Back to results
US 2026/0301131 A1Published application
Generation Of Artificial Contrast-Enhanced Radiological Images
AssigneeBayer Aktiengesellschaft
InventorsMatthias LENGA, Ivo Matteo BALTRUSCHAT, Parvaneh JANBAKHSHI, Felix Karl KREIS
Life of this patent
Estimating the term…
Abstract
The present invention relates to the technical field of generating artificial contrast-enhanced radiological images.
Claims21
A computer-implemented method comprising the steps of:
- providing a first representation (R1, R1I, R1F), where the first representation (R1, R1I, R1F) represents an examination region of an examination object without contrast agent or after administration of a first amount of a contrast agent,
- providing a second representation (R2, R2I, R2F), where the second representation (R2, R2I, R2F) represents the examination region of the examination object after administration of a second amount of the contrast agent, the second amount being larger than the first amount,
- feeding the first representation (R1, R1I, R1F) and the second representation (R2, R2I, R2F) to a first model (M1), where the first model (M1) is configured to generate, based on the first representation (R1, R1I, R1F) and the second representation (R2, R2I, R2F), a third representation (R3, R3I, R3F), where the third representation (R3, R3I, R3F) represents the examination region of the examination object after administration of a third amount of the contrast agent, the third amount being different from the first amount and the second amount,
- feeding the third representation (R3, R3I, R3F) to a second model (M2),
- where the second model (M2) has been trained in a training process based on training data (TD),
- where the training data (TD) for each reference object comprises a multiplicity of reference objects:
- (i) a reference representation (RR3) generated by the first model that represents a reference region of the reference object after administration of a reference amount of the contrast agent, and
- (ii) a measured reference representation (RR3M) of the reference region of the reference object after administration of the reference amount of the contrast agent,
- where the training process for each reference object comprises the steps of:
- feeding the reference representation generated by the first model (M1) to the second model (M2),
- receiving a corrected reference representation (RR3C) from the second model (M2),
- reducing the differences between the corrected reference representation (RR3C) and the measured reference representation (RR3M) by modifying model parameters,
- receiving a corrected third representation (R3C) of the examination region of the examination object from the second model (M2),
- outputting and/or storing the corrected third representation (R3C) and/or transmitting the corrected third representation (R3C) to a separate computer system.
11 more elements
A computer system (1) comprising
- a receiving unit (11),
- a control and calculation unit (12) and
- an output unit (13),
- wherein the control and calculation unit (12) is configured
- to generate a first representation (R1, R1I, R1F) or cause the receiving unit (11) to receive the first representation (R1, R1I, R1F), where the first representation (R1, R1I, R1F) represents an examination region of an examination object without contrast agent or after administration of a first amount of a contrast agent,
- to generate a second representation (R2, R2I, R2F) or to cause the receiving unit (11) to receive the second representation (R2, R2I, R2F), where the second representation (R2, R2I, R2F) represents the examination region of the examination object after administration of a second amount of the contrast agent, the second amount being larger than the first amount,
- to feed the first representation (R1, R1I, R1F) and the second representation (R2, R2I, R2F) to a first model (M1), where the first model (M1) is configured to generate, based on the first representation (R1, R1I, R1F) and the second representation (R2, R2I, R2F), a third representation (R3, R3I, R3F), where the third representation (R3, R3I, R3F) represents the examination region of the examination object after administration of a third amount of the contrast agent, the third amount being different from the first amount and the second amount,
- to feed the third representation (R3, R3I, R3F) to a second model (M2),
- where the second model (M2) has been trained in a training process based on training data (TD),
- where the training data (TD) for each reference object comprises a multiplicity of reference objects:
- (i) a reference representation (RR3) generated by the first model (M1) that represents a reference region of the reference object after administration of a reference amount of the contrast agent, and
- (ii) a measured reference representation (RR3M) of the reference region of the reference object after administration of the reference amount of the contrast agent,
- where the training process for each reference object comprises the steps of:
- feeding the reference representation (RR3) generated by the first model (M1) to the second model (M2),
- receiving a corrected reference representation (RR3C) from the second model (M2),
- reducing the differences between the corrected reference representation (RR3C) and the measured reference representation (RR3M) by modifying model parameters (MP),
- to receive a corrected third representation (R3c) of the examination region of the examination object from the second model (M2),
- to cause the output unit (13) to output the corrected third representation (R3c), store it and/or transmit it to a separate computer system.
