US 2021/0233239 A1 · SYSTEMS AND METHODS FOR MEDICAL IMAGE STYLE TRANSFER USING DEEP NEURAL NETWORKS

Abstract

The current disclosure provides for mapping medical images to style transferred medical images using deep neural networks, while maintaining clinical quality of the style transferred medical image, thereby enabling a clinician to evaluate medical images in a preferred style without loss of clinically relevant content. In one embodiment the current disclosure provides for a method comprising, acquiring a medical image of an anatomical region of a subject, wherein the medical image is in a first style, selecting a target style, wherein the target style is distinct from the first style, selecting a clinical quality metric, selecting a trained style transfer network based on the target style and the clinical quality metric, mapping the medical image to a style transferred medical image using the trained style transfer network, wherein the style transferred medical image is in the target style, and displaying the style transferred medical image via a display device.

Claims20

Dependent claims

A method comprising:

acquiring a medical image of an anatomical region of a subject, wherein the medical image is in a first style;
selecting a target style, wherein the target style is distinct from the first style;
selecting a clinical quality metric;
selecting a trained style transfer network based on the target style and the clinical quality metric;
mapping the medical image to a style transferred medical image using the trained style transfer network, wherein the style transferred medical image is in the target style;
and
displaying the style transferred medical image via a display device.

4 more elements

A method comprising:

selecting a set of medical images, wherein the set of medical images are in a first style;
selecting a set of target images, wherein the set of target images are in a second style, and wherein the set of medical images and the set of target images are unpaired;
selecting a clinical quality estimator;
selecting a style similarity estimator;
selecting an image content regularizer;
training a style transfer network using the set of medical images, the set of target images, the clinical quality estimator, the style similarity estimator, and the image content regularizer, to produce a trained style transfer network;
receiving a medical image, wherein the medical image is in the first style;
mapping the medical image to a style transferred medical image using the trained style transfer network, wherein the style transferred medical image is in the second style;
and
displaying the style transferred medical image via a display device.

7 more elements

An image processing system comprising:

a display device;
a user input device;
a memory storing a trained style transfer network and instructions;
and
a processor communicably coupled to the display device, the user input device, and the memory, and when executing the instructions, configured to:
receive a medical image of an anatomical region of a subject, wherein the medical image is in a first style;
receive a target style selection via the user input device, wherein the target style selection indicates a target style;
receive a clinical quality metric selection via the user input device, wherein the clinical quality metric selection indicates a clinical quality metric;
select a trained style transfer network based on the target style and the clinical quality metric;
map the medical image to a style transferred medical image using the trained style transfer network, wherein the style transferred medical image is in the target style;
and
display the style transferred medical image via the display device.

9 more elements

Dependencies are inferred from the claim text.

Systems and methods for medical image style transfer using deep neural networks

Life of this patent

Systems and methods for medical image style transfer using deep neural networks

Life of this patent

Abstract

Claims20