Researchers at MIT University have made a deep-learning model that predicts the risk of breast cancer in women up to five years in advance. The model therefore looks at subtle tissue patterns in breasts that occur in the early phase of the disease.
To train the model, researchers used the mammograms of more than thirty thousand Massachusetts General Hospital patients whose medical consequences were known. As a result, the model learned to recognize the subtle tissue patterns that are not perceptible with the human and can indicate future cancer cells. By looking at those patterns in patients, the model can indicate whether a patient has an increased risk of breast cancer in the period of three to five years after mammography.
According to the researchers, the deeplearning model is more accurate than the Tyrer-Cuzick model, which is now used by doctors to predict the risk of breast cancer in women. This TC model looks at the breast tissue density and life characteristics of women. Of the sixty thousand patients, 269 are known to have or have had breast cancer. Of those 269, the new MIT model placed 31 percent in a high-risk group. The TC model is said to have placed only 18.2 percent of those women in a high-risk group.
An additional advantage of the model is that it works better for minorities. The existing models are based on characteristics such as age, hormonal factors, family histories and the tissue density of the breast. These models are mostly made on the basis of data from white women. This makes them less accurate for black women, for example. In America, this target group is 43 percent more likely to die from breast cancer than white women. Because the MIT model is based on the tissue patterns of more than thirty thousand patients, the skin color of a woman is not important.
Based on the findings of this model, personal screening agreements could be made with patients. For example, the doctor may recommend additional tests for a woman who, according to the model, has an increased risk of breast cancer. According to the researchers, there have been doctors who have been advocating individual screening appointments for some time, but this would not be possible because tests are not accurate enough for that. This model would be accurate enough for that, the researchers said.
The research is published under the title A Deep Learning Mammography-based Model for Improved Breast Cancer Risk Prediction.