| CPC G06T 7/0012 (2013.01) [G06V 10/255 (2022.01); G06V 10/764 (2022.01); G06V 10/7747 (2022.01); G06V 10/82 (2022.01); G06V 20/698 (2022.01); G06T 2207/10056 (2013.01); G06T 2207/30024 (2013.01)] | 11 Claims |

|
1. A method of labeling an image of cells of a patient, in particular an immunocytochemistry image, as positive to a biomarker, comprising:
receiving a digital image of a stained immunocytochemistry biological sample of the patient,
performing a computerized classification of cells in the digital image, said classification comprising:
classifying pixels according to their color as positive,
classifying regions of the digital image as positive according to a number of neighboring pixels classified as positive,
applying a plurality of test functions on the positively classified region of the digital image to provide a test result representative of positivity to a respective test for the positively classified region, and
applying a scoring function combining the test results of the test functions for the positively classified region of the digital image, and
labeling the digital image by applying a trained neural network on at least one portion of the digital image which comprises a digital image of one cell classified as positive during the computerized classification.
|