Classification of tumor tissue with a personalized threshold

• US 9,498,136 B2
• Filed: 04/10/2012
• Issued: 11/22/2016
• Est. Priority Date: 04/18/2011
• Status: Active Grant

• Current Assignee: Koninklijke Philips N.V.
• Original Assignee: Koninklijke Philips N.V.
• Inventors: Lucassen, Gerhardus Wilhelmus, Hendriks, Bernardus Hendrikus Wilhelmus, Nachabe, Rami
• Primary Examiner(s): Le, Long V
• Assistant Examiner(s): Sakamoto, Colin T
• Application Number:
  US14/112,555
• Publication Number:
  US 20140046197A1
• Time in Patent Office: 1,687 Days
• US Class Current: 1/1
• CPC Class Codes: A61B 1/00 Instruments for performing medical examinations of the interior of cavities or tubes of the body by visual or photographical inspection, e.g. endoscopes examination of body cavities or body tracts using ultrasonic, sonic or infrasonic waves A61B8/12; endoscopic instruments for taking cell samples or for biopsy A61B10/04; for surgical purposes A61B17/00; endoscopic surgical cutting instruments A61B17/32; surgical instruments using a laser beam being directed along or through a flexible conduit A61B18/22; Illuminating arrangements therefor for the eyes A61B3/00
• CPC Class Codes: A61B 5/0071 by measuring fluorescence emission
• CPC Class Codes: A61B 5/0075 by spectroscopy, i.e. measuring spectra, e.g. Raman spectroscopy, infrared absorption spectroscopy A61B5/0071 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 5/0091 for mammography
• CPC Class Codes: A61B 5/4887 Locating particular structures in or on the body
• CPC Class Codes: A61B 5/6848 Needles
• CPC Class Codes: A61B 5/6852 Catheters
• CPC Class Codes: G01N 2021/6421 Measuring at two or more wavelengths
• CPC Class Codes: G01N 21/64 Fluorescence; Phosphorescence

Abstract

The present invention deals with discrimination of malignant tissue from normal and benign tissue in a single patient on the basis of optical spectroscopic measurements. Starting from spectroscopic measurements in normal tissue, reference values are obtained for the normal class. With spectroscopic measurements in other tissues data points can be assigned to new class(es) when the spectral characteristics fall outside a threshold defining the reference class. Thresholds between different classes can also be defined. Finding (the transition to) malignant tissue is based on comparing the spectroscopic values to the classification threshold discriminating normal and benign versus malignant tissue. Thus, the basis of normal spectroscopic measurements is tuned to the individual patient characteristic. Discriminating the normal plus benign and malignant from that reference is more efficient compared to the reference of the all patient database.

Claims

1. A system for obtaining at least one patient specific threshold for discrimination among different tissue types within a patient, the system comprising:

an optical probe configured to obtain light measurements at one or more positions in tissue of a patient;

a means for confirming said optical probe is positioned to obtain light measurements at one or more positions in patient tissue of a first tissue type; and

a console arranged configured to;

spectrally analyze light measurements obtained by the optical probe at said one or more positions in patient tissue of the first tissue type,

calculate predetermined spectral characteristics for the patient tissue of the first tissue type derived from fits of the spectrally analyzed light measurements obtained by the optical probe at said one or more positions in patient tissue of the first tissue type

define patient specific first tissue type data points in a score plot of a multivariate statistical analysis to form a patient specific first tissue type class as a first tissue type class on a basis of the calculated predetermined spectral characteristics for the patient tissue of the first tissue type,

define a first patient specific threshold on the score plot for the first tissue type class by using (1) the calculated predetermined spectral characteristics for the patient tissue of the first tissue type as a reference tissue of the first tissue type class and (2) intra-patient a priori knowledge of the predetermined characteristics for the first tissue type and/or other tissue types relative to the first tissue type,

spectrally analyze further light measurements obtained by the optical probe at another position in patient tissue,

calculate the predetermined spectral characteristics for the further light measurements derived from fits of the spectrally analyzed further light measurements obtained by the optical probe at said another position in patient tissue,

define data points for the further light measurements in the score plot on a basis of the calculated predetermined spectral characteristics for the further light measurements,

test whether the data points for the further light measurements fall outside the first patient specific threshold in said score plot, and

define a patient specific second tissue type class as a second tissue type class on the basis of the calculated predetermined spectral characteristics for the further light measurements if the data points for the further light measurements fall outside the first patient specific threshold in said score plot.

2. The system according to claim 1, wherein said predetermined spectral characteristics comprise absorption and scattering characteristics.

3. The system according to claim 1, wherein said predetermined spectral characteristics comprise fluorescence characteristics.

