Non-invasive tissue characterization system and method

• US 7,175,597 B2
• Filed: 02/03/2003
• Issued: 02/13/2007
• Est. Priority Date: 02/03/2003
• Status: Active Grant

• Current Assignee: Cleveland Clinic Foundation
• Original Assignee: Cleveland Clinic Foundation
• Inventors: Nair, Anuja, Vince, D. Geoffrey, Klingensmith, Jon D.
• Primary Examiner(s): Jaworski; Francis J.
• Application Number:
  US10/356,812
• Publication Number:
  US 20040152983A1
• Time in Patent Office: 1,471 Days
• Field of Search: 600/437, 600440-447, 600449-450, 600/459, 600466-467, 128/916, 382/128
• US Class Current: 600/443
• CPC Class Codes: A61B 5/02007 Evaluating blood vessel condition, e.g. elasticity, compliance
• CPC Class Codes: A61B 5/7264 Classification of physiological signals or data, e.g. using neural networks, statistical classifiers, expert systems or fuzzy systems neural networks per se G06N3/00; expert systems per se G06N5/00
• CPC Class Codes: A61B 8/00 Diagnosis using ultrasonic, sonic or infrasonic waves imaging of objects using sonar G01S15/00
• CPC Class Codes: A61B 8/0825 for diagnosis of the breast, e.g. mammography
• CPC Class Codes: G16H 50/20 for computer-aided diagnosis, e.g. based on medical expert systems

Abstract

One embodiment of the present system and method is directed to the identification of tissues within a vascular object by analyzing ultrasound data collected from the vascular object by non-invasive scans. By identifying and characterizing types of tissue from ultrasound data, an assessment can be made about the health condition of a patient without an invasive procedure. Other applications of the present system will also be appreciated including identifying other types of tissues.

Claims

1. A system for determining plaque composition, the system comprising:

an ultrasound system with a non-invasive probe for collecting ultrasound data including backscatter signals from a blood vessel;

a signal analyzer for analyzing the ultrasound signal data and determining one or more signal properties from the backscatter signals of the blood vessel; and

a correlation processor configured to associate the one or more signal properties to pre-determined signal properties of plaque components wherein the pre-determined signal properties are embodied as a classification tree having branch node conditions based on the pre-determined signal properties and one or more leaf nodes that identify a type of plaque component, the correlation processor further configured to identify a plaque component based on the one or more signal properties.

2. The system of claim 1 further including transformation logic configured to transform the ultrasound data to a power spectral density format.

3. The system of claim 2 wherein the one or more signal properties includes one or more spectral properties.

4. The system of claim 1 wherein the correlation processor being configured to traverse the classification tree to a leaf node based on a comparison of the one or more signal properties from the backscatter signal to the branch node conditions.

5. The system of claim 1 further including border detection logic configured to determine borders of the blood vessel from the backscatter signals.

6. The system as set forth in claim 5, where the signal analyzer logic selectively analyzes substantially only the ultrasound signal data within the borders of the blood vessel.

7. The system of claim 1 wherein the non-invasive probe is configured to collect the ultrasound data with a plurality of transducers.

8. The system of claim 1 wherein the ultrasound system includes at least one processor configured to process the ultrasound data.

9. The system of claim 1 wherein the ultrasound system further includes diagnostic logic for generating an assessment as to a health condition based on the components of the blood vessel identified.

10. An article of manufacture embodied in a computer-readable medium for use in a processing system for analyzing ultrasound signal data, the article of manufacture comprising:

first processor executable instructions for causing a processor to receive ultrasound signal data of a scanned object collected from a non-invasive probe;

second processor executable instructions for causing a processor to determine signal properties of one or more regions of interest associated with the scanned object from the ultrasound signal data; and

third processor executable instructions for causing a processor to classify the one or more regions of interest as a component type based on a classification data structure pre-determined from measured associations between signal properties and one or more component types of an object similar to the scanned object, the classification data structure having branch node conditions and one or more leaf nodes that identify the component based on the measured associations.

11. The article of manufacture as set forth in claim 10 further including fourth processor executable instructions for causing a processor to generate an assessment relating to a condition of the scanned object based on the classified one or more regions of interest.

12. The article of manufacture as set forth in claim 11 wherein the assessment is a score reflecting an amount of a plaque component identified within the scanned object.

13. The article of manufacture as set forth in claim 11 wherein the assessment is an image identifying the classified regions of interest.

14. The article of manufacture as set forth in claim 10 further including fourth processor executable instructions for causing a processor to analyze a frequency spectrum of the ultrasound signal data where the signal properties include spectral properties.

15. The article of manufacture as set forth in claim 10 wherein the non-invasive probe is configured to scan an object from a location external to the object.

16. The article of manufacture as set forth in claim 10 wherein the second processor executable instructions include instructions for causing a processor to analyze frequency data from the ultrasound signal data to determine the signal properties of the one or more regions of interest.

17. The article of manufacture as set forth in claim 10 wherein the ultrasound signal data includes a plurality of scan line data and, the second processor executable instructions include instructions for causing a processor to segment the scan line data.

18. The article of manufacture as set forth in claim 10 wherein the classification data structure includes measured associations between signal properties and one or more component types of cancerous and non-cancerous tissue.

19. The article of manufacture as set forth in claim 10 wherein the classification data structure includes measured associations between signal properties and one or more component types of plaque.

20. A method of identifying one or more components of an object, the method comprising:

receiving backscatter signals from an ultrasonic probe scanning the object from a location external to the object;

determining one or more signal properties from the backscatter signals;

associating the one or more signal properties to pre-determined signal properties of object components wherein the pre-determined signal properties comprise branch node conditions based on the pre-determined signal properties and one or more leaf nodes identifying a type of object component; and

identifying one or more object components based on the associating.

21. The method as set forth in claim 20 wherein the backscatter signals include a plurality of scan lines and the determining step includes determining signal properties for a plurality of segments from the plurality of scan lines.

22. The method as set forth in claim 20 where the receiving step includes collecting backscatter signals from a carotid artery.

23. The method as set forth in claim 22 where the identifying step includes identifying one or more types of plaque within the carotid artery.

24. The method as set forth in claim 20 where the receiving step includes collecting backscatter signals from breast tissue.

25. The method as set forth in claim 24 where the identifying step includes identifying whether cancerous tissue is present.