Method for identifying analytes in an image series

A method for training a machine learning system using a candidate extraction model for extracting candidate signal series from an image series, the image series being generated by marking analytes with markers in multiple coloring rounds and detecting the markers using a camera, the camera recording an image of the image series in each coloring round, the markers being selected in such a way that image signals of an analyte in an image area over the image series include colored signals and uncolored signals, comprising

• providing an annotated data set, and
• optimizing an objective function by adapting the model parameters of the candidate extraction model, the objective function detecting a difference between a result output that is output by the candidate extraction model and a target output, wherein
• the annotated data set includes at least one signal series of an image area in which the image signals of an analyte are captured, and includes a signal series of an image area in which the image signals of a background are captured, and for each of the signal series includes a target output that indicates whether or not the signal series includes image signals of an analyte.

A method for training a machine learning system, using a registration model for determining registration information from images of an image series, the registration information including at least translation information and rotation information, comprising:

• providing an annotated data set, and
• optimizing an objective function by adapting the model parameters of the registration model, the objective function detecting a difference between a result registration output that is output by the registration model, and a target registration output, wherein
• the annotated data set includes at least two images with registration structures, the registration structures being displaced and/or tilted relative to one another, and it being possible to register the registration structures with one another in the images, based on the target registration output.

A method for identifying analytes in an image series, the image series being generated by marking analytes with markers in multiple coloring rounds and detecting the markers using a camera, the camera recording an image of the image series in each coloring round, the markers being selected in such a way that image signals of an analyte in an image area over the image series include colored signals and uncolored signals, comprising:

• extracting multiple signal series of an image area of the image series in each case,
• filtering out candidate signal series from the extracted signal series, a ratio of at least one of the colored and/or uncolored signals of a candidate signal series to at least one other of the colored and/or uncolored signals of the particular signal series being a characteristic ratio, and/or a candidate signal series having a characteristic signature that has the at least one characteristic ratio, so that when the signal series has at least one characteristic ratio and/or the characteristic signature, the signal series is assessed as a candidate signal series, and
• assigning the candidate signal series to a type of analyte or to the background.

A method for determining registration information of images of an image series by use of a registration model, the registration information including at least translation information and rotation information, the registration model being trained to recognize registration structures in images, and the registration structures being structures that occur in images, and to which a location may be unambiguously assigned, comprising:

• inputting the image series into the registration model,
• determining the registration information.