Body sensing system

• US 6,976,013 B1
• Filed: 06/16/2004
• Issued: 12/13/2005
• Est. Priority Date: 08/28/2000
• Status: Expired due to Term

• Current Assignee: United States Of America As Represented By The Administrator Of The National Aeronautics And Space Administration
• Original Assignee: United States Of America As Represented By The Administrator Of The National Aeronautics And Space Administration
• Inventors: Mah, Robert W.
• Primary Examiner(s): DAVIS, GEORGE B
• Application Number:
  US10/874,003
• Time in Patent Office: 545 Days
• Field of Search: 706/27, 706/28, 706/26, 706/21
• US Class Current: 706/27
• CPC Class Codes: A61B 2017/00022 Sensing or detecting at the treatment site
• CPC Class Codes: A61B 34/10 Computer-aided planning, simulation or modelling of surgical operations
• CPC Class Codes: A61B 5/00 Measuring for diagnostic purposes radiation diagnosis A61B6/00; diagnosis by ultrasonic, sonic or infrasonic waves A61B8/00; Identification of persons
• CPC Class Codes: A61B 5/0073 by tomography, i.e. reconstruction of 3D images from 2D projections A61B5/0066 takes precedence
• CPC Class Codes: A61B 5/0084 for introduction into the body, e.g. by catheters A61B5/1459 takes precedence
• CPC Class Codes: A61B 5/0261 using optical means, e.g. infrared light
• CPC Class Codes: A61B 5/031 Intracranial pressure
• CPC Class Codes: A61B 5/14539 for measuring pH
• CPC Class Codes: A61B 5/1473 invasive, e.g. introduced into the body by a catheter A61B5/1482 takes precedence
• CPC Class Codes: A61B 5/369 Electroencephalography [EEG] devices for psychotechnics A61B5/16
• CPC Class Codes: A61B 5/415 the glands, e.g. tonsils, adenoids or thymus
• CPC Class Codes: A61B 5/418 lymph vessels, ducts or nodes
• CPC Class Codes: A61B 5/7275 Determining trends in physiological measurement data; Predicting development of a medical condition based on physiological measurements, e.g. determining a risk factor
• CPC Class Codes: A61B 8/08 Detecting organic movements or changes, e.g. tumours, cysts, swellings A61B8/02 - A61B8/06 take precedence
• CPC Class Codes: A61B 90/10 for stereotaxic surgery, e.g. frame-based stereotaxis
• CPC Class Codes: G16H 50/20 for computer-aided diagnosis, e.g. based on medical expert systems

Abstract

System and method for performing one or more relevant measurements at a target site in an animal body, using a probe. One or more of a group of selected internal measurements is performed at the target site, is optionally combined with one or more selected external measurements, and is optionally combined with one or more selected heuristic information items, in order to reduce to a relatively small number the probable medical conditions associated with the target site. One or more of the internal measurements is optionally used to navigate the probe to the target site. Neural net information processing is performed to provide a reduced set of probable medical conditions associated with the target site.

Claims

1. A system for estimating a medical condition associated with a target site in an animal body, the system comprising:

a first database that contains R-dimensional vector values x(q) of reference values of measurements that characterize one or more medical conditions of the target site in the animal body, with q in Q1 or q in Q2, where Q1 and Q2 are mutually exclusive index sets, where each vector value x(q) in the first database is associated with a first set S1 of medical conditions, corresponding to q being a member of Q1, or with a second set S2 of medical conditions, corresponding to q being a member of Q2, where S1 and S2 are mutually exclusive and R is a selected positive integer;

a second database that contains vector values y in a set S3 of one or more measurements made at or adjacent to the target site, where y is a P-dimensional vector and P is a selected positive integer with P≦

R; and

a computer that is programmed to form a non-negative, real-valued medical condition function of a metric distance between the vector x(q) and one or more of the vector values y, where the medical condition function distinguishes between a first medical condition in which y is more likely associated with the first set S1 and a second medical condition in which y is more likely associated with the second set S2.

2. The system of claim 1, wherein at least one of said sets S1 and S2 corresponds to at least one of a normal medical condition and a benign medical condition.

