomical object of interest.
17. The non-transitory computer readable medium of claim 13 , wherein the anatomical object of interest is a heart of the patient.
18. The non-transitory computer readable medium of claim 17 , wherein the target view comprises one of a short axis view, a 2-chamberview, a 3-chamberview, or a 4-chamberview of the heart.