Granted Patent B2

US 12,283,045 · App. 18/007,862 · Granted Apr 22, 2025

Inventors: Alexandre Bouyssoux (Paris, FR); Riadh Fezzani (Montrouge, FR); Jean-Christophe Olivo-Marin (Sceaux, FR)

Assignees: VITADX INTERNATIONAL; INSTITUT PASTEUR; CENTRE NATIONAL DE LA RECHERCHE SCIENTIFIQUE

G06T7/0012G06T5/20G06T5/50G06V10/56H04N1/40012H04N23/676G06T2207/10024G06T2207/10056G06T2207/20032G06T2207/20064G06T2207/20221

Abstract

Claims (45)

1. A computer implemented method for generating a color-faithful extended depth-of-field (EDF) image from a color volume of a biological sample having dimension (N, M, L) and values I(n, m, l), the voxels (n, m, l) for a fixed l going from 1 to L being images acquired at different focal depths in a z-direction using a microscope, said method comprising the following steps:

a) receiving the color volume and generating a grayscale volume by applying an invertible color-to-grayscale transformation to said color volume;

b) applying a wavelet transform on each set of N×M voxels of the grayscale volume having a same l index and (n, m) index going from (1,1) to (N, M), so as to obtain a 3D wavelet coefficient matrix wherein the value of each voxel having a (n, m, l) index comprises a set of wavelet coefficients;

c) for each group of L voxels of the 3D wavelet coefficient matrix having a same (n, m) index and a l index going from 1 to L, selecting one set of wavelet coefficients using a predefined coefficient selection rule;

d) generating:

a 2D wavelet coefficient matrix WCM wherein the value WCM(n, m) of each pixel having a (n, m) index is the set of wavelet coefficients selected from the 3D wavelet coefficient matrix by the coefficient selection rule;

a 2D coefficient map CM, wherein the value CM(n, m) of each pixel having a (n, m) index is the l index of the voxel of the 3D wavelet coefficient matrix that comprises the set of wavelet coefficients selected by the coefficient selection rule;

e) applying an inverse transformation of the wavelet transform to the 2D wavelet coefficient matrix WCM so as to obtain a 2D grayscale EDF image;

f) generating a 2D color composite image CC, wherein the value CC(n, m) of each pixel having (n, m) index is the value I(n, m, l) of the voxel of the color volume ( 1 ) having a l index equal to the value CM(n, m) of the 2D coefficient map CM;

g) applying an inverse transformation of the invertible color-to-grayscale transformation to the 2D grayscale EDF image to obtain a 2D color EDF image;

h) converting the 2D color composite image CC and the 2D color EDF image into a color space comprising at least one chromaticity components and at least one intensity component; and

i) concatenating, the at least one chromaticity components of the 2D color composite image CC and the at least one intensity component of the 2D color EDF image, to obtain the color-faithful extended depth-of-field (EDF) image.

2. The method according to claim 1 , wherein in the selection step a first subset of wavelet coefficients is selected using a first predefined coefficient selection rule and a second subset of wavelet coefficients is selected using a second predefined coefficient selection rule; and wherein the step of generating a 2D wavelet coefficient matrix WCM and a 2D coefficient map CM comprises:

generating a first 2D coefficient map from the first subset of wavelet coefficients;

generating a second 2D coefficient map from the second subset of wavelet coefficients;

combining the first and the second 2D coefficient maps, so as to obtain one 2D coefficient map CM, and

generating a 2D wavelet coefficient matrix WCM wherein the value WCM(n, m) of each pixel is the value of the voxel of the 3D wavelet coefficient matrix having a (n, m) index and having a l index equal to the value CM(n, m) of the obtained 2D coefficient map CM.

3. The method according to claim 2 , wherein the step of combining the first and the second 2D coefficient maps comprises:

filtering the first 2D coefficient map and the second 2D coefficient map, preferentially using a median filter;

averaging the first and the second 2D coefficient maps; and

rounding the averaged 2D coefficient map so as to obtain one 2D coefficient map CM.

4. The method according to claim 1 , wherein the set of wavelet coefficients comprises at least four wavelet coefficients and the subset of wavelet coefficients comprises at least one wavelet coefficient.

5. The method according to claim 1 , wherein the color-faithful extended depth-of-field (EDF) image is converted to a different color space, preferentially the color space of the color volume ( 1 ).

6. The method according to claim 1 , wherein the invertible color-to-grayscale transformation is a principal component analysis (PCA).

7. The method according to claim 1 , wherein wavelet transform applied in the applying step is a stationary wavelet transform (SWT).

8. The method according to claim 1 , wherein the color volume is a biomedical image and the method further comprises a step of segmentation of the color-faithful extended depth-of-field (EDF) image.

9. A system for analysis of biological samples, said system comprising:

at least one input adapted to receive a color volume;

at least one processor configured to:

generate a grayscale volume by applying (M 10 ) an invertible color-to-grayscale transformation to said color volume;

apply a wavelet transform on each set of N×M voxels of the grayscale volume having a same l index and (n, m) index going from (1,1) to (N, M), so as to obtain a 3D wavelet coefficient matrix wherein the value of each voxel having a (n, m, l) index comprises a set of wavelet coefficients;

for each group of L voxels of the 3D wavelet coefficient matrix having a same (n, m) index and a l index going from 1 to L, select one set of wavelet coefficients using a predefined coefficient selection rule;

generate:

a 2D wavelet coefficient matrix WCM wherein the value WCM(n, m) of each pixel having a (n, m) index is the set of wavelet coefficients selected from the 3D wavelet coefficient matrix by the coefficient selection rule;

a 2D coefficient map CM, wherein the value CM(n, m) of each pixel having a (n, m) index is the l index of the voxel of the 3D wavelet coefficient matrix that comprises the set of wavelet coefficients selected by the coefficient selection rule;

apply an inverse transformation of the wavelet transform to the 2D wavelet coefficient matrix WCM so as to obtain a 2D grayscale EDF image;

generate (M 60 ) a 2D color composite image CC, wherein the value CC(n, m) of each pixel having (n, m) index is the value I(n, m, l) of the voxel of the color volume having a l index equal to the value CM(n, m) of the 2D coefficient map CM;

apply an inverse transformation of the invertible color-to-grayscale transformation to the 2D grayscale EDF image to obtain a 2D color EDF image;

convert the 2D color composite image CC and the 2D color EDF image into a color space comprising at least one chromaticity components and at least one intensity component; and

concatenate, the at least one chromaticity components of the 2D color composite image CC and the at least one intensity component of the 2D color EDF image, to obtain the color-faithful extended depth-of-field (EDF) image; and

at least one output adapted to provide said color-faithful extended depth-of-field (EDF) image.

10. The system according to claim 9 , wherein the biological sample is a urine sample and the system comprises an automated digital cytology system configured to acquire a color volume, the color volume comprising at least two 2D color images.

11. A bladder cancer detection apparatus according to claim 9 .

12. A computer program product for analysis of biological samples, the computer program product comprising instructions which, when the program is executed by a computer, cause the computer to carry out the steps of the method according to claim 1 .

13. A non-transitory computer-readable storage medium comprising instructions which, when the program is executed by a computer, cause the computer to carry out the steps of the method according to claim 1 .

Assignments (1)

Priority Claims (1)

Continuity (1)

References Cited (22)