AI needs to be better at comparing present and past images to maximize its abilities and avert misdiagnoses of breast cancer and other conditions. Imaging expert Kyle Henson argues better outcomes may be achieved if AI interprets images in a more human way, while using its edge in spotting abnormalities faster and more accurately than people.

Based on how humans can tell the similarities and differences between certain objects, mathematical features and classifiers can be used in algorithms so that AI can come to the same types of conclusions when analyzing more complex problems. But what is the best way to use features and classifiers to minimize the risk of an algorithm returning false positives or false negatives?

Artificial intelligence based image interpretation often fails to live up to its billing in a clinical environment. When training any AI algorithm, the most crucial element is good data. Flawed, incomplete, or biased data will yield a poor outcome. A common problem is available datasets do not represent the population on which the AI is used, and even when it is, issues can still arise in the training process.