Back to results
US 12,670,592 B2Granted
Method for training a predictive model, receiving a training data set for multiple reference tomograms, and providing a prediction model
AssigneeBayer Aktiengesellschaft
InventorMatthias Lenga
Life of this patent
Estimating the term…
Abstract
The present invention relates to the technical field of producing artificial contrast-enhanced radiological images by way of machine learning methods.
Claims18
A method for training a prediction model, comprising:
- receiving a training data set, wherein the training data set comprises a plurality of reference tomograms for each reference object of a multiplicity of reference objects,
- wherein the reference tomograms represent a field of view of the reference object after the administration of a contrast agent,
- wherein the reference tomograms comprise at least two tomograms for each reference object:
- a first reference tomogram and a second reference tomogram,
- wherein the first reference tomogram represents a first layer within the field of view,
- wherein the second reference tomogram represents a second layer within the field of view,
- wherein the second reference tomogram has been generated after the first reference tomogram;
- and
- training the prediction model, wherein the first and the second reference tomogram are fed to the prediction model during training, wherein the prediction model is trained to transfer contrast enhancement from the first reference tomogram to the second reference tomogram and to generate an artificial tomogram which represents the second layer.
6 more elements
A method for generating an artificial, contrast-enhanced tomogram, comprising:
- receiving a first tomogram, wherein the first tomogram represents a first layer within a field of view of an examination object after the administration of a contrast agent;
- receiving a second tomogram, wherein the second tomogram represents a second layer within the field of view of the examination object after the administration of the contrast agent, wherein the second tomogram has been generated after the first tomogram;
- providing a prediction model, wherein the prediction model has been trained on the basis of a training data set to transfer contrast information from at least one tomogram to another tomogram and to generate an artificial tomogram in the process;
- feeding the first and second tomogram to the prediction model;
- receiving an artificial tomogram from the prediction model, wherein the artificial tomogram represents the second layer in the field of view, wherein contrast information from the first tomogram has been transferred in the artificial tomogram;
- and
- outputting the artificial tomogram.
4 more elements
A computer system comprising:
- a receiving unit,
- a control and calculation unit, and
- an output unit,
- wherein the control and calculation unit is configured to prompt the receiving unit to receive at least a first and a second tomogram,
- wherein the first tomogram represents a first layer within a field of view of an examination object after the administration of a contrast agent,
- wherein the second tomogram represents a second layer within the field of view of the examination object after the administration of the contrast agent,
- wherein the second tomogram has been generated after the first tomogram,
- wherein the control and calculation unit is configured to feed the first and the second tomogram to a prediction model, wherein the prediction model has been trained on the basis of a training data set to transfer contrast information from at least one tomogram to another tomogram and to generate an artificial tomogram in the process,
- wherein the control and calculation unit is configured to receive an artificial tomogram from the prediction model, wherein the artificial tomogram represents the second layer in the field of view, wherein contrast information from the first tomogram has been transferred in the artificial tomogram, and
- wherein the control and calculation unit is configured to prompt the output unit to output the artificial tomogram.
7 more elements
A non-transitory computer readable storage medium storing instructions that, when executed by one or more processors of a computer system, cause the computer system to:
- receive a first tomogram, wherein the first tomogram represents a first layer within a field of view of an examination object after the administration of a contrast agent,
- receive a second tomogram, wherein the second tomogram represents a second layer within the field of view of the examination object after the administration of the contrast agent, wherein the second tomogram has been generated after the first tomogram,
- feed the first and second tomogram to a prediction model, wherein the prediction model has been trained on the basis of a training data set to transfer contrast information from at least one tomogram to another tomogram and to generate an artificial tomogram in the process,
- receive an artificial tomogram from the prediction model, wherein the artificial tomogram represents the second layer in the field of view, wherein contrast information from the first tomogram has been transferred in the artificial tomogram, and
- output the artificial tomogram.
2 more elements
A method comprising:
- using a contrast agent to predict an artificial contrast-enhanced tomogram, wherein predicting the artificial contrast-enhanced tomogram comprises:
- generating a first tomogram, wherein the first tomogram represents a first layer within a field of view of an examination object after the administration of a contrast agent,
- generating a second tomogram, wherein the second tomogram represents a second layer within the field of view of the examination object after the administration of the contrast agent, wherein the second tomogram is generated after the first tomogram,
- feeding the first and second tomogram to a prediction model, wherein the prediction model has been trained on the basis of a training data set to transfer contrast information from at least one tomogram to another tomogram and to generate an artificial tomogram in the process,
- receiving an artificial tomogram from the prediction model, wherein the artificial tomogram represents the second layer in the field of view, wherein contrast information from the first tomogram has been transferred in the artificial tomogram, and
- outputting the artificial tomogram.
3 more elements
A contrast agent for use in a method for predicting an artificial contrast-enhanced tomogram, wherein the method comprises the following steps:
- generating a first tomogram, wherein the first tomogram represents a first layer within a field of view of an examination object after the administration of a contrast agent,
- generating a second tomogram, wherein the second tomogram represents a second layer within the field of view of the examination object after the administration of the contrast agent, wherein the second tomogram is generated after the first tomogram,
- feeding the first and second tomogram to a prediction model, wherein the prediction model has been trained on the basis of a training data set to transfer contrast information from at least one tomogram to another tomogram and to generate an artificial tomogram in the process,
- receiving an artificial tomogram from the prediction model, wherein the artificial tomogram represents the second layer in the field of view, wherein contrast information from the first tomogram has been transferred in the artificial tomogram, and
- outputting the artificial tomogram.
2 more elements
Dependencies are inferred from the claim text.