An artificial intelligence tool called Mia, tested by the NHS, successfully detected signs of breast cancer in 11 women that doctors had missed.
The BBC he says:
The tool, called Mia, was piloted with its clinicians NHS and analyzed the mammograms of more than 10.000 women. Most of them did not have cancer, but she successfully identified all those with symptoms, as well as 11 more that doctors failed to detect.
In their early stages, cancers can be extremely small and difficult to detect. The BBC saw Mia in action at NHS Grampian, and there were tumors that were practically invisible to the human eye. But, depending on their type, they can grow and spread quickly.
Barbara was one of 11 patients whose cancer had been flagged by Mia but had not been detected on her scan when studied by hospital radiologists.
Because her 6mm tumor was caught so early, she had surgery and only needed five days of radiation therapy.
Breast cancer patients with tumors that are smaller than 15 mm when discovered have a 90% survival rate over the next five years.
Barbara reported that she was pleased that the treatment was much less invasive than that of her sister and mother, who had also previously battled the disease.
Without the help of the AI tool, Barbara's cancer would not have been detected until her next routine mammogram three years later. He had not shown any noticeable symptoms.
“These results are encouraging and help highlight the exciting possibilities of artificial intelligence, diagnostics. There is no doubt that true clinical radiologists are essential and irreplaceable, but a clinical radiologist using insights from validated AI tools will be a formidable force in patient care.” said Dr Katharine Halliday, President of the Royal College of Radiologists.
