# US 11,896,360 B2 · Systems and methods for generating thin image slices from thick image slices

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

- Number: US 11,896,360 B2
- Document ID: US11896360B2
- Status: Granted
- Kind: B2
- Application number: 16/979,104
- Filed: 2019-03-12
- Published: 2020-12-24
- Granted: 2024-02-13
- Earliest claimed: 2018-03-12
- Assignees: LVIS Corporation
- Applicants: LVIS Corporation; The Board of Trustees of the Leland Stanford Junior University
- Inventors: Zhongnan Fang; Akshay S. Chaudhari; Jin Hyung Lee; Brian A. Hargreaves
- Web page: https://patentgrep.com/patent/US11896360B2

## CPC

- A61B 5/055: involving electronic [EMR] or nuclear [NMR] magnetic resonance, e.g. magnetic resonance imaging
- A61B 5/7267: {involving training the classification device}
- G06N 3/045: Combinations of networks
- G06N 3/0464: Convolutional networks [CNN, ConvNet]
- G06N 3/048: Activation functions
- G06N 3/08: Learning methods
- G06N 3/09: Supervised learning
- G06T 3/4053: based on super-resolution, i.e. the output image resolution being higher than the sensor resolution
- G06T 5/60: using machine learning, e.g. neural networks
- G06T 5/73: Deblurring; Sharpening
- G06T 15/00: Three-dimensional [3D] image rendering
- G16H 50/70: for mining of medical data, e.g. analysing previous cases of other patients
- A61B 2576/00: Medical imaging apparatus involving image processing or analysis (A61B1/00009, A61B6/52 and A61B8/52 take precedence)
- G06T 2207/10072: Tomographic images
- G06T 2207/10136: 3D ultrasound image
- G06T 2207/20081: Training; Learning
- G06T 2207/20084: Artificial neural networks [ANN]
- G06T 2207/30004: Biomedical image processing
- G16H 30/40: for processing medical images, e.g. editing
- A61B: DIAGNOSIS; SURGERY; IDENTIFICATION (usefulness limited to only animals A61D)
- G06N: COMPUTING ARRANGEMENTS BASED ON SPECIFIC COMPUTATIONAL MODELS
- G06T: IMAGE DATA PROCESSING OR GENERATION, IN GENERAL
- G16H: HEALTHCARE INFORMATICS, i.e. INFORMATION AND COMMUNICATION TECHNOLOGY [ICT] SPECIALLY ADAPTED FOR THE HANDLING OR PROCESSING OF MEDICAL OR HEALTHCARE DATA

## Abstract

Systems and methods for generating thin slice images from thick slice images are disclosed herein. In some examples, a deep learning system may calculate a residual from a thick slice image and add the residual to the thick slice image to generate a thin slice image. In some examples, the deep learning system includes a neural network. In some examples, the neural network may include one or more levels, where one or more of the levels include one or more blocks. In some examples, each level includes a convolution block and a non-linear activation function block. The levels of the neural network may be in a cascaded arrangement in some examples.

## Claims

### Claim 1

A method of generating thin slice images from thick slice images, the method comprising:
receiving a first image having a first resolution at a neural network;
performing a convolution on the first image with the neural network;
performing a non-linear activation function on the first image with the neural network;
repeating the convolution and non-linear activation function;
generating a residual based on the convolution; and
summing the residual and the first image with the neural network to generate a second image having a second resolution, wherein the second resolution is higher than the first resolution.

### Claim 2 (depends on 1)

The method of claim 1, wherein the performing the convolution and performing the non-linear activation function are performed and repeated in a plurality of layers of the neural network, wherein the first image is an input of a first layer of the plurality of layers, an output of the first layer of the plurality of layers is an input of a second layer of the plurality of layers, and an output of a last layer of the plurality of layers is the residual.

### Claim 3 (depends on 1)

The method of claim 1, further comprising training the neural network on a training data set, wherein the training data set includes a plurality of first images and a plurality of second images.

### Claim 4 (depends on 1)

The method of claim 1, further comprising testing the neural network on a testing data set, wherein the testing data set includes a plurality of first images.

### Claim 5 (depends on 1)

The method of claim 1, wherein performing the convolution includes performing a three dimensional convolution.

### Claim 6 (depends on 1)

The method of claim 1, wherein training the neural network includes dividing the first images into a plurality of pixel patches.

### Claim 7 (depends on 1)

The method of claim 1, wherein the non-linear activation function includes a form of R(x)=max(0,x).

### Claim 8 (depends on 1)

The method of claim 1, further comprising acquiring the first image from an imaging system.

### Claim 9 (depends on 8)

The method of claim 8, wherein the imaging system is a magnetic resonance imaging system.

### Claim 10

A system for generating thin slice images from thick slices images, the system comprising:
a non-transitory computer readable medium including instructions for implementing a neural network, wherein the neural network comprises a level including a convolution block and a rectified linear unit non-linear activation block, wherein the level is configured to generate a residual from a first image having a first resolution received by the neural network, wherein the neural network is configured to sum the first image and the residual to generate a second image having a second resolution, wherein the second resolution is higher than the first resolution; and
a processor configured to execute the instructions to implement the neural network.

### Claim 11 (depends on 10)

The system of claim 10, further comprising a display configured to display the second image.

### Claim 12 (depends on 10)

The system of claim 10, wherein the convolution block applies a three dimensional convolution and thresholding using rectified linear unit function to the first image.

### Claim 13 (depends on 10)

The system of claim 10, wherein the neural network includes a plurality of levels, wherein an output of a first level of the plurality of levels is provided as an input to a second level of the plurality of levels.

### Claim 14 (depends on 13)

The system of claim 13, wherein a last level of the plurality of levels does not include the rectified linear unit non-linear activation block.

### Claim 15 (depends on 13)

The system of claim 13, wherein a last level of the plurality of levels has a dimension less than others of the plurality of levels.

### Claim 16 (depends on 10)

The system of claim 10, wherein the neural network divides the first image into a plurality of pixel patches.

### Claim 17 (depends on 16)

The system of claim 16, wherein the plurality of pixel patches overlap.

### Claim 18 (depends on 17)

The system of claim 17, wherein the plurality of pixel patches overlap by 50%.

### Claim 19 (depends on 10)

The system of claim 10, wherein the convolution block applies a zero- padded convolution and an output of the zero-padded convolution is cropped to an original size of the input image.

### Claim 20 (depends on 10)

The system of claim 10, wherein the convolution block outputs a plurality of feature maps.

### Claim 21

A system for generating high resolution images from low resolution images, the system comprising:
an image acquisition unit configured to acquire a first image of a feature of interest at a first resolution;
a computing system configured to implement a deep learning system, wherein the deep learning system is configured to receive the first image of the feature of interest and, perform a convolution on the first image, perform a non-linear activation function on the first image, repeat the convolution and non-linear activation function, generate a residual based on the convolution, and sum the residual and the first image to generate a second image of the feature of interest at a second resolution, wherein the second resolution is higher than the first resolution; and
a display configured to display the second image of the feature of interest.

### Claim 22 (depends on 21)

The system of claim 21, wherein the image acquisition unit is a magnetic resonance imaging system.

### Claim 23 (depends on 21)

The system of claim 21, wherein the deep learning system generates the second image by supplementing the first image.

### Claim 24 (depends on 21)

The system of claim 21, wherein the computing system is configured to implement a second deep learning system and the second image of the feature of interest is provided as an input to the second deep learning system.