# US 2019/0378311 A1 · Machine-Learned Network for Fourier Transform in Reconstruction for Medical Imaging

> Agents: this data is available as JSON from the patentgrep API and MCP server — see https://patentgrep.com/llms.txt

- Number: US 2019/0378311 A1
- Document ID: US20190378311A1
- Status: Published application
- Kind: A1
- Application number: 16/150,304
- Filed: 2018-10-03
- Published: 2019-12-12
- Earliest claimed: 2018-06-12
- Assignees: Siemens Healthcare GmbH
- Applicants: Siemens Healthcare GmbH
- Inventors: Boris Mailhe; Simon Arberet; Florent Billy Romaric Gbelidji; Mariappan S. Nadar
- Web page: https://patentgrep.com/patent/US20190378311A1

## CPC

- G06T 12/20: Inverse problem, i.e. transformations from projection space into object space
- G06F 17/142: {Fast Fourier transforms, e.g. using a Cooley-Tukey type algorithm}
- G06N 3/044: Recurrent networks, e.g. Hopfield networks
- G06N 3/045: Combinations of networks
- G06N 3/0455: Auto-encoder networks; Encoder-decoder networks
- G06N 3/0464: Convolutional networks [CNN, ConvNet]
- G06N 3/047: Probabilistic or stochastic networks
- G06N 3/048: Activation functions
- G06N 3/08: Learning methods
- G06N 3/084: Backpropagation, e.g. using gradient descent
- G06N 3/088: Non-supervised learning, e.g. competitive learning
- G06N 3/09: Supervised learning
- G16H 30/40: for processing medical images, e.g. editing
- G16H 50/20: for computer-aided diagnosis, e.g. based on medical expert systems
- G06T 2211/441: AI-based methods, deep learning or artificial neural networks
- G06T: IMAGE DATA PROCESSING OR GENERATION, IN GENERAL
- G06F: ELECTRIC DIGITAL DATA PROCESSING (computer systems based on specific computational models G06N)
- G06N: COMPUTING ARRANGEMENTS BASED ON SPECIFIC COMPUTATIONAL MODELS
- G16H: HEALTHCARE INFORMATICS, i.e. INFORMATION AND COMMUNICATION TECHNOLOGY [ICT] SPECIALLY ADAPTED FOR THE HANDLING OR PROCESSING OF MEDICAL OR HEALTHCARE DATA

## Abstract

For low-complexity to learned reconstruction and/or learned Fourier transform-based operators for reconstruction, a neural network is used for the transform operators. The network architecture is modeled on the Cooley-Tukey fast Fourier transform (FFT) approach. By splitting input data before recursive calls in the network architecture, the network may be trained to perform the transform with similar complexity as FFT. The learned operators may be used in a trained network for reconstruction, such as with a learned iterative framework and image regularizer.

## Claims

### Claim 1

A method for converting data between scan space and image domain in an imaging system, the method comprising:
scanning, by the imaging system, an object, the scanning resulting in input data representing the patient;
performing a fast transform of the input data based on application of the input data to a machine-learned neural network, the machine-learned neural network comprising an architecture of a sequence of a convolutional splitting layer, parallel recursive deep networks, a diagonal linear layer, and a convolutional butterfly layer;
generating image domain data from an output of the machine-learned neural network; and
displaying an image from the image domain data.

### Claim 2 (depends on 1)

The method of claim 1 wherein performing comprises performing with the architecture of the machine-learned network being structured as a radix fast Fourier transform.

### Claim 3 (depends on 1)

The method of claim 1 wherein performing comprises performing with the convolutional spitting layer have a stride of R, R being two or greater.

### Claim 4 (depends on 1)

The method of claim 1 wherein performing comprises performing with the recursive deep networks comprising nested radix fast Fourier transform networks at iteratively reducing scales.

### Claim 5 (depends on 4)

The method of claim 4 wherein performing comprises performing with the nested radix fast Fourier transform networks having unshared weights.

### Claim 6 (depends on 5)

The method of claim 5 wherein performing comprises performing with a number of output channels being equal to a number of a stride of the convolution splitting layer.

### Claim 7 (depends on 6)

The method of claim 6 wherein performing comprises performing with the convolution splitting layer being two-dimensional, the number of output channels being four and the stride being four.

### Claim 8 (depends on 6)

The method of claim 6 wherein performing comprises performing with a complexity of O(N log N) where N is a total number of samples of the image domain data.

### Claim 9 (depends on 1)

The method of claim 1 wherein performing comprises performing with the diagonal layer being a twiddle layer.

### Claim 10 (depends on 9)

The method of claim 9 wherein the twiddle layer comprises a neural network layer defined to learn weights in diagonal linear operations.

### Claim 11 (depends on 1)

The method of claim 1 wherein performing comprises performing with the convolution butterfly layer being a sum and difference-based convolutional layer.

### Claim 12 (depends on 1)

The method of claim 1 wherein generating the image domain data comprises reconstructing with a machine-learned reconstruction network trained with gradient descent and regularization and including the machine-learned neural network.

### Claim 13 (depends on 1)

The method of claim 1 wherein displaying comprises displaying the magnetic resonance image as a two-dimensional magnetic resonance image.

### Claim 14

A system for reconstruction in medical imaging, the system comprising:
a medical scanner configured to scan a patient, the scan providing scan data;
a reconstruction processor configured to reconstruct an image from the scan data, the reconstruction processor configured to reconstruct with a machine-learned neural network containing blocks having a radix fast Fourier transform architecture;
a display configured to display the image as reconstructed from the scan data.

### Claim 15 (depends on 14)

The system of claim 14 wherein the medical scanner comprises a magnetic resonance scanner and where in the image comprises a magnetic resonance image.

### Claim 16 (depends on 14)

The system of claim 14 wherein the radix fast Fourier transform architecture comprises a convolutional splitting layer with a stride of 2 or greater, parallel recursive deep networks, a diagonal linear layer, and a convolutional butterfly layer.

### Claim 17 (depends on 14)

The system of claim 14 wherein the machine-learned neural network is configured to perform forward or adjoint measurement operations.

### Claim 18

A method for Fourier transform-based reconstruction in a medical imaging system, the method comprising:
scanning, by the medical imaging system, a patient, the scanning resulting in scan data representing the patient;
reconstructing an image of the patient from the scan data, the reconstructing being based on a model of the medical imaging system, the model including a transformation implemented by a trained neural network having a convolution layer to split an input prior to a layer for recursive calls;
displaying the image of the patient.

### Claim 19 (depends on 18)

The method of claim 18 wherein reconstructing comprises reconstructing with the transformation being a fast Fourier transformation and the trained neural network including a layer with a diagonal operator after the layer for recursive calls and a convolution layer after the layer with the diagonal operator.

### Claim 20 (depends on 18)

The method of claim 18 wherein reconstructing comprises reconstructing with the trained neural network having an architecture with a Cooley-Tukey fast Fourier transform structure, the structure including the convolution layer to split and the layer for the recursive calls.
