Image analysis apparatus, imaging system, surgery support system, image analysis method, and storage medium

Patent metadata

Field	Value
Publication number	US-10156518-B2
Application number	US-201615386254-A
Country	US
Kind code	B2
Filing date	Dec 21, 2016
Priority date	Jun 24, 2014
Publication date	Dec 18, 2018
Grant date	Dec 18, 2018

Abstract

An image analysis apparatus includes: a calculator that generates, on the basis of a plurality of sample images obtained by irradiating a biological tissue with light having N wavelength bands selected from a wavelength bandwidth from 950 nm or more to 1600 nm or less as a predetermined wavelength bandwidth, sample data on the tissue in the predetermined wavelength bandwidth; and a data generator that compares the sample data with training data on a substance that is a training target, to generate distribution data indicating a distribution of the substance in the tissue.

First claim

What is claimed is:

1. An imaging system comprising:
an imaging device that acquires a hyperspectral image obtained by irradiating a biological tissue with infrared light having a predetermined wavelength band;
a calculator that generates, on the basis of the hyperspectral image, sample data on the tissue in the predetermined wavelength band; and
a data generator that compares the sample data with training data on water that is a training target, to generate first image data indicating a distribution of the water in the tissue, and compares the sample data with training data on lipid that is a training target, to generate second image data indicating a distribution of the lipid in the tissue.

2. The imaging system of claim 1 , wherein the data generator performs processing of combining a sample image based on the sample data with a water rule image based on the training data on the water to generate the first image data.

3. The imaging system of claim 2 , wherein the data generator performs processing of combining a sample image based on the sample data with a lipid rule image based on the training data on the lipid to generate the second image data.

4. The imaging system of claim 3 , wherein the data generator generates, on the basis of the first image data or the second image data, a color image indicating a distribution of the water or a distribution of the lipid.

5. The imaging system of claim 1 , wherein the data generator compares the sample data with training data on a protein that is a training target, to generate third image data indicating a distribution of the protein in the tissue.

6. A surgery support system comprising:
the imaging system of claim 1 ; and
a display that displays an image based on the first image data or an image based on the second image data.

7. An imaging method comprising:
acquiring a hyperspectral image obtained by irradiating a biological tissue with infrared light having a predetermined wavelength band;
generating, on the basis of the hyperspectral image, sample data on the tissue in the predetermined wavelength band; and
comparing the sample data with training data on water that is a training target, to generate first image data indicating a distribution of the water in the tissue, and comparing the sample data with training data on lipid that is a training target, to generate second image data indicating a distribution of the lipid in the tissue.

8. A non-transitory storage medium that stores therein an image analysis program that causes a computer to execute:
acquiring a hyperspectral image obtained by irradiating a biological tissue with infrared light having a predetermined wavelength band;
generating, on the basis of the hyperspectral image, sample data on the tissue in the predetermined wavelength band; and
comparing the sample data with training data on water that is a training target, to generate first image data indicating a distribution of the water in the tissue, and comparing the sample data with training data on lipid that is a training target, to generate second image data indicating a distribution of the lipid in the tissue.

9. An image analysis apparatus comprising:
a calculator that generates, on the basis of a plurality of pieces of sample information obtained by irradiating a biological tissue with infrared light having N wavelength bands selected from a predetermined wavelength bandwidth, sample data on the tissue in the predetermined wavelength bandwidth; and
a data generator that compares the sample data with training data on water that is a training target, with use of at least one of spectral angle mapper classification, spectral correlation mapper classification, or Euclidean distance classification, to generate distribution data indicating a distribution of the water in the tissue, wherein
the predetermined wavelength bandwidth is set from a wavelength bandwidth from 700 nm or more to 2500 nm or less as a training region for the water.

10. The image analysis apparatus of claim 9 , wherein
the data generator compares the sample data with training data on lipid that is a training target, with use of at least one of spectral angle mapper classification, spectral correlation mapper classification, or Euclidean distance classification, to generate distribution data indicating a distribution of the lipid in the tissue.

11. The image analysis apparatus of claim 9 , wherein
the data generator compares the sample data with training data on blood that is a training target, with use of at least one of spectral angle mapper classification, spectral correlation mapper classification, or Euclidean distance classification, to generate distribution data indicating a distribution of the blood in the tissue.

12. An imaging system comprising:
an imaging device that acquires a hyperspectral image obtained by irradiating a biological tissue with infrared light having a predetermined wavelength band;
a calculator that generates, on the basis of the hyperspectral image, sample data on the tissue in the predetermined wavelength band; and
a data generator that compares the sample data with training data on water that is a training target, with use of at least one of spectral angle mapper classification, spectral correlation mapper classification, or Euclidean distance classification, to generate first image data indicating a distribution of the water in the tissue, wherein
the predetermined wavelength bandwidth is set from a wavelength bandwidth from 700 nm or more to 2500 nm or less as a training region for the water.

13. The imaging system according to claim 12 , comprising:
an input device that accepts input from a user.

14. The imaging system according to claim 12 , comprising:
a light source that outputs infrared light having a spot shape elongated in one direction.

15. The imaging system according to claim 12 , wherein
the data generator compares the sample data with training data on lipid that is a training target, with use of at least one of spectral angle mapper classification, spectral correlation mapper classification, or Euclidean distance classification, to generate second image data indicating a distribution of the lipid in the tissue.

16. The imaging system according to claim 12 , wherein
the data generator compares the sample data with training data on blood that is a training target, with use of at least one of spectral angle mapper classification, spectral correlation mapper classification, or Euclidean distance classification, to generate third image data indicating a distribution of the blood in the tissue.

Assignees

• Nikon Corp

Inventors

• Liu Zhen
• Hataguchi Takeshi
• Ishikawa Hiroki

Classifications

• A61B90/00

  Instruments, implements or accessories specially adapted for surgery or diagnosis and not covered by any of the groups A61B1/00 - A61B50/00, e.g. for luxation treatment or for protecting wound edges · CPC title

• G01N21/3554

  for determining moisture content · CPC title

• A61B90/37

  Surgical systems with images on a monitor during operation · CPC title

• G01N21/27

  using photo-electric detection (G01N21/31 takes precedence){; circuits for computing concentration (logarithmic circuits G06G7/24; photometric circuits in general G01J)} · CPC title

• G01N21/359 Primary

  using near infrared light · CPC title