Breast cancer is a disease that affects far too many women around the world. More than 55,000 people in the UK are diagnosed with breast cancer each year and around 1 in 8 in the US.
Digital mammography, or X-ray imaging of the breast, is the most common method of detecting cancer, with more than 42 million examinations performed each year, in the US and UK combined. But despite the wide use of digital mammography, the early detection and diagnosis of breast cancer remains a challenge.
Reading these X-ray images is a difficult task, even for experts, and can often result in both false positives and false negatives. In turn, these inaccuracies can lead to delays in detection and treatment, unnecessary stress for patients, and increased workload for radiologists, who are already in short supply.
Over the years, various studies have been carried out to find new techniques that make them more efficient. Both the diagnosis, and some of the findings that have been published in Nature, show that an AI model detected breast cancer on de-identified screening mammograms (where identifiable information was removed) with greater accuracy, fewer false positives, and fewer false negatives, laying the groundwork for future applications, where the model could help radiologists perform breast cancer screening tests.
In collaboration with DeepMind, Cancer Research UK Imperial Centre, Northwestern University and Royal Surrey County Hospital, a model was run to see if artificial intelligence could help radiologists detect signs of breast cancer more accurately.
In making its decisions, the model received less information than the human experts, who, in accordance with usual practice, had access to patient records and previous mammograms, whereas the model only processed the most recent anonymous mammogram, without Additional Information. Despite working solely with these X-ray images, the model outperformed individual experts in accurately identifying breast cancer.
Looking towards future applications, there are some promising signs that the model could potentially increase the accuracy and efficiency of screening programs, as well as reduce waiting times and stress for patients.
Including artificial intelligence innovation is the latest line in the detection and diagnosis of breast cancer, not only within the field of radiology, but also pathology.
So the inclusion of technology and digital elements in clinical practice, diagnosis and in the promotion of our services will always be differentiating in the field of health.
Fountain:
Shetty, MSS (2020, January 1). Using AI to improve breast cancer screening. Google. https://blog.google/technology/health/improving-breast-cancer-screening/