For those who are suffering from skin cancer are going to get a good news, because scientists have created a revolutionary process to identify skin cancers. Each year over 5.4 million persons all over United states gets affected by skin cancer and it is really difficult to diagnose all of the people but, this new AI(artificial Intelligence) algorithm can easily differentiate skin cancers or tumors from moles or other birthmarks.

A research team from Stanford University have started working to develop the algorithm which will be as accurate as an experienced doctor. To test the algorithm the scanner was given nearly 130,000 images of more than 2,000 different diseases which include moles, rashes and several skin diseases and tumors. Their findings were first published in Nature Journal.

Dr. Andre Esteva one of the lead researchers of this project said in a statement,”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”. The algorithm analyzes every pixel of the given images and it was tested head-to-head against 21 experienced dermatologists. The test result showed 91 percent of accuracy.

According to The Verge, Stanford researchers borrowed an algorithm developed by Google named as,’Google for image classification’ to teach their AI how to identify skin cancer. Google use their algorithm to differentiate Cats and Dogs from an image. Researchers modified the algorithm to spot several types cancerous tumors which also includes the most common type of skin cancer: Carcinoma and most deadly Melanoma.

It’s been recorded that, one among 20 skin cancers are melanoma but three fourth of melanoma patients usually die. So it is more important to detect cancer in its early stage, this system will help doctors and patients to detect cancer at the very early stage at a very minimal expense. Patients don’t have to go through the complicated and expensive process of Biopsies.

However, Stanford team also explained that developing this kind of program is not a replacement of human dermatologists. It is just developed to offer people an inexpensive way to screen their problem so that they can get enough time to treat their problems. Now, researchers are also planning to make a smartphone app using the same algorithm which will turn any smartphone into a cancer scanner.

Related