Google’s AI researchers have developed a deep learning tool that is capable of spotting advanced breast cancer when looking at slides with a much better accuracy than human pathologists.
The algorithm, called LYNA (Lymph Node Assistant) has been trained to recognize the particular characteristics of tumors by using two sets of pathological slides. This way, LYNA can spot metastasis in many different conditions to the point where it was successful in telling the difference between cancer and non-cancer slides, even when looking at extremely small metastases, 99% of the time.
In addition to accuracy, thanks to LYNA’s speed, the inspection time has been reduced to one single minute.
For now, LYNA has not yet been used in real-life clinical situations but the scientists believe that they can find further use in the AI and train it to search for other types of tumors as well.
When and if LYNA will become ready for practical use, the benefits of the AI would be immense – not only it would allow doctors more to time care for their patients but it would also lead to more reliable and swift diagnoses that could save hundreds if not thousands of lives.