RECONSTRUCTION METHOD OF BIOLOGICAL TISSUE IMAGE, APPARATUS THEREFOR, AND IMAGE DISPLAY APPARATUS USING THE BIOLOGICAL TISSUE IMAGE

• US 20200134822A1
• Filed: 12/27/2019
• Published: 04/30/2020
• Est. Priority Date: 01/08/2013
• Status: Abandoned Application

• Current Assignee: Canon Kabushiki Kaisha (Canon Inc.)
• Original Assignee: Canon Kabushiki Kaisha (Canon Inc.)
• Inventors: Tanji, Koichi
• Application Number:
  US16/728,965
• Publication Number:
  US 20200134822A1
• Time in Patent Office: Days
• CPC Class Codes: G06T 11/003 Reconstruction from projections, e.g. tomography
• CPC Class Codes: G06T 2207/10056 Microscopic image
• CPC Class Codes: G06T 2207/20021 Dividing image into blocks, subimages or windows
• CPC Class Codes: G06T 2207/20081 Training; Learning
• CPC Class Codes: G06T 2207/30024 Cell structures in vitro; Tissue sections in vitro
• CPC Class Codes: G06T 7/0014 using an image reference approach
• CPC Class Codes: G06T 7/11 Region-based segmentation
• CPC Class Codes: G06V 20/698 Matching; Classification

Abstract

The present invention provides a method for classifying biological tissues with high precision compared to a conventional method. When measuring a spectrum which has a two-dimensional distribution that is correlated with a slice of a biological tissue, and acquiring a biological tissue image from the two-dimensional measured spectrum, the method includes dividing an image region into a plurality of small blocks, and then reconstructing the biological tissue image by using the measured spectrum and a classifier corresponding to each of the regions.

Claims

1. A reconstruction method of a biological tissue image using a signal processing apparatus based on a measured spectrum correlated with a substance distributed within a biological tissue comprising:

acquiring, within an image region, the measured spectrum at each of plural points within the biological tissue;

dividing the image region into a plurality of small blocks;

selecting one or more of peaks of the measured spectrum in each of the small blocks;

acquiring a classifier corresponding to each of the small blocks; and

acquiring the biological tissue image per each of the small blocks based on the selected one or more of peaks and the corresponding classifier.

2. The reconstruction method of the biological tissue image according to claim 1, wherein the classifier to be applied to an image region is generated from classification conditions acquired per each of a plurality of small blocks, by a regression analysis of the classification conditions, and then the biological tissue image in the image region is generated by applying the classifier to the measured spectrum.

3. The reconstruction method of the biological tissue image according to claim 1, wherein the biological tissue images acquired per each of a plurality of small blocks are integrated to generate the biological tissue image in the image region.

4. The reconstruction method of the biological tissue image according to claim 1, wherein the classifier is generated by applying a training data to the measured spectrum.

5. The reconstruction method of the biological tissue image according to claim 1, wherein, at the selecting one or more of peaks of the measured spectrum, the peak for use in the classification is determined based on Mahalanobis distance defined by a ratio of an inter-group dispersion to an intra-group dispersion.

6. The reconstruction method of the biological tissue image according to claim 1, wherein, the measured spectrum is any of a spectrum in an ultraviolet region, a visible region and an infrared region, a Raman spectroscopic spectrum, and a mass spectrum.

7. The reconstruction method of the biological tissue image according to claim 1, wherein, the biological tissue is a pathological tissue.

8. A biological tissue image acquiring apparatus, wherein a biological tissue image is reconstructed by the method according to claim 1.

9. An image display apparatus, wherein, at a pathological diagnosis, a lesion is displayed by the biological tissue image acquiring apparatus according to claim 7.

10. A reconstruction method of a biological tissue image using a signal processing apparatus based on a measured spectrum correlated with a substance distributed within a biological tissue comprising:

acquiring the measured spectrum within the biological tissue;

acquiring morphological information from distribution information of a peak component in the measured spectrum;

acquiring a classifier; and

applying the classifier to both of the measured spectrum of the biological tissue and of the morphological information acquired from the distribution information of the peak component in the measured spectrum, to acquire the biological tissue image.

11. The reconstruction method of the biological tissue image according to claim 10, wherein when the classifier is generated and the biological tissue image is reconstructed, both of the measured spectrum and a higher-order local autocorrelation which is acquired from distribution information thereof are used.