Cancer is a leading cause of death globally and one of the main challenges modern healthcare is facing.

To date, pathology is the sole medical specialty responsible for diagnosing and grading cancer, based on the morphology of various structures within the specimen. The diagnosis is traditionally performed by a pathologist observing the stained specimen on a glass slide under a microscope. Recent years have seen the rise of digital pathology, also referred to as virtual microscopy – the practice of pathology using scanned slides on a computer screen. While the utility of replacing a microscope with a screen is under much debate amongst pathologists, the value, for medical practice as well as for patients, of applying artificial intelligence on top of digitized scans is widely recognized.

The problem of diagnosing cancer is a classic one for Convolutional Neural Networks (CNNs), ideally suited for identifying subtle, complex patterns and classifying them with high accuracy. CNN-based.