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 method for CAD analysis of a medical image of a patient, comprising:
performing a first CAD abnormality detection algorithm on the medical image, said first CAD abnormality detection algorithm not requiring the presence of contrast agent in the patient;
automatically determining, based only on the contents of the medical image, whether the patient was administered a contrast agent; and
if it is determined that the patient was administered a contrast agent, performing a second CAD abnormality detection algorithm on the medical image, said second CAD abnormality detection algorithm requiring the presence of the contrast agent.
2. The method of claim 1 further comprising the steps of:
if it is determined that the patient was not administered a contrast agent, informing the reviewing clinician that results corresponding to only said first CAD abnormality detection algorithm are available for review; and
if it is determined that the patient was administered a contrast agent, informing the reviewing clinician that results corresponding to both said first and said second CAD abnormality detection algorithms are available for review.
3. The method of claim 1 , wherein said medical image is a three-dimensional lung volume, said first CAD abnormality detection algorithm is a lung nodule detection algorithm, and said second CAD abnormality detection algorithm is a pulmonary embolism detection algorithm.
4. The method of claim 1 wherein the step of automatically determining comprises the steps of measuring gray scale values of image pixels in a blood-containing area of the medical image and comparing said values with gray scale values of image pixels in a water containing area of the medical image.
5. The method of claim 4 wherein the step of automatically determining further comprises the step of detecting a blood-containing area of the medical image.
6. The method of claim 5 wherein the step of automatically determining further comprises the step of detecting a water containing area of the medical image.
7. The method of claim 5 , wherein said medical image is a three-dimensional lung volume, said first CAD abnormality detection algorithm is a lung nodule detection algorithm, and said second CAD abnormality detection algorithm is a pulmonary embolism detection algorithm.
8. The method of claim 1 wherein the step of automatically determining comprises the steps of counting the number of image pixels in the medical image having a gray scale value in excess of a first predetermined threshold and comparing said count with a second predetermined threshold.
9. The method of claim 8 , wherein said medical image is a three-dimensional lung volume, said first CAD abnormality detection algorithm is a lung nodule detection algorithm, and said second CAD abnormality detection algorithm is a pulmonary embolism detection algorithm.
10. The method of claim 8 wherein the gray scale values are expressed in Hounsfield units.
11. The method of claim 8 wherein the first predetermined threshold is 100 Hounsfield units.
12. The method of claim 8 wherein the second predetermined threshold is 15% of the total number of image pixels in the medical image.
13. A method for CAD analysis of a medical image of a patient comprising:
counting the number of pixels in the medical image having a gray scale value in excess of a first predetermined threshold;
comparing said count with a second predetermined threshold;
if said count does not exceed said second threshold, performing a first CAD abnormality detection algorithm on the medical image, said first CAD abnormality detection algorithm not requiring the presence of contrast agent in the patient; and
if said count exceeds said second threshold performing on the medical image both the first CAD abnormality detection algorithm and a second CAD abnormality detection algorithm, said second CAD abnormality detection algorithm requiring the presence of contrast agent in the patient.
14. The method of claim 13 further comprising the step of informing a reviewing clinician whether the first CAD detection algorithm or the first and second CAD detection algorithms were performed.
15. The method of claim 13 , wherein said medical image is a three-dimensional lung volume, said first CAD abnormality detection algorithm is a lung nodule detection algorithm, and said second CAD abnormality detection algorithm is a pulmonary embolism detection algorithm.
16. The method of claim 13 wherein the gray scale values are expressed in Hounsfield units.
17. The method of claim 13 wherein the first predetermined threshold is 100 Hounsfield units.
18. The method of claim 13 wherein the second predetermined threshold is 15% of the total number of image pixels in the medical image.