Auxiliary diagnostic apparatus and auxiliary diagnostic method

• US 8,775,096 B2
• Filed: 10/22/2010
• Issued: 07/08/2014
• Est. Priority Date: 10/29/2009
• Status: Active Grant

• Current Assignee: Hoya Corporation
• Original Assignee: Hoya Corporation
• Inventors: Chiba, Toru
• Primary Examiner(s): NEGIN, RUSSELL SCOTT
• Application Number:
  US13/499,395
• Publication Number:
  US 20120191365A1
• Time in Patent Office: 1,355 Days
• Field of Search: None
• US Class Current: 702/19
• CPC Class Codes: A61B 1/000094 extracting biological structures
• 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: G01N 33/50 Chemical analysis of biological material, e.g. blood, urine; Testing involving biospecific ligand binding methods; Immunological testing measuring or testing processes involving enzymes or microorganisms, compositions or test papers therefor; processes for forming such compositions, condition responsive control in microbiological or enzymological processes C12Q
• CPC Class Codes: G06F 17/10 Complex mathematical operations function generation by table look-up G06F1/03; evaluation of elementary functions by calculation G06F7/544
• CPC Class Codes: G06F 17/11 for solving equations , e.g. nonlinear equations, general mathematical optimization problems optimization specially adapted for a specific administrative, business or logistic context G06Q10/04
• CPC Class Codes: G06T 2207/10068 Endoscopic image
• CPC Class Codes: G06T 2207/30092 Stomach; Gastric
• CPC Class Codes: G06T 7/0012 Biomedical image inspection
• CPC Class Codes: G16B 5/00 ICT specially adapted for modelling or simulations in systems biology, e.g. gene-regulatory networks, protein interaction networks or metabolic networks
• CPC Class Codes: G16B 5/20 Probabilistic models
• CPC Class Codes: G16H 50/50 for simulation or modelling of medical disorders

Abstract

Disclosed is an auxiliary diagnostic apparatus including: a vector input unit that reads a test vector which is a spectral property vector of a biological tissue targeted for a diagnosis; a multiple linear regression analysis unit that executes a multiple liner regression analysis for the test vector with a plurality of individual component vectors which are spectral property vectors of particular substances, and obtains an error vector which is a vector of a residual error component; and an indicator calculation unit that extracts a feature of the error vector, and, from the extracted error vector, calculates an indicator representing whether an affected area is included in the biological tissue targeted for the diagnosis and which type of affected area has a possibility of being included in the biological tissue.

Claims

1. An auxiliary diagnostic apparatus, comprising:

a vector inputter that reads a test vector which is a spectral property vector of a biological tissue targeted for a diagnosis;

a multiple linear regression analyzer that executes a multiple linear regression analysis for the test vector with a plurality of individual component vectors which are spectral property vectors of particular substances, and obtains an error vector which is a vector of a residual error component; and

an indicator calculator that extracts a feature of the error vector, and, from the extracted feature, calculates an indicator indicating an affected area included in the biological tissue targeted for the diagnosis and which type of affected area is included in the biological tissue.

2. The auxiliary diagnostic apparatus according to claim 1,

wherein the individual component vectors are calculated by an individual component analysis from spectral property vectors of a plurality of biological tissue samples each of which corresponds to a same portion of the biological tissue targeted for the diagnosis and which does not include an affected area.

3. The auxiliary diagnostic apparatus according to claim 1,

wherein the indicator calculator calculates the indicator based on an affected area substance vector obtained by the individual component analysis from affected area sample error vectors which are vectors of residual error components obtained by executing, with the plurality of individual component vectors, the multiple linear regression analysis for spectral property vectors of a plurality of biological tissue samples including particular affected areas.

4. The auxiliary diagnostic apparatus according to claim 3,

wherein the indicator calculator operates to:

calculate, by the multiple linear regression analysis, a coefficient s_d satisfying a following expression (a);

E≈

s_dE_d 

 

(a)

where the error vector is defined as E=[E<sub>λ

1</sub>, E<sub>λ

2</sub>, . . . E<sub>λ

M</sub>] and the affected area substance vector is defined as Ed=[E<sub>dλ

1</sub>, E<sub>dλ

2</sub>, . . . E<sub>dλ

M</sub>];

calculate, using a weighing coefficient w<sub>λ

m</sub>, a similarity D between vectors E/s_d and E_d through a following expression (b);

5. The auxiliary diagnostic apparatus according to claim 4,

wherein the indicator calculator operates to:

calculate a probability that the similarity D is included in a similarity group D_dk, by a test based on a coefficient s_dk, satisfying a following expression (c) and obtained by the multiple linear regression analysis while defining the plurality of affected area sample error vectors as E_dk=[E<sub>dkλ

1</sub>, E<sub>dkλ

2</sub>, . . . E<sub>dkλ

M</sub>] (k=1, 2, . . . , K), and the similarity group D_dk between E_d and respective ones of vectors E_dk/s_dk obtained by a following expression (d); and

define the probability that the similarity D is included in the similarity group D_dk as the indicator,

6. An auxiliary diagnostic method, comprising:

reading, using a processor, a test vector which is a spectral property vector of a biological tissue targeted for a diagnosis;

executing, using the processor, a multiple linear regression analysis for the test vector with a plurality of individual component vectors which are spectral property vectors of particular substances, and obtaining an error vector which is a vector of a residual error component;

extracting, using the processor, a feature of the error vector, and, from the extracted feature, calculating an indicator indicating an affected area included in the biological tissue targeted for the diagnosis and which type of affected area is included in the biological tissue.

7. The auxiliary diagnostic method according to claim 6,

wherein the individual component vectors are calculated by an individual component analysis from spectral property vectors of a plurality of biological tissue samples each of which corresponds to a same portion of the biological tissue targeted for the diagnosis and which does not include an affected area.

8. The auxiliary diagnostic method according to claim 6,

wherein the calculating includes calculating the indicator based on an affected area substance vector obtained by the individual component analysis from affected area sample error vectors which are vectors of residual error components obtained by executing, with the plurality of individual component vectors, the multiple linear regression analysis for spectral property vectors of a plurality of biological tissue samples including particular affected areas.

9. The auxiliary diagnostic method according to claim 8,

wherein, the calculating includes,

calculating, by the multiple linear regression analysis, a coefficient s_d satisfying a following expression (a):

E≈

s_dE_d

where the error vector is defined as E=[E<sub>λ

1</sub>, E<sub>λ

2</sub>, . . . E<sub>λ

M</sub>] and the affected area substance vector is defined as Ed=[E<sub>dλ

1</sub>, E<sub>dλ

2</sub>, . . . E<sub>dλ

M</sub>];

calculating, using a weighing coefficient w<sub>λ

m</sub>, a similarity D between vectors E/s_d and E_d through a following expression (b);

10. The auxiliary diagnostic method according to claim 9,

wherein, the calculating includes,

calculating a probability that the similarity D is included in a similarity group D_dk, by a test based on a coefficient s_dk, satisfying a following expression (c) and obtained by the multiple linear regression analysis while defining the plurality of affected area sample error vectors as E_dk=[E_dkλ

1, E<sub>dkλ

2</sub>, . . . E<sub>dkλ

M</sub>] (k=1, 2, . . . , K), and the similarity group D_dk between E_d and respective ones of vectors E_dk/s_dk obtained by a following expression (d); and

defining the probability that the similarity D is included in the similarity group D_dk as the indicator,