Training end-to-end weakly supervised networks at the specimen (supra-image) level

A system for determining a presence of a pathology property in a supra-image, the system comprising:

• a processor;
• and
• a memory communicatively coupled to the processor, the memory storing instructions which, when executed on the processor, perform operations comprising:
• receiving an electronic evaluation supra-image, wherein the electronic evaluation supra-image comprises constituent images of a same specimen;
• providing the electronic evaluation supra-image to an electronic neural network that has been trained, using a training corpus of training supra-images and on an electronic computer, to determine the presence of the pathology property in a supra-image, each training supra-image comprising at least one image of a same specimen, each image corresponding to a plurality of components, wherein a respective component comprises a tile of an image or a feature vector representative of the tile, wherein each training supra-image of the training corpus is associated with a respective electronic label indicating whether the pathology property is present, wherein the training corpus is sufficient to train the electronic neural network to determine a presence of the pathology property;
• receiving from the electronic neural network an output indicative of whether the pathology property is present in the evaluation supra-image;
• and
• providing the output.