SYSTEM AND METHOD FOR RADIATION DOSE REPORTING

• US 20120106817A1
• Filed: 04/29/2011
• Published: 05/03/2012
• Est. Priority Date: 04/30/2010
• Status: Active Grant

• Current Assignee: Trustees Of Columbia University In The City Of New York (Columbia University), Cornell University
• Original Assignee: Cornell University
• Inventors: Shih, George, Kenney, Devin, Zabih, Ramin, Nickoloff, Edward L., Lu, Zheng Feng
• Granted Patent: US 9,129,044 B2
• Time in Patent Office: Days
• US Class Current: 382/131
• CPC Class Codes: A61B 6/032 Transmission computed tomography [CT]
• CPC Class Codes: A61B 6/542 involving control of exposure
• CPC Class Codes: A61B 6/563 involving image data transmission via a network
• CPC Class Codes: A61B 6/583 using calibration phantoms
• CPC Class Codes: G16H 15/00 ICT specially adapted for medical reports, e.g. generation or transmission thereof
• CPC Class Codes: G16H 30/20 for handling medical images, e.g. DICOM, HL7 or PACS
• CPC Class Codes: G16H 30/40 for processing medical images, e.g. editing
• CPC Class Codes: G16H 50/70 for mining of medical data, e.g. analysing previous cases of other patients

Abstract

Systems and method can be employed to automatically extract radiation dose information from medical images, particularly a plurality of heterogeneous CT images including those from legacy CT scanners. A report including the extracted radiation dose information can be generated, and alerts can be sent to reduce the possibility of overexposures.

Claims

1. A method comprising:

automatically extracting radiation dose information from medical images; and

generating a report including the extracted radiation dose information.

2. The method of claim 1, wherein the medical images comprise one of computed tomography (CT) or positron emission tomography-computed tomography (PET-CT) images.

3. The method of claim 1, wherein said automatically extracting dose information comprises performing an image segmentation on the medical images.

4. The method of claim 3, wherein said performing an image segmentation comprises performing a connected component analysis.

5. The method of claim 4, wherein said connected component analysis is performed using DCMTK.

6. The method of claim 3, further comprising an optical character recognition (OCR) process to convert the segmented images from binary data into textual data.

7. The method of claim 1, further comprising correcting a patient size.

8. The method of claim 7, wherein said correcting comprises obtaining a relationship between patent size and weight.

9. The method of claim 8, wherein said correcting further comprises calculating an equivalent cylindrical phantom diameter.

10. The method of claim 9, wherein said calculating comprises calculating the equivalent cylindrical phantom diameter using:

phantom diameter=square root(AP dimension*LAT dimension)*C,

wherein C is the correction factor that takes into consideration of the density difference in soft tissue and in acrylic PMMA phantom material, AP dimension is a patient'"'"'s anteriorposterior dimension, and LAT dimension is the patient'"'"'s lateral dimension.

11. The method of claim 10, further comprising generating a correction factor as a function of patient weight for each CT scanner.

12. The method of claim 7, further comprising determining a body portion of the patient that is scanned, wherein said correcting a patient size comprises correcting the patient size using a formula specific to the body portion.

13. The method of claim 1, wherein said extracted radiation dose information comprises an effective dose.

14. The method of claim 1, further comprising storing the dose information in a database.

15. The method of claim 1, further comprising storing the dose information in DICOM metadata of a medical image.

16. The method of claim 1, wherein said automatically extracting dose information comprises extracting dose information from medical images obtained from a plurality of heterogeneous CT scanners.

17. The method of claim 16, wherein at least some of the medical images obtained from some of the plurality of heterogeneous CT scanners are not in DICOM format.

18. The method of claim 1, further comprising comparing the extracted radiation dose information with a predetermined threshold.

19. The method of claim 18, further comprising providing an alert if a radiation dose from the extracted radiation dose information is higher than a predetermined threshold.

20. The method of claim 1, further comprising displaying the report through a web interface.

21. The method of claim 1, wherein said generating a report comprises generating at least one of an effective dose, an accumulative dose, or an average dose for a patient.

22. The method of claim 21, further comprising providing an alert if a new CT study is ordered and if an accumulative dose exceeds a predetermined threshold.

