Method for analyzing biological specimens by spectral imaging

Patent metadata

Field	Value
Publication number	US-10067051-B2
Application number	US-201514606812-A
Country	US
Kind code	B2
Filing date	Jan 27, 2015
Priority date	Jun 25, 2010
Publication date	Sep 4, 2018
Grant date	Sep 4, 2018

Abstract

A method for analyzing biological specimens by spectral imaging to provide a medical diagnosis includes obtaining spectral and visual images of biological specimens and registering the images to detect cell abnormalities, pre-cancerous cells, and cancerous cells. This method eliminates the bias and unreliability of diagnoses that is inherent in standard histopathological and other spectral methods. In addition, a method for correcting confounding spectral contributions that are frequently observed in microscopically acquired infrared spectra of cells and tissue includes performing a phase correction on the spectral data. This phase correction method may be used to correct various types of absorption spectra that are contaminated by reflective components.

First claim

What is claimed is:

1. A method executed by a system for analyzing biological specimens by spectral imaging, comprising:
acquiring a spectral image of the biological specimen;
acquiring a visual image of the biological specimen; and
registering the visual image and spectral image to generate a registered image,
wherein acquiring the spectral image of the biological specimen further comprises:
acquiring spectral data from the biological specimen;
performing pre-processing on the spectral data by selecting a spectral range, computing a second derivative, performing reverse Fourier transformation, performing zero-filling and reverse Fourier transformation, and performing a phase correction;
performing multivariate analysis on the spectral data; and
preparing, by the system, a grayscale or pseudo-color spectral image based on the multivariate analysis of the spectral data.

2. The method of claim 1 , further comprising:
storing the registered image.

3. The method of claim 2 , wherein registering the visual image and spectral image comprises:
aligning corresponding control points on the spectral image and visual image.

4. The method of claim 1 , wherein the biological specimen comprises cells or tissue.

5. The method of claim 1 , wherein acquiring spectral data from the biological specimen comprises:
performing infrared spectroscopy, Raman spectroscopy, visible, terahertz, or fluorescence spectroscopy on the biological specimen.

6. The method of claim 1 , wherein multivariate analysis of the spectral data comprises:
performing unsupervised analysis.

7. The method of claim 6 , wherein performing unsupervised analysis comprises:
performing hierarchical cluster analysis (HCA) or principal component analysis (PCA).

8. The method of claim 1 , wherein multivariate analysis on the spectral data comprises:
performing analysis of the data via a supervised algorithm.

9. The method of claim 8 , wherein performing analysis of the data via a supervised algorithm comprises:
performing analysis of the data via a machine learning algorithm selected from the group consisting of artificial neural networks (ANNs), hierarchical artificial neural networks (hANN), support vector machines (SVM), and random forest algorithms.

10. The method of claim 1 , wherein acquiring a visual image of the biological specimen comprises:
obtaining a digital image of the biological specimen.

11. The method of claim 1 , further comprising:
providing one or more of a diagnostic decision and prognostic decision.

12. The method of claim 11 , further comprising:
obtaining a selected region of a spectral image;
comparing data for the selected region to data in a repository that is associated with a disease or condition;
determining any correlation between the repository data and the data for the selected region; and
outputting a classification of the selected region based on the determination, wherein the classification is used for one or more of the diagnostic decisions and prognostic decisions.

13. The method of claim 12 ,
wherein the repository data is obtained for a plurality of images, and
wherein each of the plurality of images in the repository is associated with a disease or condition.

14. A system for analyzing biological specimens by spectral imaging, comprising:
a memory in communication with a processor, wherein the memory and the processor are cooperatively configured to:
acquire a spectral image of the biological specimen;
acquire a visual image of the biological specimen; and
register the visual image and spectral image to generate a registered image,
wherein acquiring the spectral image of the biological specimen further comprises:
acquiring spectral data from the biological specimen;
performing pre-processing on the spectral data by selecting a spectral range, computing a second derivative, performing reverse Fourier transformation, performing zero-filling and reverse Fourier transformation, and performing a phase correction;
performing multivariate analysis on the spectral data; and
preparing a grayscale or pseudo-color spectral image based on the multivariate analysis of the spectral data.

15. The system of claim 14 , further comprising:
storing the registered image.

16. The system of claim 15 , wherein registering the visual image and spectral image further comprises:
aligning corresponding control points on the spectral image and visual image.

17. The system of claim 14 , wherein the biological specimen comprises cells or tissue.

18. The system of claim 14 , wherein acquiring spectral data from the biological specimen comprises:
performing infrared spectroscopy, Raman spectroscopy, visible, terahertz, or fluorescence spectroscopy on the biological specimen.

19. The system of claim 14 , wherein multivariate analysis of the spectral data comprises:
performing unsupervised analysis.

20. The system of claim 19 , wherein performing unsupervised analysis comprises:
performing hierarchical cluster analysis (HCA) or principal component analysis (PCA).

21. The system of claim 14 , wherein multivariate analysis on the spectral data comprises:
performing analysis of the data via a supervised algorithm.

22. The system of claim 21 , wherein performing analysis of the data via a supervised algorithm further comprises:
performing analysis of the data via a machine learning algorithm selected from the group consisting of artificial neural networks (ANNs), hierarchical artificial neural networks (hANN), support vector machines (SVM), and random forest algorithms.

23. The system of claim 14 , wherein acquiring a visual image of the biological specimen comprises:
obtaining a digital image of the biological specimen.

24. The system of claim 14 , further comprises:
obtaining a selected region of a spectral image;
comparing data for the selected region to data in a repository that is associated with a disease or condition;
determining any correlation between the repository data and the data for the selected region; and
outputting a classification of the selected region based on the determination.

25. The system of claim 24 , wherein the classification is used for one or more of diagnostic decisions and prognostic decisions.

26. The system of claim 24 ,
wherein the repository data is obtained for a plurality of images, and
wherein each of the plurality of images in the repository is associated with a disease or condition.

27. A non-transitory computer-readable medium storing instructions that when executed by a computer device, cause the computer device to:
acquire a spectral image of the biological specimen;
acquire a visual image of the biological specimen; and
register the visual image and spectral image to generate a registered image,
wherein acquiring the spectral image of the biological specimen further comprises:
acquiring spectral data from the biological specimen;
performing pre-processing on the spectral data by selecting a spectral range, computing a second derivative, performing reverse Fourier transformation, performing zero-filling and reverse Fourier transformation, and performing a phase correction;
performing multivariate analysis on the spectral data; and
preparing a grayscale or pseudo-color spectral image based on the multivariate analysis of the spectral data.

Assignees

• Cireca Theranostics Llc
• Univ Northeastern

Inventors

• Diem Max
• Bird Benjamin
• Miljkovic Milos
• Remiszewski Stanley H
• Thompson Clay M

Classifications

• G01N21/31 Primary

  Investigating relative effect of material at wavelengths characteristic of specific elements or molecules, e.g. atomic absorption spectrometry {(G01N21/72 takes precedence)} · CPC title

• G16Z99/00 Primary

  Subject matter not provided for in other main groups of this subclass · CPC title

• G06V10/58

  relating to hyperspectral data · CPC title

• G01N2201/1296

  using neural networks · CPC title

• G01N21/552

  Attenuated total reflection · CPC title