Skin cancer is one another common type of cancer. Although, it is the uncontrol growth of abnormal skin cells. According to the estimate by World Health Organization (WHO), almost 65,161 people a year worldwide die due to this type of cancer. There are various types of treatment for patients with skin cancer. Almost New types of treatment are being tested in clinical trials.

Similarly, scientists from the Standford University have developed a new AI software to treat skin cancer. This new image scanning AI software differentiates dead skin cells from gentle ones as accurately as top dermatologists.

Scientists took the idea from Google algorithm. It is designed to differentiate between categories of objects based on images. It assembles a database of nearly 130,000 photos of skin disease.

According to scientists, “This potentially life-saving technology could soon be incorporated into a smartphone.”

Scientists make the algorithm in such way so that it combines visual processing with a type of AI called deep learning.

Senior author Sebastian Thrun said, “That’s when our thinking changed. This is not just a class project for students. This is an opportunity to do something great for humanity.”

By adjusting with the help of physicians, scientists created an app that performed like a panel of 21 board-certified dermatologists.

Dermatologists check signs of cancer according to their experience that relies on their training. If they spotted any injury, they generally took the help of a dermatoscopy process. And if there is still doubt, their final step involves taking a skin sample to test in a lab.

Co-author Brett Kuprel said, “There’s no huge dataset of skin cancer, so we had to make our own.”

The app challenged 21 dermatologists to identify cancer and gentle lesions in over 370 images. Scientists reported both performed equally well.

In this technology era, everyone has a supercomputer in their pockets. So, scientists decided to create a smartphone version.

Scientists said, “A smart phone app of this kind might enable effective, easy and low-cost medical assessments of more individuals than is possible with existing medical care systems.”