# US 2025/0095239 A1 · Methods and systems for generating dual-energy images from a single-energy imaging system

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

- Number: US 2025/0095239 A1
- Document ID: US20250095239A1
- Status: Published application
- Kind: A1
- Application number: 18/471,181
- Filed: 2023-09-20
- Published: 2025-03-20
- Earliest claimed: 2023-09-20
- Assignees: GE Precision Healthcare LLC
- Applicants: GE Precision Healthcare LLC
- Inventors: Rajesh Langoju; Utkarsh Agrawal; Bipul Das; Risa Shigemasa; Yasuhiro Imai; Kok Yen Tham; Yuri Teraoka
- Web page: https://patentgrep.com/patent/US20250095239A1

## CPC

- G06T 12/20: Inverse problem, i.e. transformations from projection space into object space
- G06T 12/30: Image post-processing, e.g. metal artefact correction
- G06V 10/764: using classification, e.g. of video objects
- G06V 10/774: Generating sets of training patterns; Bootstrap methods, e.g. bagging or boosting
- G06V 20/50: Context or environment of the image
- G16H 30/40: for processing medical images, e.g. editing
- G06T 2210/41: Medical
- G06T 2211/408: Dual energy
- G06T 2211/441: AI-based methods, deep learning or artificial neural networks
- G06V 2201/03: Recognition of patterns in medical or anatomical images
- G06T: IMAGE DATA PROCESSING OR GENERATION, IN GENERAL
- G06V: IMAGE OR VIDEO RECOGNITION OR UNDERSTANDING
- G16H: HEALTHCARE INFORMATICS, i.e. INFORMATION AND COMMUNICATION TECHNOLOGY [ICT] SPECIALLY ADAPTED FOR THE HANDLING OR PROCESSING OF MEDICAL OR HEALTHCARE DATA

## Abstract

Various methods and systems are provided for transforming images from one energy level to another. In an example, a method includes obtaining an image at a first energy level acquired with a single-energy computed tomography (CT) imaging system, identifying a contrast phase of the image, entering the image as input into an energy transformation model trained to output a transformed image at a second energy level, different than the first energy level, the energy transformation model selected from among a plurality of energy transformation models based on the contrast phase, and displaying a final transformed image and/or saving the final transformed image in memory, wherein the final transformed image is the transformed image or is generated based on the transformed image.

## Claims

### Claim 1

A method, comprising:
obtaining an image at a first energy level acquired with a single-energy computed tomography (CT) imaging system;
identifying a contrast phase of the image;
entering the image as input into an energy transformation model trained to output a transformed image at a second energy level, different than the first energy level, the energy transformation model selected from among a plurality of energy transformation models based on the contrast phase; and
displaying a final transformed image and/or saving the final transformed image in memory, wherein the final transformed image is the transformed image or is generated based on the transformed image.

### Claim 2 (depends on 1)

The method of claim 1, wherein identifying the contrast phase of the image comprises identifying the contrast phase of the image with a contrast phase classifier, the contrast phase classifier comprising a deep learning model trained with a plurality of training triads, each training triad including a set of projection images generated from a 3D volume of a subject.

### Claim 3 (depends on 2)

The method of claim 2, wherein each set of projection images includes a first annotated maximum intensity projection (MIP) training image in a first scanning plane, a second annotated MIP training image in a second scanning plane, and a third annotated MIP training image in a third scanning plane, and wherein a respective annotation of each annotated MIP training image indicates the contrast phase included in that annotated MIP training image.

### Claim 4 (depends on 1)

The method of claim 1, wherein the energy transformation model is trained with training pairs, each training pair including a first training image at the first energy level and a second training image at the second energy level, and wherein the first training image and the second training image are monochromatic images acquired with a dual-energy CT imaging system.

### Claim 5 (depends on 4)

The method of claim 4, wherein, during training, the energy transformation model is configured to output a transformed training image based on an input first training image, and wherein the energy transformation model is further trained based on an inverse training image, the inverse training image generated by an inverse energy transformation model based on the transformed training image.

### Claim 6 (depends on 1)

The method of claim 1, wherein the energy transformation model is a first energy transformation model and the transformed image is a first transformed image, and wherein the final transformed image is generated based on the first transformed image by entering the first transformed image as input to a second energy transformation model trained to output the final transformed image at a third energy level, the second energy level being different than the third energy level.

### Claim 7 (depends on 1)

The method of claim 1, wherein the contrast phase is a first contrast phase and wherein identifying the contrast phase of the image comprises identifying the first contrast phase and a second contrast phase of the image and a ratio of the first contrast phase relative to the second contrast phase.

