New AI method predicts future risk of breast cancer

Henrietta Strickland
May 10, 2019

One of the biggest challenges with breast cancer is the delayed diagnosis.

When comparing the hybrid deep mastering version towards breast density, the researchers determined that patients with non-dense breasts and version-assessed high hazard had three.9 instances the most cancers incidence of sufferers with dense breasts and model-assessed low chance.

Moreover, most breast cancer patients are still taken back by surprise by detection.

The researchers trained their deep learning model to induce the patterns directly from the data on over 90,000 mammograms.

"Unlike traditional models, our deep learning model performs equally well across diverse races, ages and family histories", said Regina Barzilay, Professor at MIT. "For example, a doctor might recommend supplemental MRI screening for women with high model-assessed risk". As their official release explains, the system has been trained on mammograms and known outcomes from over 60,000 patients to learn the subtle patterns in breast tissue. This proved that the AI model was a significant improvement from traditional techniques considering that the latter method could only accurately predict about 18 per cent of the same. These subtle differences will empower physicians to detect breast cancer as early as five years in advance.

"Since the 1960s radiologists have noticed that women have unique and widely variable patterns of breast tissue visible on the mammogram, " said Lehman.

Professor of radiology Constance Lehman from Harvard Medical School said in reference to this: "There's previously been minimal support in the medical community for screening strategies that are risk-based rather than age-based". Identifying patients at risk of developing breast cancer has therefore been a key focus for researchers looking to reduce the number of breast cancer-related deaths. "We can now leverage this detailed information to be more precise in our risk assessment at the individual woman level". There has been a disparity between black and white women when detecting breast cancer, as most of the breast cancer guidelines are based on white populations.

The deep learning fashions yielded substantially improved chance discrimination over the Tyrer-Cuzick model, a contemporary scientific fashionable that uses breast density in factoring danger. But some of these factors are less correlated with breast cancer than others, harming the models' accuracy. "We are eager to provide this power of information to all women undergoing screening mammography, not only by sharing their mammographic density but also their future risk of breast cancer".

Adam Yala who is the lead author of the paper said, "Our goal is to make these advancements a part of the standard of care".

Other reports by Click Lancashire

Discuss This Article