Automatically detecting the presence of contrast agent in medical image
View Patent ↗A CAD system pre-analyzes a medical image to automatically determine whether contrast agent was introduced into the patient before forming that image. In one embodiment, contrast agent detection is performed by comparing the voxel values in known blood-containing areas to voxel values of known water-containing areas, and if there is a substantial difference above a preferred threshold, then it is determined that this patient was indeed injected with the contrast agent. Upon finding that the patient was indeed injected with contrast agent, the CAD algorithm then automatically performs both a detection algorithm that uses the contrast agent and one that does not and notifies the clinician that both sets of results are available to look at. However, if it is determined that the patient was, not injected with contrast agent, the CAD algorithm does not perform the algorithm that uses the contrast agent does not give the user the option to view any results from such algorithm. The invention may be practiced with a variety of imaging technologies some of which may not require an explicit comparison of the voxel values from the blood-containing and water-containing areas.
1. A computer program product, stored on a computer-readable medium, for CAD analysis of a medical image of a patient, said computer program product comprising instructions for:
obtaining the medical image of the patient comprising pixels;
calculating a total number of pixels in the medical image;
calculating a number of pixels having a gray scale value in excess of a first predetermined threshold;
performing a first CAD abnormality detection algorithm on the medical image, the first CAD abnormality detection algorithm not requiring administration of a contrast agent to the patient; and
if the number of pixels exceeds a second predetermined threshold, automatically performing a second CAD abnormality detection algorithm on the medical image and indicating that both the first CAD abnormality detection algorithm and the second CAD abnormality detection algorithm were performed, the second CAD abnormality detection algorithm requiring administration of a contrast agent to the patient.
2. The computer program product of claim 1 , wherein the medical image is a three-dimensional lung volume, the first CAD abnormality detection algorithm is a lung nodule detection algorithm, and the second CAD abnormality detection algorithm is a pulmonary embolism detection algorithm.
3. The computer program product of claim 1 , wherein the first predetermined threshold is 100 Hounsfield units.
4. The computer program product of claim 1 , wherein the second predetermined threshold is 15% of the pixels in the medical image.
5. A computer program product, stored on a computer-readable medium, for performing CAD analysis of a medical image of a patient, the computer program product comprising instructions operable to cause a programmable processor to:
obtain the medical image of the patient;
execute a first CAD abnormality detection algorithm on the medical image, the first CAD abnormality detection algorithm does not require administering a contrast agent to the patient;
automatically determine, based on image pixels in the medical image, whether the patient was administered a contrast agent by detecting a blood-containing area of the medical image and evaluating gray scale values of the image pixels in the blood-containing area of the medical image; and
perform a second CAD abnormality detection algorithm on the medical image and indicate that both the first CAD abnormality detection algorithm and the second CAD abnormality detection algorithm were performed only if the patient was administered a contrast agent, the second CAD abnormality detection algorithm requires administering the contrast agent to the patient.
6. The computer program product of claim 5 wherein the medical image is a three-dimensional lung volume, the first CAD abnormality detection algorithm is a lung nodule detection algorithm, and the second CAD abnormality detection algorithm is a pulmonary embolism detection algorithm.
7. The computer program product of claim 5 , wherein the evaluating gray scale values of the image pixels in the blood-containing area comprises comparing gray scale values of image pixels in a water containing area of the medical image to gray scale values of other image pixels in the medical image.
8. The computer program product of claim 5 wherein the instructions operable to cause a programmable processor to automatically determine include instructions operable to detect a water containing area of the medical image.
9. The computer program product of claim 5 wherein the automatically determining includes counting the image pixels in the medical image having a gray scale value in excess of a first predetermined threshold and to compare the count with a second predetermined threshold.
10. The computer program product of claim 9 , wherein the gray scale values are expressed in Hounsfield units.
11. The computer program product of claim 9 , wherein the first predetermined threshold is 100 Hounsfield units.
12. The computer program product of claim 9 , wherein the second predetermined threshold is 15% of the image pixels in the medical image.
13. A system for facilitating review of a medical image of a patient by a reviewing clinician, comprising:
a processing device configured to:
(i) obtain the medical image of the patient comprising image pixels;
(ii) execute a first CAD abnormality detection algorithm on the medical image to generate a first CAD result set, the first CAD abnormality detection algorithm not requiring administration of a contrast agent in the patient,
(iii) automatically determine, based on the contents of the medical image, whether the patient was administered a contrast agent by detecting a blood-containing area of the medical image and evaluating gray scale values of image pixels in the blood-containing area of the medical image, and
(iv) perform a second CAD abnormality detection algorithm on the medical image to generate a second CAD result set only if it is determined that the patient was administered the contrast agent, the second CAD abnormality detection algorithm requires administering the contrast agent to the patient; and
a display device operably coupled to the processing device for displaying the results of the first detection algorithm to the reviewing clinician, and said display device further displaying the results of the second detection algorithm and an indication that both the first CAD abnormality detection algorithm and the second CAD abnormality algorithm were performed only if it is determined that the patient was administered the contrast agent.
14. The system of claim 13 , wherein said evaluating gray scale values of image pixels in the blood-containing area comprises comparing said values with gray scale values of image pixels in a water containing area of the medical image.
15. The system of claim 13 wherein the processing device is configured to detect a water containing area of the medical image.
16. The system of claim 13 wherein said medical image is a three-dimensional lung volume, the first CAD abnormality detection algorithm is a lung nodule detection algorithm, and the second CAD abnormality detection algorithm is a pulmonary embolism detection algorithm.
17. The system of claim 13 wherein gray scale values are evaluated by counting the image pixels in the medical image having a gray scale value in excess of a first predetermined threshold and comparing the count with a second predetermined threshold.
18. The system of claim 17 wherein the gray scale values are expressed in Hounsfield units.
19. The system of claim 17 wherein the first predetermined threshold is 100 Hounsfield units.
20. The system of claim 17 wherein the second predetermined threshold is 15% of the image pixels in the medical image.