Breast cancer is a major health risk among women worldover. One in eight cases of breast cancer cases turn invasive and 1 in 39 women die from the disease. Although medical science has come a long way in saving lives, early detection of breast cancer remains the key.
Industrialist Anand Mahindra highlighted a post on X which spoke of an Artificial Intelligence which helped in early detection of breast cancer by 5 years.
The study on the new AI system, called AsymMirai, has been published in scientific journal Radiology.
As reported by Medscape, the AI simplified previous models of breast cancer detection by observing comparative changes in left and right breasts. The study has reportedly been carried out by researchers at Duke University along with others.
" With traditional AI, you ask it a question and it spits out an answer, but no one really knows how it makes its decisions. It's a black box," said Jon Donnelly, who is a PhD student in the Department of Computer Science at Duke University. Donelly is also the first author of the research paper.
"With our approach, people know how the algorithm comes up with its output so they can fact-check it and trust it," he said.
Medscape report says that AsymMirai was able to detect twice as many cases of future breast cancer than conventionally used risk calculator Tyrer-Cuzick. The results were also reliable among patients belonging to minority communities. Exclusion, even inadvertently, of minority communities during scientific and medical studies lead to errors in defining various yardsticks.
"We found that we can, with surprisingly high accuracy, predict whether a woman will develop cancer in the next 1-5 years based solely on localized differences between her left and right breast tissue," said Donelly as quoted by Medscape in its report.
(With inputs from agencies)
