US 12,292,370 B2
Systematic characterization of objects in a biological sample
Thibaut Troude, Paris (FR); Florent Couzinie-Devy, Montrouge (FR); Riadh Fezzani, Montrouge (FR); Marin Scalbert, Paris (FR); and Shuxian Li, Antony (FR)
Assigned to VITADX INTERNATIONAL, Rennes (FR)
Appl. No. 17/795,755
Filed by VITADX INTERNATIONAL, Rennes (FR)
PCT Filed Jan. 29, 2021, PCT No. PCT/EP2021/052105
§ 371(c)(1), (2) Date Jul. 27, 2022,
PCT Pub. No. WO2021/152089, PCT Pub. Date Aug. 5, 2021.
Claims priority of application No. 20305082 (EP), filed on Jan. 30, 2020.
Prior Publication US 2023/0066976 A1, Mar. 2, 2023
Int. Cl. G01N 15/1433 (2024.01); G06T 7/00 (2017.01); G06V 10/44 (2022.01); G06V 20/69 (2022.01); G01N 15/10 (2006.01); G01N 15/14 (2006.01)
CPC G01N 15/1433 (2024.01) [G06T 7/0012 (2013.01); G06V 10/457 (2022.01); G06V 20/698 (2022.01); G01N 2015/1006 (2013.01); G01N 2015/1486 (2013.01); G06T 2207/10056 (2013.01); G06T 2207/20081 (2013.01)] 18 Claims
OG exemplary drawing
 
1. A computer-implemented method for classifying and counting objects recoverable from a urine sample processed onto a slide, said method comprising:
receiving at least one digitalized image of the whole slide;
detecting connected components by segmentation of the image of the whole slide;
classifying the detected connected components into countable connected components and uncountable connected components using a classifier;
for the countable connected components:
inputting each countable connected component into an object detection model so as to detect objects and obtain an output comprising a bounding box and an associated class for each detected object;
counting the bounding boxes associated to each class obtaining a number of objects for each class;
for the uncountable components:
inputting each uncountable connected component into a semantic segmentation model and obtaining as output a segmentation mask in which all pixels are classified into one class among multiple predefined available classes;
for each class, counting the number of objects as a ratio between a total pixel's area of the class, obtained as a number of pixels of the segmentation mask associate to said class, and an average area of the object of said class;
summing up the number of objects for each class obtained from the semantic segmentation model and the object detection model;
outputting the number of objects for each class;
wherein said classes for the semantic segmentation model and the object detection model are the same.