Method and system for image registration using an intelligent artificial agent
Methods and systems for image registration using an intelligent artificial agent are disclosed. In an intelligent artificial agent based registration method, a current state observation of an artificial agent is determined based on the medical images to be registered and current transformation parameters. Action-values are calculated for a plurality of actions available to the artificial agent based on the current state observation using a machine learning based model, such as a trained deep neural network (DNN). The actions correspond to predetermined adjustments of the transformation parameters. An action having a highest action-value is selected from the plurality of actions and the transformation parameters are adjusted by the predetermined adjustment corresponding to the selected action. The determining, calculating, and selecting steps are repeated for a plurality of iterations, and the medical images are registered using final transformation parameters resulting from the plurality of iterations.
1. A method for registration of medical images; comprising:
performing an initial registration of a first medical image acquired at a first time and a second medical image acquired at a second time using a first trained deep neural network;
generating higher-resolution patches around anatomical landmarks for the first medical image and the second medical image, the higher-resolution patches having a higher resolution than the first medical image and the second medical image; and
refining the initial registration based on the higher-resolution patches using a second trained deep neural network to register the first medical image and the second medical image.
2. The method of claim 1 , wherein the first medical image is a pre-operative image and the second medical image is an interventional image.
3. The method of claim 2 , wherein a therapy is guided based on the registration of the first medical image and the second medical image.
4. The method of claim 1 , wherein the first medical image is a past image of a patient and the second medical image is a follow-up image of the patient.
5. The method of claim 4 , wherein longitudinal change analysis is performed based on the registration of the first medical image and the second medical image.
6. The method of claim 1 , wherein the first medical image is of a first modality and the second medical image is of a second modality.
7. The method of claim 1 , wherein generating higher-resolution patches around anatomical landmarks for the first medical image and the second medical image comprises:
extracting the higher-resolution patches from a version of the first medical image and a version of the second medical image having the higher resolution.
8. The method of claim 7 , wherein generating higher-resolution patches around anatomical landmarks for the first medical image and the second medical image further comprises:
up-sampling the first medical image and the second medical image to generate the version of the first medical image and the version of the second medical image having the higher resolution.
9. The method of claim 1 , further comprising down-sampling a version of the first medical image and a version of the second medical image having the higher resolution to generate the first medical image and the second medical image, wherein generating higher-resolution patches around anatomical landmarks for the first medical image and the second medical image comprises:
extracting the higher-resolution patches from the first medical image and the second medical image.
10. An apparatus for registration of medical images; comprising:
means for performing an initial registration of a first medical image acquired at a first time and a second medical image acquired at a second time using a first trained deep neural network;
means for generating higher-resolution patches around anatomical landmarks for the first medical image and the second medical image, the higher-resolution patches having a higher resolution than the first medical image and the second medical image; and
means for refining the initial registration based on the higher-resolution patches using a second trained deep neural network to register the first medical image and the second medical image.
11. The apparatus of claim 10 , wherein the first medical image is a pre-operative image and the second medical image is an interventional image.
12. The apparatus of claim 11 , wherein a therapy is guided based on the registration of the first medical image and the second medical image.
13. The apparatus of claim 10 , wherein the first medical image is a past image of a patient and the second medical image is a follow-up image of the patient.
14. The apparatus of claim 13 , wherein longitudinal change analysis is performed based on the registration of the first medical image and the second medical image.
15. A non-transitory computer readable medium storing computer program instructions for registration of medical images, the computer program instructions defining operations comprising:
performing an initial registration of a first medical image acquired at a first time and a second medical image acquired at a second time using a first trained deep neural network;
generating higher-resolution patches around anatomical landmarks for the first medical image and the second medical image, the higher-resolution patches having a higher resolution than the first medical image and the second medical image; and
refining the initial registration based on the higher-resolution patches using a second trained deep neural network to register the first medical image and the second medical image.
16. The non-transitory computer readable medium of claim 15 , wherein the first medical image is a pre-operative image and the second image is an interventional image.
17. The non-transitory computer readable medium of claim 16 , wherein a therapy is guided based on the registration of the first medical image and the second medical image.
18. The non-transitory computer readable medium of claim 15 , wherein the first medical image is a past image of a patient and the second medical image is a follow-up image of the patient.
19. The non-transitory computer readable medium of claim 18 , wherein longitudinal change analysis is performed based on the registration of the first medical image and the second medical image.
20. The non-transitory computer readable medium of claim 15 , wherein the first medical image is of a first modality and the second medical image is of a second modality.