Automatic assessment of confidence in imaging data

Patent metadata

Field	Value
Publication number	US-9317911-B2
Application number	US-201013266469-A
Country	US
Kind code	B2
Filing date	Apr 9, 2010
Priority date	May 5, 2009
Publication date	Apr 19, 2016
Grant date	Apr 19, 2016

Abstract

A system and method are provided to automatically assess a confidence in imaging data based on a proposed diagnostic task or treatment decision, by determining one or more imaging quality indicators relating to the imaging data corresponding to a confidence of the proposed diagnostic task or treatment decision, comparing those imaging quality indicators with confidence benchmark values, and determining a confidence value indicative of the confidence in the imaging data for purposes of performing the proposed diagnostic task or making the proposed treatment decision.

First claim

Having thus described the preferred embodiments, the invention is now claimed to be:

1. A system to automatically assess a confidence in an dynamic functional imaging acquisition data based on a proposed diagnostic task or treatment decision, the system comprising a computer readable non-transitory medium configured to receive dynamic functional imaging data, the computer readable non-transitory medium comprising logic to:
determine one or more imaging quality indicators relating to the acquisition of the acquired imaging data based on one or more quantitative imaging quality factors corresponding to a confidence of the proposed diagnostic task or treatment decision, wherein the one or more quantitative imaging quality factors each comprise a quantitative assessment of at least one of the accuracy, location, and timing of the acquisition, and wherein the one or more imaging quality indicators are generated by applying the one or more quantitative imaging quality factors to the acquired imaging data; and
compare the one or more imaging quality indicators to one or more confidence benchmark values associated with the one or more quantitative imaging quality factors and determine a confidence value indicative of the confidence that the acquisition of the imaging data is of sufficient quality for purposes of performing the proposed diagnostic task or making the proposed treatment decision.

2. The system of claim 1 , wherein the logic further generates at least one composite confidence value based on two or more individual confidence values.

3. The system of claim 2 , wherein the logic generates the at least one composite value by a linear combination, a weighted combination, a principal component analysis, a linear discriminant analysis, a voting, a clustering, a support vector machine, or an artificial network.

4. The system of claim 1 , wherein the logic further generates time concentration curves from the imaging data.

5. The system of claim 1 , wherein the confidence value indicates that the imaging data is appropriate for use in a brain perfusion study, and the imaging quality indicators correspond to a confidence in the brain perfusion study.

6. The system of claim 1 , wherein the logic further presents the confidence value to a user of the system.

7. The system of claim 6 , wherein the logic further presents the confidence value as corresponding to one level in a multi-level evaluation system.

8. The system of claim 6 , wherein the logic further tailors the presentation of the confidence value to be different for different classes of users, based on the need of each class of users.

9. The system of claim 6 , wherein the logic further presents the confidence value in conjunction with imaging results.

10. The system of claim 1 further comprising a scanner console which includes the logic, and the scanner console presents the confidence value to a user of the scanner console while a patient being imaged is still available for further imaging in the event the confidence level is not high enough.

11. The system of claim 1 , wherein the logic further identifies a reason for a poor confidence value.

12. The system of claim 11 , wherein the logic further proposes a modification to an image acquisition technique to increase the poor confidence value.

13. The system of claim 12 , wherein the modification to the image acquisition technique may include changing a setting of either an imaging device or an associated equipment.

14. A method automatically implemented by a computer to assess a confidence in an dynamic functional imaging data based on a proposed diagnostic task or treatment decision, the method comprising:
determining one or more imaging quality indicators relating to the acquisition of acquired dynamic functional imaging data based on one or more quantitative imaging quality factors corresponding to the proposed diagnostic task or treatment decision, wherein the one or more quantitative imaging quality factors each comprise a quantitative assessment of at least one of the accuracy, location, and timing of the acquisition, and wherein the one or more imaging quality indicators are generated by applying the one or more quantitative imaging quality factors to the acquired imaging data; and
comparing the one or more imaging quality indicators to one or more confidence benchmark values associated with the one or more quantitative imaging quality factors, and determining a confidence value indicative of the confidence that he acquisition of the imaging data is of sufficient quality for purposes of performing the proposed diagnostic task or making the proposed treatment decision.

15. The method of claim 14 , further comprising generating at least one composite confidence value based on two or more individual confidence values.

16. The method of claim 15 , further comprising generating the at least one composite confidence value by a linear combination, a weighted combination, a principal component analysis, a linear discriminant analysis, a voting, a clustering, a support vector machine, or an artificial network.

17. The method of claim 14 , further comprising generating time concentration curves from the imaging data.

18. The method of claim 14 , wherein the confidence value indicates that the imaging data is appropriate for use in a brain perfusion study, and the imaging quality indicators correspond to a confidence in the brain perfusion study.

19. The method of claim 14 , further comprising determining the confidence value as corresponding to one level in a multi-level evaluation system.

20. The method of claim 14 , further comprising tailoring presentation of the confidence value to a user to be different for different classes of users, based on the need of each class of users.

21. The method of claim 14 , further comprising identifying a reason for a poor confidence value.

22. The method of claim 21 , further comprising proposing a modification to an image acquisition technique to increase the poor confidence value.

23. The method of claim 22 , wherein the modification to the image acquisition technique may include changing a setting of either an imaging device or an associated equipment.

24. A training system to improve confidence in an dynamic functional imaging acquisition based on a proposed diagnostic task or treatment decision, the system comprising a computer readable non-transitory medium configured to receive dynamic functional imaging data, the computer readable non-transitory medium comprising logic to:
determine one or more imaging quality indicators relating to the acquisition of the acquired imaging data base on one or more quantitative imaging quality factors corresponding to the proposed diagnostic task or treatment decision, wherein the one or more quantitative imaging quality factors each comprise a quantitative assessment of at least one of the accuracy, location, and timing of the acquisition, and wherein the one or more imaging quality indicators are generated by applying the one or more quantitative imaging quality factors to the acquired imaging data;
compare the one or more imaging quality indicators to one or more confidence benchmark values associated with the one or more quantitative imaging quality factors and determine a confidence value indicative of the confidence that he acquisition of the imaging data is of sufficient quality for purposes of performing the proposed diagnostic task or making the proposed treatment

Assignees

• Olszewski Mark
• Bredno Joerg
• Koninkl Philips Nv

Inventors

• Olszewski Mark
• Bredno Joerg

Classifications

• G06T7/0002 Primary

  Inspection of images, e.g. flaw detection · CPC title

• G06T2207/30104

  Vascular flow; Blood flow; Perfusion · CPC title

• G06T2207/10072

  Tomographic images · CPC title

• G06T2207/30016

  Brain · CPC title

• G06T2207/30168

  Image quality inspection · CPC title