4. The system according to claim 1, wherein said different tissue types comprise different normal types of tissue, or normal and diseased tissue;

or normal and tumor tissue, or normal tissue, benign and malignant tissue.

5. The system according to claim 1, wherein said optical probe comprises a needle, a catheter or an endoscope.

6. The system according to claim 1, wherein the console is further configured to recognize data points in said score plot as belonging to the second tissue type class based on a plot shape of said data points in said score plot.

7. The system according to claim 1, wherein the first tissue type class relates to fat or gland tissue and the second tissue type class relates to adenocarcinoma or ductal carcinoma in situ tissue.

8. The system according to claim 1, wherein the console is further configured to:

define a third tissue type class from data points in said score plot not classified in either the first or second tissue type classes, and

assign tissue types to the second and third tissue type classes based on an orientation of a triangle defined by data points of the first, second, and third tissue type classes in said score plot.

9. The system according to claim 1, wherein the console is further configured to discriminate or identify tissue types of the first and second tissue type classes based on a known correlation between measured spectra and a database of individual patient spectra.

10. The system according to claim 1, wherein the console is further configured to:

generate a reference map in a space defined by at least two selected from the group consisting of extracted water, lipid, and collage fractions,

classify the space based on the tissue type, and

tag the reference map with data point representing the spectrally analyzed light measurements.

11. A method for obtaining at least one threshold for discrimination among different tissue types, the method comprising:

positioning an optical probe at one or more positions in patient tissue of a first tissue type under guidance of a position confirmation means;

obtaining light measurements at said one or more positions in patient tissue of said first tissue type with the optical probe;

spectrally analyzing the light measurements obtained by the optical probe at said one or more positions in patient tissue of the first tissue type;

calculating predetermined spectral characteristics for the patient tissue of the first tissue type derived from fits of the spectrally analyzed light measurements obtained by the optical probe at said one or more positions in patient tissue of the first tissue type;

defining patient specific first tissue type data points in a score plot of multivariate statistical analysis to form a patient specific first tissue type class as a first tissue type class on a basis of the calculated predetermined spectral characteristics for the patient tissue of the first tissue type;

defining a first patient specific threshold on the score plot for the first tissue type class by using (1) the calculated predetermined spectral characteristics for the patient tissue of the first tissue type as a reference tissue of the first tissue type class and (2) intra-patient a priori knowledge of the predetermined characteristics for the first tissue type and/or other tissue types relative to the first tissue type;

positioning the optical probe at further positions in the tissue;

obtaining further light measurements at said further positions in the tissue with the optical probe;

spectrally analyzing said further light measurements;

calculating the predetermined spectral characteristics for the further light measurements derived from fits of the spectrally analyzed further light measurements;

defining data points for the further light measurements in the score plot on a basis of the calculated predetermined spectral characteristics for the further light measurements;

testing whether the data points for the further light measurements fall outside the first patient specific threshold in said score plot; and

defining a patient specific second tissue type class as a second tissue type class on the basis of the calculated predetermined spectral characteristics for the further light measurements if the data points for the further light measurements fall outside the first patient specific threshold in said score plot.

12. The method according to claim 11, wherein said predetermined spectral characteristics comprise absorption and scattering characteristics.

13. The method according to claim 11, wherein said predetermined spectral characteristics comprise fluorescence characteristics.

14. The method according to claim 11, wherein said different tissue types comprise different normal types of tissue, or normal and diseased tissue, or normal and tumor tissue, or normal tissue, benign and malignant tissue.

15. The method according to claim 11, wherein said optical probe comprises a nee a catheter or an endoscope.

16. The method according to claim 11, further comprising recognizing data points in said score plot as belonging to the second tissue type class based on a plot shape of said data points in said score plot.

17. The method according to claim 11, wherein the first tissue type class relates to fat or gland tissue and the second tissue type class relates to adenocarcinoma or ductal carcinoma in situ tissue.

18. The method according to claim 11, further comprising:

defining a third tissue type class from data points in said score plot not classified in either the first or second tissue type classes; and

assigning tissue types to the second and third tissue type classes based on an orientation of a triangle defined by data points of the first, second, and third tissue type classes in said score plot.

19. The method according to claim 11, further comprising discriminating or identifying tissue types of the first and second tissue type classes based on a known correlation between measurement spectra and a database of individual patient spectra.

20. The method according to claim 11, further comprising:

generating a reference map in a space defined by at least two selected from the group consisting of extracted water, lipid, and collagen fractions;

classifying the space based on the tissue types; and

tagging the reference map with data points representing the spectrally analyzed light measurements.