15 more elements
A computer program product comprising a data carrier on which is stored a computer program (40) that can be loaded into a working memory (22) of a computer system (1), where it causes the computer system (1) to execute the following steps:
- providing a first representation (R1, R1I, R1F), where the first representation (R1, R1I, R1F) represents an examination region of an examination object without contrast agent or after administration of a first amount of a contrast agent,
- providing a second representation (R2, R2I, R2F), where the second representation (R2, R2I, R2F) represents the examination region of the examination object after administration of a second amount of the contrast agent, the second amount being larger than the first amount,
- feeding the first representation (R1, R1I, R1F) and the second representation (R2, R2I, R2F) to a first model (M1), where the first model (M1) is configured to generate, based on the first representation (R1, R1I, R1F) and the second representation (R2, R2I, R2F), a third representation (R3, R3I, R3F), where the third representation (R3, R3I, R3F) represents the examination region of the examination object after administration of a third amount of the contrast agent, the third amount being different from the first amount and the second amount,
- feeding the third representation (R3, R3I, R3F) to a second model (M2),
- where the second model (M2) has been trained in a training process based on training data (TD),
- where the training data (TD) for each reference object comprises a multiplicity of reference objects:
- (i) a reference representation (RR3) generated by the first model that represents a reference region of the reference object after administration of a reference amount of the contrast agent, and
- (ii) a measured reference representation (RR3M) of the reference region of the reference object after administration of the reference amount of the contrast agent,
- where the training process for each reference object comprises the steps of:
- feeding the reference representation (RR3) generated by the first model (M1) to the second model (M2),
- receiving a corrected reference representation (RR3C) from the second model (M2),
- reducing the differences between the corrected reference representation (RR3C) and the measured reference representation (RR3M) by modifying model parameters (MP),
- receiving a corrected third representation (R3C) of the examination region of the examination object from the second model (M2),
- outputting and/or storing the corrected third representation (R3C) and/or transmitting the corrected third representation (R3C) to a separate computer system.
11 more elements
The use of a contrast agent in a radiological examination method comprising the steps of:
- providing a first representation (R1, R1I, R1F), where the first representation (R1, R1I, R1F) represents an examination region of an examination object without the contrast agent or after administration of a first amount of the contrast agent,
- providing a second representation (R2, R2I, R2F), where the second representation (R2, R2I, R2F) represents the examination region of the examination object after administration of a second amount of the contrast agent, the second amount being larger than the first amount,
- feeding the first representation (R1, R1I, R1F) and the second representation (R2, R2I, R2F) to a first model (M1), where the first model (M1) is configured to generate, based on the first representation (R1, R1I, R1F) and the second representation (R2, R2I, R2F), a third representation (R3, R3I, R3F), where the third representation (R3, R3I, R3F) represents the examination region of the examination object after administration of a third amount of the contrast agent, the third amount being different from the first amount and the second amount,
- feeding the third representation (R3, R3I, R3F) to a second model (M2),
- where the second model (M2) has been trained in a training process based on training data (TD),
- where the training data (TD) for each reference object comprises a multiplicity of reference objects:
- (i) a reference representation (RR3) generated by the first model that represents a reference region of the reference object after administration of a reference amount of the contrast agent, and
- (ii) a measured reference representation (RR3M) of the reference region of the reference object after administration of the reference amount of the contrast agent,
- where the training process for each reference object comprises the steps of:
- feeding the reference representation (RR3) generated by the first model (M1) to the second model (M2),
- receiving a corrected reference representation (RR3C) from the second model (M2),
- reducing the differences between the corrected reference representation (RR3C) and the measured reference representation (RR3M) by modifying model parameters (MP),
- receiving a corrected third representation (R3C) of the examination region of the examination object from the second model (M2),
- outputting and/or storing the corrected third representation (R3C) and/or transmitting the corrected third representation (R3C) to a separate computer system.
11 more elements
A contrast agent for use in a radiological examination method comprising the steps of:
- providing a first representation (R1, R1I, R1F), where the first representation (R1, R1I, RIF) represents an examination region of an examination object without the contrast agent or after administration of a first amount of the contrast agent,
- providing a second representation (R2, R2I, R2F), where the second representation (R2, R2I, R2F) represents the examination region of the examination object after administration of a second amount of the contrast agent, the second amount being larger than the first amount,
- feeding the first representation (R1, R1I, R1F) and the second representation (R2, R2I, R2F) to a first model (M1), where the first model (M1) is configured to generate, based on the first representation (R1, R1I, R1F) and the second representation (R2, R2I, R2F), a third representation (R3, R3I, R3F), where the third representation (R3, R3I, R3F) represents the examination region of the examination object after administration of a third amount of the contrast agent, the third amount being different from the first amount and the second amount,
- feeding the third representation (R3, R3I, R3F) to a second model (M2),
- where the second model (M2) has been trained in a training process based on training data (TD),
- where the training data (TD) for each reference object comprises a multiplicity of reference objects:
- (i) a reference representation (RR3) generated by the first model that represents a reference region of the reference object after administration of a reference amount of the contrast agent, and
- (ii) a measured reference representation (RR3M) of the reference region of the reference object after administration of the reference amount of the contrast agent,
- where the training process for each reference object comprises the steps of:
- feeding the reference representation (RR3) generated by the first model (M1) to the second model (M2),
- receiving a corrected reference representation (RR3C) from the second model (M2),
- reducing the differences between the corrected reference representation (RR3C) and the measured reference representation (RR3M) by modifying model parameters (MP),
- receiving a corrected third representation (R3C) of the examination region of the examination object from the second model (M2),
- outputting and/or storing the corrected third representation (R3C) and/or transmitting the corrected third representation (R3C) to a separate computer system.
11 more elements
Dependencies are inferred from the claim text.