Method of determining contrast phase of a computerized tomography image

1. A computer-implemented method for classifying and presenting a contrast phase (CP) of a contrast enhanced computerized tomography (CECT) scan comprising:

training an artificial intelligence (AI) algorithm utilizing a set of CPs labeled CECT data to associate a set of characteristics of the data with a probability associated with the CP;

receiving a new set of unlabeled CECT data;

applying the AI algorithm to the new unlabeled CECT data to associate a first probability of a first CP and a second probability of a second CP; and

providing a graphical representation including the first probability of the first CP and the second probability of the second CP.

2. The computer-implemented method according to claim 1 , wherein the CP is selected from the group consisting of pre-contrast, early arterial, arterial, portal-venous, nephrogenic, and late.

3. The computer-implemented method according to claim 1 , wherein the graphical representation is in a form of a polygon.

4. The computer-implemented method according to claim 3 , wherein a number of sides of the polygon corresponds to a number of the CPs, and each vertex of the polygon corresponds to a different one of the CPs.

5. The computer-implemented method according to claim 4 , wherein locations of the vertices of the polygon correspond to 100% probabilities for the respective CP.

6. The computer-implemented method according to claim 4 , wherein the graphical representation includes at least one marker located on an edge of the polygon or in an interior of the polygon, wherein distances from the marker to the respective vertices correspond to probabilities that the CP of the new unlabeled CECT data corresponds to the CP associated with the respective vertices.

7. The computer-implemented method according to claim 1 , further comprising assigning an AI model to process the new unlabeled CECT data based on the first probability of the first contrast phase.

8. The computer-implemented method according to claim 1 , further comprising:

determining that the first probability exceeds a threshold probability;

assigning an AI model that is associated with the first contrast phase; and

processing the new unlabeled CECT data with the AI model to determine at least one anomaly.

9. A computer system comprising:

one or more computer readable storage media with program instructions collectively stored on the one or more computer readable storage media; and

one or more processors configured to execute the program instructions to perform a method for generating a training model for object detection, the method comprising:

training an artificial intelligence (AI) algorithm utilizing a set of CPs labeled CECT data to associate a set of characteristics of the data with a probability associated with the CP;

receiving a new set of unlabeled CECT data;

applying the AI algorithm to the new unlabeled CECT data to associate a first probability of a first CP and a second probability of a second CP; and

providing a graphical representation including the first probability of the first CP and the second probability of the second CP.

10. The computer system according to claim 9 , wherein the graphical representation is in a form of a polygon.

11. The computer system according to claim 10 , wherein a number of sides of the polygon correspond to a number of the CPs, and each vertex of the polygon corresponds to a different one of the CPs.

12. The computer system according to claim 11 , wherein locations of the vertices of the polygon corresponds to 100% probabilities for the respective CP.

13. The computer system according to claim 11 , wherein the graphical representation includes at least one marker located on an edge of the polygon or in an interior of the polygon, wherein distances from the marker to the respective vertices correspond to probabilities that the CP of the new unlabeled CECT data corresponds to the CP associated with the respective vertices.

14. The computer system according to claim 9 , assigning an AI model to process the new unlabeled CECT data based on the first probability of the first contrast phase.

15. The computer system according to claim 9 , further comprising:

determining that the first probability exceeds a threshold probability;

assigning an AI model that is associated with the first contrast phase; and

processing the new unlabeled CECT data with the AI model to determine at least one anomaly.

16. A computer program product for context aware anomaly detection, the computer program product comprising:

one or more computer readable storage media, and program instructions collectively stored on the one or more computer readable storage media, the program instructions comprising:

program instructions to train an artificial intelligence (AI) algorithm utilizing a set of CPs labeled CECT data to associate a set of characteristics of the data with a probability associated with the CP;

program instructions to receive a new set of unlabeled CECT data;

program instruction to apply the AI algorithm to the new unlabeled CECT data to associate a first probability of a first CP and a second probability of a second CP; and

program instructions to provide a graphical representation including the first probability of the first CP and the second probability of the second CP.

17. The computer program product according to claim 16 , wherein the graphical representation is in a form of a polygon.

18. The computer program product according to claim 17 , wherein a number of sides of the polygon corresponds to a number of the CPs, and each vertex of the polygon corresponds to a different one of the CPs.

19. The computer program product according to claim 18 , wherein locations of the vertices of the polygon correspond to 100% probabilities for the respective CP.

20. The computer program product according to claim 18 , wherein the graphical representation includes at least one marker located on an edge of the polygon or in an interior of the polygon, wherein distances from the marker to the respective vertices correspond to probabilities that the CP of the new unlabeled CECT data corresponds to the CP associated with the respective vertices.