3. The system of claim 1, wherein at least one of said sets S1 and S2 corresponds to a malignant medical condition.

4. A system for estimating a medical condition associated with a target site in an animal body, the system comprising:

a first database that contains R-dimensional vector values x(q) of reference values of measurements that characterize one or more medical conditions of the target site in the animal body, with q in Q1 or q in Q2, where Q1 and Q2 are mutually exclusive index sets, where each vector value x(q) in the first database is associated with a first set S1 of medical conditions, corresponding to q being a member of Q1, or with a second set S2 of medical conditions, corresponding to q being a member of Q2, where S1 and S2 are mutually exclusive and R is a selected positive integer;

a second database that contains vector values y in a set S3 of one or more measurements made at or adjacent to the target site, where y is a P-dimensional vector and P is a selected positive integer with P≦

R; and

a computer that is programmed;

to form a non-negative, real-valued metric d(x(q);

y;

q), depending upon vectors x(q) and y drawn from the first and second databases, respectively, and upon the index q;

to form a medical condition function F(d(x(q);

y;

q)), depending upon the metric values d(x(q);

y;

q), where F is a selected non-negative, monotonically decreasing function of the metric value d(x(q);

y;

q);

to compute the quantities F1(y)=max_{w(q) in S1}F(d(w(q);

y;

q)) and F2(y)=max_{w(q) in S2}F(d(w(q);

y;

q));

when F1(y)>

F2(y), to interpret the value F1(y)/{F1(y)+F2(y)} as a lower bound on a probability that the measurement value y is associated with the first set S1, and to interpret the value F2(y)/{F1 (y)+F2(y)} as an upper bound on a probability that the measurement value y is associated with the first set S2; and

when F1(y)<

F2(y), to interpret the value F1(y)/{F1(y)+F2(y)} as an upper bound on a probability that the measurement value y is associated with the first set S1, and to interpret the value F2(y)/{F1(y)+F2(y)} as a lower bound on a probability that the measurement value y is associated with the first set S2.

5. The system of claim 4, wherein said computer is further programmed to draw said function F(z) for a non-negative value z from a group of functions consisting of F(z)=exp{−

α

·

z^p}, F(z)={β

+χ

·

z^r}<sup>−

γ</sup>

and F(z)=μ

−

ν

·

z^s, where α

, β

, χ

, γ

, μ

, ν

, p, r and s are selected non-negative values.

6. The system of claim 4, wherein said metric d(x(q);

y;

q) depends upon said vectors x(q) and y and depends upon said index q only through said vector x(q).

7. The system of claim 4, wherein, for at least two distinct values q′

and q″

with corresponding vectors x(q′

) in said set S1 and x(q″

) in said set S2, said metric value d(x(q′

);

y;

q′

) differs from said metric value d(x(q″

);

y;

q″

) for at least one measurement vector y.

8. The system of claim 4, wherein each of said functions F(d(x(q);

y;

q)) is chosen to satisfy 0≦

max_{y in S3} F(d(x(q);

y;

q))≦

1 for each vector x(q) and said computer is further programmed to interpret said value F(d(x′

(q);

y;

q)) for at least one vector x′

(q) in said set S1 as a probability that said measurement vector y belongs to said set S1.

9. The system of claim 4, wherein each of said functions F(d(x(q);

y;

q)) is chosen to satisfy 0≦

max_{y in S3}F(d(x(q);

y;

q))≦

1 for each vector x(q) and said computer is further programmed to interpret said value F(d(x′

(q);

y;

q)) for at least one vector x′

(q) in said set S2 as a probability that said measurement vector y belongs to said set S2.

10. The system of claim 4, wherein at least one of said sets S1 and S2 corresponds to at least one of a normal medical condition and a benign medical condition.

11. The system of claim 4, wherein said at least one of said sets S1 and S2 corresponds to a malignant medical condition.

12. A method for estimating a medical condition associated with a target site in an animal body, the method comprising:

providing a first database that contains R-dimensional vector values x(q) of reference values of measurements that characterize one or more medical conditions of the target site in the animal body, with q in Q1 or q in Q2, where Q1 and Q2 are mutually exclusive index sets, where each vector value x(q) in the first database is associated with a first set S1 of medical conditions, corresponding to q being a member of Q1, or with a second set S2 of medical conditions, corresponding to q being a member of Q2, where S1 and S2 are mutually exclusive and R is a selected positive integer;

providing a second database that contains vector values y in a set S3 of one or more measurements made at or adjacent to the target site, where y is a P-dimensional vector and P is a selected positive integer with P≦

R; and

programming providing a computer that is programmed to form a non-negative, real-valued medical condition function of a metric distance between the vector x(q) and one or more of the vector values y, where the medical condition function distinguishes between a first medical condition in which y is more likely in the first set S1 and a second medical condition in which y is more likely in the second set S2.

