The method of the invention is for automated, scalable, high-
throughput detection of objects in biological samples (1). The method comprises: taking several computer-readable images of biological samples, each of which containing multiple objects (S100); taking a detection coordination unit (5), which is used to identify the biological sample images one after the other and generate an identifier (S200) for each biological
sample image; taking a detection
management unit (6) transmitting the biological sample images with at least an identifier, where the detection
management unit (6) is creating a detection task associated with each biological
sample image and arrange the detection tasks in a
list one after the other (S300); taking at least one
detector unit (7) to process the biological sample images with at least one identifier, by detecting the objects on a single biological
sample image one at a time in order to create an object image for each detected object comprising at least the identifier of the given biological sample image and position coordinates (S400); taking a
learning management unit (8), transmitting the object images with at least identifiers and position coordinates to a
learning management unit, creating a learning task associated with each object image, organizing the learning tasks in a
list one after the other (S500); taking at least one teaching unit (9) which includes an initial learning model, the object images comprising at least an identifier and position coordinates, learning the encoding of a single object image one at a time to thereby create a current learning model by improving the initial learning model (S600); taking a learning model
database (12) which contains the initial learning model, transmitting the current learning model to a learning model
database by overwriting the initial learning model and storing the current learning model (S700); after step S400, taking a coding
management unit (10) transmitting the object images comprising at least an identifier and position coordinates, creating one coding task associated with each object image, organizing the coding tasks one after the other into a
list (S800); taking at least one encoding unit (11) using the initial or current learning model stored in the learning model
database,
processing the object images by encoding a single object image at the same time, in order to thereby create an
object code that is equipped with at least the identifier of the given object image (S900); taking an
object code database (13), transmitting the
object code with at least an identifier and store it in an object code database (S1000). A
system according to the invention is for implementing a method according to the invention.