Scientists at the University of Michigan (U-M) used machine learning to predict which early stage breast cancers are likely to spread, according to a press release from the university.
About one in five new breast cancers are caught at their earliest stages, before they have spread from milk ducts into the surrounding breast tissue. But what doctors can’t currently predict with high confidence is which of these cancers – known as ductal carcinoma in situ (DCIS) or stage 0 breast cancer – are likely to recur and spread after surgery, and which ones surgery is likely to cure.
Researchers at the U-M Rogel Cancer Center have developed a new diagnostic approach using artificial intelligence that aims to do exactly that, according to findings published in the American Journal of Physiology-Cell Physiology.
The researchers started with samples from 70 patients with stage 0 breast cancer who had undergone a mastectomy, and for whom there were at least 10 additional years of medical records available. Twenty of the 70 patients experienced a recurrence of their cancer, while 50 did not. These tissue samples were stained so that the proteins of interest would fluoresce under the microscope. Then, using a computer vision application, the scientists created a library of microscope images that were associated either with aggressive or non-aggressive DCIS, based on what had happened to that patient.
Next the researchers showed the program roughly 100 micrographs that it had not seen before – known as holdout images – to see how well it could accurately predict whether that patient’s cancer was likely to recur. With refinements over time, the program is now able to correctly identify aggressive and non-aggressive disease 96 percent of the time, the team reported. The program also reported false positives in 4 percent of cases — that is, it identified aggressive disease in patients who did not experience recurrence.
