Automated methods and systems for vascular plaque detection and analysis

• US 7,657,299 B2
• Filed: 08/21/2004
• Issued: 02/02/2010
• Est. Priority Date: 08/21/2003
• Status: Expired due to Fees

• Current Assignee: Ischem Corporation
• Original Assignee: Ischem Corporation
• Inventors: Huizenga, Joel T., Brotherton, Thomas Woodley, Anderson, Russell W.
• Primary Examiner(s): Winakur; Eric F
• Assistant Examiner(s): Rozanski; Michael T
• Application Number:
  US10/923,124
• Publication Number:
  US 20050043614A1
• Time in Patent Office: 1,991 Days
• Field of Search: 600/407, 382/276
• US Class Current: 600/410
• CPC Class Codes: A61B 5/02007 Evaluating blood vessel condition, e.g. elasticity, compliance
• CPC Class Codes: A61B 5/055 involving electronic [EMR] or nuclear [NMR] magnetic resonance, e.g. magnetic resonance imaging
• CPC Class Codes: A61B 5/7235 Details of waveform analysis A61B5/349 takes precedence
• CPC Class Codes: A61B 5/726 using Wavelet transforms
• CPC Class Codes: A61B 6/00 Apparatus or devices for radiation diagnosis; Apparatus or devices for radiation diagnosis combined with radiation therapy equipment instruments measuring radiation intensity for application in the field of nuclear medicine, e.g. in vivo counting, G01T1/161; apparatus for taking X-ray photographs G03B42/02
• CPC Class Codes: C23F 11/08 in other liquids
• CPC Class Codes: G06T 2207/10088 Magnetic resonance imaging [MRI]
• CPC Class Codes: G06T 2207/30101 Blood vessel; Artery; Vein; Vascular
• CPC Class Codes: G06T 2210/41 Medical
• CPC Class Codes: G06T 7/0012 Biomedical image inspection
• CPC Class Codes: G06V 2201/032 of protuberances, polyps nodules, etc.

Abstract

Automated methods and systems for the detection and analysis of plaque in one or more regions of a patient'"'"'s vasculature are described.

Claims

1. A fully automated method of determining whether a blood vessel of a patient'"'"'s vasculature contains plaque by classifying plaque components, comprising computationally processing at least a first processable data type and a second processable data type obtained using at least one non-invasive medical imaging system in order to analyze at least one cross section of a blood vessel of a patient'"'"'s vasculature using statistical classifiers developed using statistical modeling to determine if the blood vessel comprises at least one tissue correlated with the presence of plaque, in which event the blood vessel is determined to contain plaque, wherein the fully automated method does not require human intervention and wherein at least each of the first and second processable data types are processable magnetic resonance data generated by an MRI instrument and selected from the group consisting of T1-weighted data, T2-weighted data, PDW-weighted data, TOF-weighted data, and data generated by a combination of two or more of the foregoing.

2. A fully automated method according to claim 1 wherein the MRI instrument generates raw magnetic resonance data from which processable magnetic resonance data are derived.

3. A fully automated method according to claim 2 wherein a plurality of different radio frequency pulse sequence series are employed, wherein each of the different radio frequency pulse sequence series allows raw magnetic resonance data to be generated for a subset of different tissues that may be present in the blood vessel.

4. A fully automated method according to claim 3 wherein the components comprising the processable magnetic resonance data are computationally brought into registration.

5. A fully automated method according to claim 4 wherein registration is accomplished by aligning the components comprising the processable magnetic resonance data about a representation that represents a landmark selected from the group consisting of a vessel lumen centroid and a vessel branch point.

6. A fully automated method according to claim 5 wherein the landmark is selected from the group consisting of a physical landmark and a computational landmark.

7. A fully automated method according to claim 1 wherein the blood vessel comprises a portion of the vasculature supplying blood to an organ selected from the group consisting of a brain and a heart.

8. A fully automated method according to claim 1 wherein the blood vessel is selected from the group consisting of a carotid artery and a coronary artery.

9. A fully automated method according to claim 1 wherein the patient is human.

10. A fully automated method according to claim 1 wherein the processable data are generated by pre-processing raw data generated by the medical imaging system.

11. A fully automated method according to claim 10 further comprising normalizing the processable data prior to computationally processing the processable data.

12. A fully automated method according to claim 1 wherein the processable data are computationally processed to determine whether the blood vessel, in the region of the cross section, comprises artery and plaque.

13. A fully automated method according to claim 12 wherein the statistical classifiers are developed using known outcome data by a process selected from the group consisting of logistic regression, decision trees, non-parametric regression, Fisher discriminant analysis, Bayesian network modeling, and a fuzzy logic system.

14. A fully automated method according to claim 13 wherein at least one of the plurality of stored tissue classifier elements was determined by a process selected from the group consisting of post-operative histological examination, direct tissue inspection, and labeling by one or more experts.