13. The method of claim 12, further comprising choosing said at least one of said sets S1 and S2 to correspond to at least one of a normal medical condition and a benign medical condition.

14. The method of claim 12, further comprising choosing at least one of said sets S1 and S2 to correspond to a malignant medical condition.

15. A method for estimating a medical condition associated with a target site in an animal body, the method comprising:

providing a first database that contains R-dimensional vector values x(q) of reference values of measurements that characterize one or more medical conditions of the target site in the animal body, with q in Q1 or q in Q2, where Q1 and Q2 are mutually exclusive index sets, where each vector value x(q) in the first database is associated with a first set S1 of medical conditions, corresponding to q being a member of Q1, or with a second set S2 of medical conditions, corresponding to q being a member of Q2, where S1 and S2 are mutually exclusive and R is a selected positive integer;

providing a second database that contains vector values y in a set S3 of one or more measurements made at or adjacent to the target site, where y is a P-dimensional vector and P is a selected positive integer with P≦

R; and

providing a computer that is programmed;

to form a non-negative, real-valued metric d(x(q);

y;

q), depending upon vectors x(q) and y drawn from the first and second databases, respectively, and upon the index q;

to form a medical condition function F(d(x(q);

y;

q)), depending upon the metric values d(x(q);

y;

q), where F is a selected non-negative, monotonically decreasing function of the metric value d(x(q);

y;

q);

to compute the quantities F1(y)=max_{w(q) in S1}F(d(w(q);

y;

q)) and F2(y)=max_{w(q) in S2}F(d(w(q);

y;

q));

when F1(y)>

F2(y), to interpret the value F1(y)/{F1(y)+F2(y)} as a lower bound on a probability that the measurement value y is associated with the first set S1, and to interpret the value F2(y)/{F1(y)+F2(y)} as an upper bound on a probability that the measurement value y is associated with the first set S2; and

when F1(y)<

F2(y), to interpret the value F1(y)/{F1(y)+F2(y)} as an upper bound on a probability that the measurement value y is associated with the first set S1, and to interpret the value F2(y)/{F1(y)+F2(y)} as a lower bound on a probability that the measurement value y is associated with the first set S2.

16. The method of claim 15, further comprising programming said computer to draw said function F(z) for z≧

0 from a group of functions consisting of F(z)=exp{−

α

·

z^P}, F(z)={β

+χ

·

z^r}<sup>−

γ</sup>

and F(z)=μ

−

ν

·

z^s, where α

, β

, χ

, γ

, μ

, ν

, p, r and s are selected non-negative values.

17. The method of claim 15, further comprising programming said metric d(x(q);

y;

q) to depend upon said vectors x(q) and y and depends upon said index q only through said vector x(q).

18. The method of claim 15, wherein, for at least two distinct values q′

and q″

, with corresponding vectors x(q′

) in said set S1 and x(q″

) in said set S2, further comprising programming said metric value d(x(q′

);

y;

q′

) to differ from said metric value d(x(q″

);

y;

q″

) for at least one measurement vector y.

19. The method of claim 15, further comprising programming each of said functions F(d(x(q);

y;

q)) to satisfy 0≦

max_{y in S3}F(d(x(q);

y;

q))≦

1 for each vector x(q) and further comprising programming said computer to interpret said value F(d(x′

(q);

y;

q)) for at least one vector x′

(q) in said set S1 as a probability that said measurement vector y belongs to said set S1.

20. The method of claim 15, further comprising programming each of said functions F(d(x(q);

y;

q)) to satisfy 0≦

max_{y in S3}F(d(x(q);

y;

q))≦

1 for each vector x(q) and further comprising programming said computer to interpret said value F(d(x′

(q);

y;

q)) for at least one vector x′

(q) in said set S2 as a probability that said measurement vector y belongs to said set S2.

21. The method of claim 15, further comprising programming said computer so that at least one of said sets S1 and S2 corresponds to at least one of a normal medical condition and a benign medical condition.

22. The method of claim 15, further comprising programming said computer so that at least one of said sets S1 and S2 corresponds to a malignant medical condition.