Close this search box.

Algorithm created by Stanford researchers to visually detect skin cancer

About 5.4 million people in the United States are diagnosed with skin cancer each year, making it the most common type of cancer. It is also the best treatable type if it is detected in the early stages. But not everyone has the same access to dermatologists. A group of Stanford researchers took this problem as an opportunity to create an algorithm that can visually detect and potentially diagnose skin cancer.

Let the algorithm figure it out

the researchers from Stanford’s Artificial Intelligence Laboratory published a study in the journal Nature, in which they explain how they fed an algorithm images as raw pixels and associated labels, which required very little processing. "We made a very powerful machine learning algorithm that learns from data, instead of writing into computer code exactly what to look for, you let the algorithm figure it out," said co-lead author Andre Esteva.

“There’s no huge dataset of skin cancer that we can just train our algorithms on, so we had to make our own,” Brett Kuprel, graduate student and co-lead author of the paper said. “We gathered images from the internet and worked with the medical school to create a nice taxonomy out of data that was very messy – the labels alone were in several languages, including German, Arabic and Latin.”

Head-to-head with 21 dermatologists

Then Stanford dermatologists and microbiology and immunology professor Helen M. Blau classified the images, resulting in 130,000 images of skin lesions representing over 2,000 different diseases. They trained a convolutional neural network, or CNN, to classify skin lesions using only pixels and disease labels as inputs, then put it head-to-head with 21 board-certified dermatologists.

The testing involved biopsy-proven clinical images of the most common and deadly types of skin cancers – malignant carcinomas and melanomas– provided by the University of Edinburgh and the International Skin Imaging Collaboration Project. Tasked with identifying benign lesions and the deadly lesions, the algorithm matched the performance of the dermatologists.

“We realized it was feasible, not just to do something well, but as well as a human dermatologist,” Sebastian Thrun, an adjunct professor in the Stanford Artificial Intelligence Laboratory, said to the Stanford news site. “That’s when our thinking changed. That’s when we said, ‘Look, this is not just a class project for students, this is an opportunity to do something great for humanity.’”

Strict validation

The algorithm only exists on a computer at this moment, but they intend to put it on smartphones to bring the ability to reliably diagnose skin cancer to a large population. For that they need of strict validation — apps that promise to detect skin cancer with the smartphone have already been the subject of FTC action — but the researchers are hopeful that the technology could be a real option for many without access to a dermatologist.

“My main Eureka moment was when I realized how ubiquitous smartphones will be,” said Esteva. “Everyone will have a supercomputer in their pockets with a number of sensors in it, including a camera. What if we could use it to visually screen for skin cancer? Or other ailments?”


ICT&health World Conference 2024

Experience the future of healthcare at the ICT&health World Conference from May 14th to 16th, 2024!
Secure your ticket now and immerse yourself in groundbreaking technologies and innovative solutions.
Engage with fellow experts and explore the power of global collaborations.

Share this article!

Read also
Navigating Digital Maturity in Healthcare IT
Digital maturity vs. Reality. How to rethink the IT staff role in a hospital
Online health care icon application on smart phone
End-users of mobile health apps expect far more than a good design
Mayo Clinic started with its innovations for its ten million patients and demonstrated that its model worked, and that data could be ethically and responsibly used to drive innovations.
John Halamka: 'Create the Fear of Missing Out'
Balancing regulatory compliance with seamless adoption, healthcare navigates the integration of AI solutions.
A guide to implementing AI in healthcare amid the EU AI Act
Futurist Amy Webb claims that wearables will evolve into "connectables"
Digital health solutions empower patients to better manage their health and integrate care into their daily lives.
How to improve Digital Patient Engagement to streamline workflows
For people with diabetes, inaccurate blood glucose measurements can lead to errors in diabetes management, including taking the wrong dose of insulin, sulfonylureas, or other medications that can rapidly lower blood glucose.
Smartwatches measuring glucose level: Harmful but easy to buy fake innovations
How to introduce innovation and AI in healthcare organizations if there is no business model for prevention and quality – Our interview with Professor Ran Balicer, the Chief Innovation Officer at Clalit Health Services and founding Director of Clalit Research Institute.
I see no legitimate rationale for delaying the digital transformation in healthcare
Pioneering Cardiac Arrest Detection for Enhanced Survival.
CardioWatch Revolutionizes Cardiac Arrest Detection
Dr. Oscar Díaz-Cambronero, Head of Perioperative Medicine Department at La Fe Hospital, spearheads innovative telemonitoring initiatives revolutionizing patient care
Smartwatches Saving Lives Inside and Outside the Hospital
Follow us