### Claim 8 (depends on 7)

The method of claim 7, wherein the energy transformation model is a first energy transformation model and the transformed image is a first transformed image, and further comprising entering the image as input to a second energy transformation model trained to output a second transformed image at the second energy level, the second energy transformation model selected from among the plurality of energy transformation models based on the second contrast phase.

### Claim 9 (depends on 8)

The method of claim 8, further comprising blending the first transformed image and the second transformed image to generate the final transformed image.

### Claim 10 (depends on 9)

The method of claim 9, wherein the blending comprises weighting the first transformed image and the second transformed image based on the ratio of the first contrast phase relative to the second contrast phase.

### Claim 11

A system, comprising:
one or more processors; and
memory storing instructions executable by the one or more processors to:
obtain an image at a first energy level, the image reconstructed from projection data acquired at a single peak energy level;
identify a contrast phase of the image with a contrast phase classifier model;
enter the image as input into an energy transformation model trained to output a transformed image at a second energy level, different than the first energy level, the energy transformation model selected from among a plurality of energy transformation models based on the contrast phase; and
display a final transformed image and/or save the final transformed image in memory, wherein the final transformed image is the transformed image or is generated based on the transformed image.

### Claim 12 (depends on 11)

The system of claim 11, wherein the contrast phase comprises one or more of no contrast, a venous phase, a portal phase, an arterial phase, and a delayed phase.

### Claim 13 (depends on 11)

The system of claim 11, wherein the first energy level is greater than the second energy level.

### Claim 14 (depends on 11)

The system of claim 11, wherein training of the contrast phase classifier model comprises:
obtaining a plurality of training triads, each training triad including a set of 3 projection images at a respective contrast phase of a plurality of contrast phases;
entering a selected training triad from the plurality of training triads as input to the contrast phase classifier model;
receiving, from the contrast phase classifier model, one or more predicted contrast phases included in the selected training triad;
comparing the one or more predicted contrast phases to one or more ground truth contrast phases indicated via annotations of the selected training triad; and
adjusting model parameters of the contrast phase classifier model based on the comparison.

### Claim 15 (depends on 11)

The system of claim 11, wherein training of the energy transformation model comprises:
entering a first image of a training image pair to the energy transformation model, the first image at the first energy level;
receiving a first transformed training image output from the energy transformation model;
determining a loss function based on the first transformed training image and a second image of the training image pair, the second image at the second energy level; and
updating the energy transformation model based on the loss function, wherein the first image and the second image are monochromatic images generated from dual-energy projection data.

### Claim 16 (depends on 15)

The system of claim 15, wherein training of the energy transformation model further comprises calculating a second loss function based on the first image of the training image pair and an inverse transformed image, the inverse transformed image generated from an inverse transformation model based on the first transformed training image, and updating the energy transformation model based on the second loss function.

### Claim 17

A method, comprising:
obtaining an image of a subject at a first energy level, the image reconstructed from projection data acquired with a single-energy computed tomography (CT) imaging system;
identifying a first contrast phase and a second contrast phase in the image with a contrast phase classifier model;
selecting a first energy transformation model for the first contrast phase and a second energy transformation model for the second contrast phase;
entering the image as input to the first energy transformation model and the second energy transformation model, each of the first energy transformation model and the second energy transformation model trained to output a respective transformed image at a second energy level based on the image at the first energy level;
blending each respective transformed image to form a final transformed image at the second energy level; and
displaying the final transformed image on a display device and/or saving the final transformed image in memory.

### Claim 18 (depends on 17)

The method of claim 17, wherein the first energy transformation model outputs a first transformed image at the second energy level and the second energy transformation model outputs a second transformed image at the second energy level, wherein the contrast phase classifier model outputs a ratio of the first contrast phase relative to the second contrast phase, and wherein the blending comprises weighting the first transformed image and the second transformed image based on the ratio.

### Claim 19 (depends on 17)

The method of claim 17, wherein the final transformed image is a first final transformed image, and further comprising:
selecting a third energy transformation model for the first contrast phase and a fourth energy transformation model for the second contrast phase; and
entering the first final transformed image at the second energy level as input to the third energy transformation model and the fourth energy transformation model, each of the third energy transformation model and the fourth energy transformation model trained to output a respective further transformed image at a third energy level based on the first final transformed image at the second energy level; and
blending each respective further transformed image to form a second final transformed image at the third energy level.

### Claim 20 (depends on 19)

The method of claim 19, wherein the third energy level is different than both of the first energy level and the second energy level and the third energy transformation model outputs a third transformed image at the third energy level and the fourth energy transformation model outputs a fourth transformed image at the third energy level, wherein the contrast phase classifier model outputs a ratio of the first contrast phase relative to the second contrast phase, and wherein the blending comprises weighting the third transformed image and the fourth transformed image based on the ratio.