Reinforcement Learning for Online Sampling Trajectory Optimization for Magnetic Resonance Imaging

• US 20200134887A1
• Filed: 10/16/2019
• Published: 04/30/2020
• Est. Priority Date: 10/25/2018
• Status: Active Grant

• Current Assignee: Board of Trustees of the Leland Stanford Junior University (Stanford Management Co.)
• Original Assignee: Board of Trustees of the Leland Stanford Junior University (Stanford Management Co.)
• Inventors: Zeng, David Y., Vasanawala, Shreyas S., Cheng, Joseph Yitan
• Granted Patent: US 11,062,490 B2
• Time in Patent Office: Days
• CPC Class Codes: A61B 5/055 involving electronic [EMR] or nuclear [NMR] magnetic resonance, e.g. magnetic resonance imaging
• CPC Class Codes: G01R 33/4818 MR characterised by data acquisition along a specific k-space trajectory or by the temporal order of k-space coverage, e.g. centric or segmented coverage of k-space
• CPC Class Codes: G01R 33/5608 Data processing and visualization specially adapted for MR, e.g. for feature analysis and pattern recognition on the basis of measured MR data, segmentation of measured MR data, edge contour detection on the basis of measured MR data, for enhancing measured MR data in terms of signal-to-noise ratio by means of noise filtering or apodization, for enhancing measured MR data in terms of resolution by means for deblurring, windowing, zero filling, or generation of gray-scaled images, colour-coded images or images displaying vectors instead of pixels image data processing or generation, in general G06T
• CPC Class Codes: G01R 33/561 by reduction of the scanning time, i.e. fast acquiring systems, e.g. using echo-planar pulse sequences
• CPC Class Codes: G06N 3/006 based on simulated virtual individual or collective life forms, e.g. social simulations or particle swarm optimisation [PSO]
• CPC Class Codes: G06N 3/04 Architecture, e.g. interconnection topology
• CPC Class Codes: G06N 3/045 Combinations of networks
• CPC Class Codes: G06N 3/08 Learning methods
• CPC Class Codes: G06N 3/088 Non-supervised learning, e.g. competitive learning
• CPC Class Codes: G06N 7/01 Probabilistic graphical models, e.g. probabilistic networks
• CPC Class Codes: G06T 11/006 Inverse problem, transformation from projection-space into object-space, e.g. transform methods, back-projection, algebraic methods
• CPC Class Codes: G06T 2207/10088 Magnetic resonance imaging [MRI]
• CPC Class Codes: G06T 2207/20081 Training; Learning
• CPC Class Codes: G06T 2207/20084 Artificial neural networks [ANN]

Abstract

A magnetic resonance imaging scan performs an MRI acquisition using an undersampling pattern to produce undersampled k-space data; adds the undersampled k-space data to aggregate undersampled k-space data for the scan; reconstructs an image from the aggregate undersampled k-space data; updates the undersampling pattern from the reconstructed image and aggregate undersampled k-space data using a deep reinforcement learning technique defined by an environment, reward, and agent, where the environment comprises an MRI reconstruction technique, where the reward comprises an image quality metric, and where the agent comprises a deep convolutional neural network and fully connected layers; and repeats these steps to produce a final reconstructed MRI image for the scan.

Claims

1. A method for performing a magnetic resonance imaging scan, the method comprising:

a) performing an MRI acquisition using an undersampling pattern to produce undersampled k-space data;

b) adding the undersampled k-space data to aggregate undersampled k-space data for the scan;

c) reconstructing an image from the aggregate undersampled k-space data;

d) updating the undersampling pattern from the reconstructed image and aggregate undersampled k-space data using a deep reinforcement learning technique defined by an environment, reward, and agent, where the environment comprises an MRI reconstruction technique, where the reward comprises an image quality metric, and where the agent comprises a deep convolutional neural network and fully connected layers;

e) repeating steps (a), (b), (c), and (d) to produce a final reconstructed MRI image for the scan.

2. The method of claim 1

where the MRI reconstruction technique produces a reconstructed image as output from undersampled k-space data as input.

3. The method of claim 1

where the image quality metric of the reward uses an L₂ norm, L₁ norm, discriminators from trained generative adversarial networks, losses trained with semi-supervised techniques, and/or deep learning measures of image quality.

4. The method of claim 3

where the deep learning measures of image quality are sharpness and/or signal-to-noise ratio.

5. The method of claim 1

where the agent is configured to have the reconstructed image and the aggregate undersampled k-space data as input and the updated undersampling pattern as output.

6. The method of claim 1

where the agent is implemented as a three-layer residual convolutional neural network.