Granted Patent B2

US 12,505,543 · App. 18/314,482 · Granted Dec 23, 2025

Inventors: Alexandre Bouyssoux (Paris, FR); Riadh Fezzani (Montrouge, FR); Florent Couzinié-Devy (Montrouge, FR); Thibaut Troude (Paris, FR)

Assignees: VitaDX INTERNATIONAL; INSTITUT PASTEUR

G06T7/0012G06V20/698G06T2207/20081G06T2207/30024

Abstract

Claims (28)

1 . A device for analysis of a digital cytology slide of a biological sample, said biological sample having been previously collected from a subject suspected to be suffering from bladder cancer, said device comprising:

at least one input configured to receive at least one digital cytology slide obtained from a digitalization of at least one Whole Slide Image (WSI) of said biological sample;

at least one processor configured to:

detect cells of interest from said at least one digital cytology slide;

for each cell of interest, compute a features vector comprising at least one feature calculated on each cell of interest;

define a bag of k instances for each digital cytology slide; wherein the k instances are selected, based on at least one feature of said features vectors, as the cells of interest being the highest atypia cells among the cells of interest detected for each digital cytology slide;

calculate a global prediction score representative of a probability of presence of bladder cancer and/or a stage of bladder cancer for said subject; said global prediction score being obtained from a combination of single prediction scores obtained from at least two multi-instance learning methods configured to receive as input said at least one defined bag; and

at least one output configured to provide said global prediction score.

2 . The device according to claim 1 , wherein the at least one digitalized cytology slide is obtained from at least one WSI being colored with Papanicolaou.

3 . The device according to claim 1 , wherein the detection of the at least one cell of interest is performed using a trained Res-Net model configured to receive as input at least one pre-processed portion of the WSI, and provide as output an identification and a classification of objects present in said at least one pre-processed portion of the WSI as belonging or not to at least one class of cells of interest.

4 . The device according to claim 1 , wherein the at least one feature comprised in the features vector are selected among: Nuclear-Cytoplasm Ratio (NCR), Nucleus Intensity, Nucleus Intensity standard deviation, Haralick's Energy, Entropy, Homogeneity, convex-hull ratio and/or nucleus circularity.

5 . The device according to claim 4 , wherein the at least one feature is Nuclear-Cytoplasm Ratio (NCR) and wherein the selection of k cells of interest comprises:

sorting the cells of interest by decreasing Nuclear-Cytoplasm Ratio values; and

select the first k cells of interest, representative of high atypia basal urothelial cells.

6 . The device according to claim 1 , wherein the computation of the features vector comprises a preliminary segmentation of the detected at least one cell of interest and its/their nuclei using a convolutional machine learning model, for example a U-Net model.

7 . The device according to claim 6 , wherein said convolutional machine learning model had been previously trained using random data augmentation.

8 . The device according to claim 1 , wherein k is a predefined and constant natural number.

9 . The device according to claim 1 , wherein the at least two multi-instance learning models are an embedding-based multi-instance learning model using a pooling operator being a weighted-mean operator.

10 . The device according to claim 1 , wherein the at least two multi-instance learning model is trained using bootstrap aggregation.

11 . The device according to claim 1 , wherein the bladder cancer is an Urothelial Carcinomas.

12 . The device according to claim 1 , wherein the biological sample is a urine sample.

13 . A computer-implemented method for analysis of a digital cytology slide of a biological sample, said biological sample having been previously collected from a subject suspected to be suffering from bladder cancer, said method comprising:

receiving at least one digital cytology slide obtained from a digitalization of at least one Whole Slide Image (WSI) of said biological sample;

detecting cells of interest from said at least one digital cytology slide;

for each cell of interest, computing a features vector comprising at least one feature calculated on each cell of interest;

defining a bag of k instances for each digital cytology slide; wherein the k instances are selected, based on at least one feature of said features vectors, as the cells of interest being the highest atypia cells among the cells of interest detected for each digital cytology slide; and

calculating a global prediction score representative of a probability of presence of bladder cancer and/or a stage of bladder cancer for said subject; said global prediction score being obtained from a combination of single prediction scores obtained from at least two multi-instance learning methods configured to receive as input said at least one defined bag.

14 . A non-transitory computer-readable storage medium comprising instructions which, when executed by a computer, cause the computer to carry out the method for analysis of a digital cytology slide of claim 13 .

Assignments (2)

Continuity (1)

References Cited (13)