Stanford University researchers said artificial intelligence can detect the skin cancer same as like the dermatologists. Victims can receive diagnosis through a Smartphone.
The researchers have made a database of nearly 130,000 skin disease images and trained their algorithm to visually diagnose potential cancer. From the first test, it is showing good accuracy.
They asked 21 dermatologists to diagnosis different skin diseases as well as they are also checking with AI. The AI shows the same performance same as like as the dermatologists.
Sebastian Thrun, an artificial intelligence professor in Stanford said “We realized it was feasible, not just to do something well, but as well as a human dermatologist.”He also said this is not a class project for students, and this is the opportunity to do something great for human race.
Ever year in the United States, doctors are finding 5.4 million new skin diseases cases. In the earlier stages of cancer the melanoma is about 97%, and it will gradually fall to 14% in last stages. In skin cancer, early detection is crucial. Giving treatment at early stages can reduce the cancer.
In diagnosing skin cancer, first of all, dermatologists look at the suspicious part through dermatoscopy, which is a handheld microscope, it provides low-level magnification of the skin.
This deep learning algorithm also follows the same process like dermatologist. This deep learning algorithm has great history, and recently only the scientists are using this algorithm and seeing great success.
Andre Esteva, the co-lead author of the paper, said we made a very powerful machine learning algorithm, which learns from given data. He also said, “Instead of writing into computer code exactly what to look for, you let the algorithm figure it out.”
This algorithm scans each image as the raw pixel with an associated disease label. When compared to other algorithms, this one is little processing because it has to sort the data before classification.
Due to this artificial intelligence, our Smartphone will become the doctor to detect the disease.