Feature detection based on neural networks

A computer program product comprising at least one computer readable storage medium that is not a transitory signal per se, the at least one computer readable storage medium having program instructions embodied therewith, the programs instructions configured, when executed by at least one computer, to cause the at least one computer to perform a method comprising:

• inputting, into a set of neural networks, a plurality of different images of a same region of interest in an object, wherein each image of the region has been captured under a different value of a variable condition;
• generating, by the set of neural networks, a classification for each image, wherein each classification includes a confidence score in a prediction of whether a visual feature is present in the region;
• ensembling the image classifications to generate a final classification for the region;
• computing, by applying a loss function, a loss based on comparing the final classification to a ground truth of whether the feature is present in the region;
• and
• adjusting parameters of the set of neural networks based on the computed loss.

A system comprising:

• at least one computer readable storage medium;
• and
• at least one processor in communication with the at least one computer readable storage medium, the at least one processor configured to obtain instructions from the at least one computer readable storage medium that cause the at least one processor to perform a method comprising:
• inputting, into a set of neural networks, a plurality of different images of a same region of interest in an object, wherein each image of the region has been captured under a different value of a variable condition;
• generating, by the set of neural networks, a classification for each image, wherein each classification includes a confidence score in a prediction of whether a visual feature is present in the region;
• ensembling the image classifications to generate a final classification for the region;
• computing, by applying a loss function, a loss based on comparing the final classification to a ground truth of whether the feature is present in the region;
• and
• adjusting parameters of the set of neural networks based on the computed loss.