23. The method of claim 1, wherein said generating a report comprises generating a summary of a healthcare provider'"'"'s history of ordering radiation-based studies.

24. The method of claim 1, further comprising sending the report through one of a short message, an email, a website, or a voice message.

25. A system comprising:

a computer configured to automatically extract dose information from a medical image and to generate a dose information report.

26. The system of claim 25, further comprising a plurality of heterogeneous scanners, wherein at least some of the scanners are configured to output image data not in DICOM format.

27. The system of claim 26, wherein the medical image comprises one of computed tomography (CT) or positron emission tomography-computed tomography (PET-CT) images.

28. The system of claim 26, further comprising a communication device configured to transmit the dose information report to a user.

29. The system of claim 26, further comprising at least one of a picture archiving and communication system (PACS) or a radiology information system (RIS).

30. A non-transitory computer readable medium containing instructions therein, wherein the instructions comprise:

automatically extracting dose information from a medical image; and

generating a dose information report.

31. The non-transitory computer readable medium of claim 30, wherein the medical images comprise one of computed tomography (CT) or positron emission tomography-computed tomography (PET-CT) images.

32. The non-transitory computer readable medium of claim 30, wherein said automatically extracting dose information comprises performing an image segmentation on the medical images.

33. The non-transitory computer readable medium of claim 32, wherein said performing an image segmentation comprises performing a connected component analysis.

34. The non-transitory computer readable medium of claim 33, wherein said connected component analysis is performed using DCMTK.

35. The non-transitory computer readable medium of claim 32, wherein the instructions further comprise converting the segmented images from binary data into textual using optical character recognition (OCR).

36. The non-transitory computer readable medium of claim 30, wherein the instructions further comprise correcting a patient size.

37. The non-transitory computer readable medium of claim 36, wherein said correcting comprises obtaining a relationship between patent sizes and weights.

38. The non-transitory computer readable medium of claim 37, wherein said correcting further comprises calculating an equivalent cylindrical phantom diameter.

39. The non-transitory computer readable medium of claim 38, wherein said calculating comprises calculating the equivalent cylindrical phantom diameter using:

phantom diameter=square root(AP dimension*LAT dimension)*C,

wherein C is the correction factor that takes into consideration of the density difference in soft tissue and in acrylic PMMA phantom material, AP dimension is a patient'"'"'s anterior posterior dimension, and LAT dimension is the patient'"'"'s lateral dimension.

40. The non-transitory computer readable medium of claim 39, wherein the instructions further comprise generating a correction factor as a function of patient weight for a CT scanner.

41. The non-transitory computer readable medium of claim 30, wherein the instructions further comprise storing the dose information in a database.

42. The non-transitory computer readable medium of claim 30, wherein the instructions further comprise storing the dose information in DICOM metadata of a medical image.

43. The non-transitory computer readable medium of claim 30, wherein said automatically extracting dose information comprises extracting dose information from a plurality of heterogeneous CT scanners.

44. The non-transitory computer readable medium of claim 30, wherein at least some of the dose information extracted from at least some of the plurality of heterogeneous CT scanners are not in DICOM format.

45. The non-transitory computer readable medium of claim 30, wherein the instructions further comprise comparing the extracted radiation dose information with a predetermined threshold.

46. The non-transitory computer readable medium of claim 45, wherein the instructions further comprise providing an alert if a radiation dose from the extracted radiation dose information is higher than a predetermined threshold.

47. The non-transitory computer readable medium of claim 30, wherein the instructions further comprise displaying the dose information report through a web interface.

48. The non-transitory computer readable medium of claim 30, wherein said generating a report comprises generating an accumulative or an average radiation dose information for a patient.

49. The non-transitory computer readable medium of claim 30, wherein the instructions further comprise providing an alert if a new CT study is ordered and if an accumulative dose exceeds a predetermined threshold.

50. The non-transitory computer readable medium of claim 30, wherein said generating a report comprises generating a summary of a healthcare provider'"'"'s history of ordering radiation-based studies.

51. The non-transitory computer readable medium of claim 30, wherein the instructions further comprise sending the report through one of a short message, an email, a website, or a voice message.