Researchers believe a computer programme that can identify breast cancer from routine scans with greater accuracy than human experts will be a vital breakthrough.
The study’s authors, including several representatives from Google Health, trained their AI algorithm with mammograms from more than 25,000 patients in the United Kingdom and more than 3,000 women in the United States.
To compare the algorithm’s performance with human specialists, the team asked a separate, unaffiliated research organization to conduct a reader study involving six MQSA-compliant radiologists. The study included 500 mammograms selected at random from the US dataset and radiologists used BI-RADS scores to grade each image.
Breast cancer is one of the most common cancers in women, with more than two million new diagnoses last year alone. Regular screening is vital in detecting the earliest signs of the disease in patients who show no obvious symptoms.
In Britain, women over 50 are advised to get a mammogram every three years, the results of which are analysed by two independent experts. However, interpreting the scans leaves room for error, and a small percentage of all mammograms either return a false positive - misdiagnosing a healthy patient as having cancer - missing the disease as it spreads.
“False positives can lead to patient anxiety, unnecessary follow-up and invasive diagnostic procedures."
The algorithm led to an absolute reduction in false-positive findings of 5.7% for the US dataset and 1.2% for the UK dataset. It also reduced the percentage of missed diagnoses by 9.4 percent among US patients and by 2.7 percent in Britain.
The applications for AI in diagnoses are seemingly endless. It feels like every week there are some advancements in the field. Although up until now, many of these projects have barely made it out of the pilot stage. In 2020, many experts are now tipping these technologies to become more widespread in the healthcare industry.