It has the same level of accuracy as expert radiologists
Researchers at MIT and the Massachusetts General Hospital have developed a deep-learning system capable of identifying a breast cancer risk factor in mammograms with the same level of accuracy as expert radiologists.
One of the issues involved in developing the disease is dense breast tissue. Some 40% of US women have dense breast tissue, which alone increases the risk of breast cancer and can make mammogram screening more difficult.
According to MIT, the deep-learning model is the first of its kind used on actual patients. The technology may one day serve as a screening option, working to automatically review mammograms and analyse them for signs of breast cancer. The system was trained using real mammogram scans.
This technology was put to use at the Massachusetts General Hospital, where it first received mammogram scans before they were passed onto human radiologists. Overall, artificial intelligence and radiologists were in agreement about scan results 94% of the time.