AI-powered skin cancer detection tools not accurate for all patients

Imagine you’re getting out of the shower one morning and you notice a mole on your thigh that you’ve never seen before. It’s reddish brown, bumpy and surprisingly large. Is it a benign mole, or is it melanoma?

A slew of new artificial intelligence tools claim they can help you figure it out. Some are smartphone apps that anyone can download to scan their skin at home, while others are software programs designed to be used directly by clinicians in a doctor’s office.

As a computer engineer studying how tools like these perform in real-world clinical settings, I know that finding a way to accurately use AI in dermatology would be immensely valuable to patients around the world. It could offer broad access to medical expertise, providing lifesaving screenings to remote areas or underresourced communities where dermatologists are scarce.

But at the moment, these tools have a crucial shortcoming that researchers will have to resolve: They are increasingly accurate for people with light skin—but they have a massive blind spot when it comes to analyzing darker skin.

Skin-deep accuracy

The central myth of AI is that it functions objectively. In reality, an AI model is simply a pattern-matching engine. It learns to associate certain visual features with certain diseases.

But it can easily be thrown off by the background color of a person’s skin. In other words, the AI model doesn’t learn to look at the lesion itself. Instead, it picks up on the color of the surrounding skin as a clue. This means that the model’s ability to make accurate predictions essentially degrades to guesses based on skin color.

My colleagues and I found that the ability of these tools to accurately diagnose skin conditions dropped significantly when we simply darkened the surrounding skin on patients’ images. We trained an AI model on photographs of known skin conditions in light-skinned patients, then digitally manipulated the images to resemble darker skin tones. The clinical condition in the photo had not changed, but the AI’s ability to recognize it deteriorated sharply.