15. A fully automated method according to claim 12 wherein the processable data are computationally processed to determine whether the blood vessel, in the region of the cross section, further comprises at least one tissue selected from the group consisting of adventitia, a calcium deposit, a cholesterol deposit, fibrous plaque, and thrombus.

16. A fully automated method according to claim 1 comprising computationally processing processable data of a plurality of spaced cross sections of the blood vessel.

17. A fully automated method according to claim 16 further comprising computationally rendering a three-dimensional model of the blood vessel over at least a portion of the region bounded by the most distantly spaced cross sections of the blood vessel.

18. A fully automated method according to claim 17 further comprising computationally determining plaque volume present in the three-dimensional model of the blood vessel.

19. A fully automated method of assessing effectiveness of a therapeutic regimen, comprising:

a. determining a plaque burden in a patient using a fully automated method according to claim 18;

b. delivering to the patient a therapeutic regimen comprising administration of a drug expected to stabilize or reduce the plaque burden in a patient over the course of the therapeutic regimen; and

c. during and/or at the end of the therapeutic regimen determining whether the plaque burden in the patient has stabilized or been reduced, thereby allowing assessment of the effectiveness of the therapeutic regimen.

20. A fully automated method according to claim 19 wherein the drug is an investigational drug.

21. A fully automated method according to claim 17 further comprising computationally determining composition of plaque present in the three-dimensional model of the blood vessel.

22. A fully automated method according to claim 21 further comprising computationally distinguishing whether the plaque is a vulnerable plaque or a stable plaque.

23. A method of treating a patient having vulnerable plaque in a blood vessel, comprising:

a. determining that a patient has a vulnerable plaque in a blood vessel using a fully automated method according to claim 21; and

b. delivering to the patient a therapeutic regimen designed to stabilize or reduce vulnerability of the vulnerable plaque to rupture over the course of the therapeutic regimen, thereby treating the patient.

24. A method according to claim 23 wherein therapeutic regimen comprises administration of a drug that stabilizes or reduces vulnerability of the plaque to rupture.

25. A method according to claim 24 wherein the drug is selected from the group consisting of statins, anti-inflammatory drugs, and anti-coagulant drugs.

26. A fully automated method according to claim 1 further comprising generating an output file comprising data resulting from the computationally processing.

27. A fully automated method according to claim 26 wherein the output file further comprises a computationally rendered three-dimensional model of the blood vessel over at least a portion of the region bounded by most distantly spaced cross sections of the blood vessel.

28. A computer program product comprising a computer usable medium having computer readable program code embodied therein, wherein the computer readable program code is configured to implement a fully automated method according to claim 1 on a computer adapted to execute the computer readable program code.

29. A system for analyzing whether a blood vessel of a patient'"'"'s vasculature contains plaque, the system comprising:

a. a computer adapted to execute the computer readable program code embodied in a computer program product according to claim 28;

b. a computer data storage system in communication with the computer, wherein the computer data storage system is configured to send to, receive from, and/or store data processed by the computer; and

c. operably connected to the computer, a communications interface for receiving data to be processed by, or for sending data after processing by, the computer.

30. A fully automated method for analyzing patient data obtained using a non-invasive medical imaging system to determine whether a blood vessel of the patient contains plaque by classifying plaque components, comprising:

a. obtaining processable data of at least one cross section of a blood vessel of a patient'"'"'s vasculature, wherein the processable data are derived from raw data collected using a medical imaging system that comprises an MRI instrument, wherein the processable data comprises at least a first processable magnetic resonance data type and a second processable magnetic resonance data type generated by an MRI instrument and selected from the group consisting of T1-weighted data, T2-weighted data, PDW-weighted data, TOF-weighted data, and data generated by a combination of two or more of the foregoing;

b. communicating the processable data to a computer configured to receive and computationally process the processable data using statistical classifiers developed using statistical modeling to determine whether the blood vessel in the region of the cross section(s) comprises at least one tissue correlated with the presence of plaque, in which event the blood vessel is determined to contain plaque; and

c. using the computer to computationally process the processable data and determine whether the blood vessel contains plaque, wherein the computational processing and determination of whether the blood vessel contains plaque does not require human intervention.

31. A fully automated method according to claim 30 wherein the medical imaging system and the computer are located at different locations.

32. A fully automated method according to claim 31 wherein the computer resides in a computational center physically removed from each of a plurality of imaging centers which each comprises a medical imaging system capable of generating raw data from which processable data can be derived.

33. A fully automated method according to claim 32 wherein at least one of the imaging centers communicates raw data to the computational center via a telecommunications link.

34. A fully automated method according to claim 30 further comprising communicating results of the analysis to an address specified as being affiliated with medical imaging system used to collect the raw data.