Systems and methods for medical image processing using deep neural network

1. A medical image processing method comprising:

receiving a first medical image having a first characteristic and one or more acquisition parameters corresponding to acquisition of the first medical image;

incorporating the one or more acquisition parameters into a trained deep neural network; and

mapping, by the trained deep neural network, the first medical image to a second medical image having a second characteristic.

2. The method of claim 1 , wherein the first image comprises an image having an artifact and the second image comprises a reduced artifact image.

3. The method of claim 1 , wherein the artifact comprises blurring, ringing, or ghosting effect in the first image.

4. The method of claim 1 , wherein the first image comprises an unsegmented image and the second image comprises a segmented image.

5. The method of claim 1 , wherein the first image comprises an unlabeled image and the second image comprises a labeled image.

6. The method of claim 1 , wherein incorporating the one or more acquisition parameters into the trained deep neural network comprises providing a preprocessing layer.

7. The method of claim 6 , wherein the preprocessing layer generates images with estimated corrections.

8. The method of claim 6 , wherein incorporating the one or more acquisition parameters into the trained deep neural network comprises:

mapping the one or more acquisition parameters to one or more weights; and

incorporating the one or more weights into the one or more trained deep neural networks.

9. The method of claim 8 , wherein the trained deep neural network comprises a convolutional neural network, and wherein incorporating the one or more weights into the trained deep neural network comprises setting one or more convolutional filter weights and/or one or more deconvolutional filter weights based on the one or more weights.

10. The method of claim 1 , wherein incorporating the one or more acquisition parameters into the trained deep neural network comprises:

mapping the one or more acquisition parameters to a plurality of values;

concatenating the plurality of values with a plurality of pixel or voxel data of the first medical image; and

inputting the plurality of values and the plurality of pixel or voxel data of the first medical image into an input layer of the trained deep neural network.

11. The method of claim 1 , further comprising training the deep neural network by using a plurality pairs of sharp medical images and corresponding first medical images.

12. The method of claim 1 , wherein the medical image is one of a magnetic resonance (MR) image, computed tomography (CT) image, positron emission tomography (PET) image, X-ray image, or ultrasound image.

13. The method of claim 1 , wherein the one or more acquisition parameters comprise one or more of echo train length, echo spacing, flip angle, voxel spatial dimension, sampling pattern, acquisition order, acceleration factor, physiological state, image reconstruction parameter, detector size, detector number, source-to-detector distance, collimator geometry, slice thickness, dose, detector type, detector geometry, ring radius, positron range, depth/line of response, transducer geometry, central frequency, ringdown, spatial pulse length, focal depth, beam apodization, or side lobe amplitude.

14. A medical image processing system comprising:

a memory storing a trained deep neural network and an acquisition parameter transform; and

a processor communicably coupled to the memory and configured to:

receive a first medical image having a first characteristic;

receive one or more acquisition parameters, wherein the one or more acquisition parameters correspond to acquisition of the first medical image;

map the acquisition parameter to a first output using the acquisition parameter transform;

incorporate the first output into the trained deep neural network;

map the first medical image to a second output using the trained deep neural network; and

produce a second medical image having a second characteristic using the second output.

15. The system of claim 14 , wherein the first image comprises an image having an artifact and the second image comprises a reduced artifact image.

16. The method of claim 15 , wherein the artifact comprises blurring, ringing, or ghosting effect in the first image.

17. The system of claim 14 , wherein the trained deep neural network is a trained convolutional neural network, wherein the first output is one or more weights, and wherein the processor is configured to incorporate the first output into the trained deep neural network by setting one or more convolutional filter weights and/or one or more deconvolutional filter weights of the convolutional neural network based on the one or more weights.

18. The system of claim 17 , wherein the acquisition parameter transform comprises an analytical model which maps the one or more acquisition parameters to the one or more weights.

19. The system of claim 18 , wherein the analytical model is based on a point-spread-function.

20. The system of claim 14 , wherein the first output is a plurality of values, and wherein the processor is configured to incorporate the first output into the trained deep neural network by conconcatenating the plurality of values with a plurality of pixel or voxel data of the first medical image as input to the trained deep neural network.

21. The system of claim 20 , wherein the acquisition parameter transform comprises another trained deep neural network that maps the one or more acquisition parameters to the plurality of values.