Breast cancer is one of the leading causes of death among women. In the UK, over 55,000 people are diagnosed with the disease each year and about 1 in 8 women in the US tend to develop breast cancer in their lifetime.
Mammography or X-ray imaging of the breast is the most common way of screening breast cancer. Each year over 42 million exams are performed in the US and UK combined. But spotting and diagnosing breast cancer is tricky and still remains a challenge.
Google has been working with leading clinical research partners in the US and UK to see how AI can improve the detection of breast cancer. The company recently published its findings in Nature. The report says that the AI was able to spot breast cancer in de-identified screening mammograms with greater accuracy, fewer false positives, and fewer false negatives than other modes.
The finding is promising as it will set the stage for future applications. The model has the potential to support radiologists perform breast cancer screenings in a better way.
Google wrote on its blog: “We’re looking forward to working with our partners in the coming years to translate our machine learning research into tools that benefit clinicians and patients.”