Deep-learnt tissue deformation for medical imaging
AssigneeSiemens Healthcare GmbH
InventorLi Zhang
Life of this patent
Estimating the term…
Abstract
A deep machine-learning approach is used for medical image fusion by a medical imaging system. This one approach may be used for different applications. For a given application, the same deep learning is used but with different application-specific training data. The resulting deep-learnt classifier provides a reduced feature vector in response to input of intensities of one image and displacement vectors for patches of the one image relative to another image. The output feature vector is used to determine the deformation for medical image fusion.
Claims20
(canceled)
(canceled)
(canceled)
(canceled)
(canceled)
(canceled)
(canceled)
(canceled)
(canceled)
(canceled)
(canceled)
(canceled)
(canceled)
A method for medical image fusion by a medical imaging system, the method comprising:
- acquiring first and second sets of scan data representing a patient with anatomy represented by the first set of scan data deformed relative to anatomy represented by the second set of scan data;
- determining a deformation field aligning the anatomy of the first and second sets of scan data with a machine-learnt deep neural network;
- and
- generating a medical image from the first and second sets of scan data and the deformation field.
A system for medical image fusion, the system comprising:
- at least one medical imaging system configured to acquire first and second data representing a patient, tissue represented in the first data displaced relative to the tissue represented in the second data;
- an image processor configured to register the tissue of the first data with the second data by application of a deep-learnt neural network;
- and
- a display configured to display an image based on the registration.
Dependencies are inferred from the claim text.