{"id":159733,"date":"2025-01-18T18:09:27","date_gmt":"2025-01-18T16:09:27","guid":{"rendered":"https:\/\/serbiantimes.info\/en\/?p=159733"},"modified":"2025-01-18T18:09:28","modified_gmt":"2025-01-18T16:09:28","slug":"artificial-intelligence-saves-lives-new-ai-model-predicts-breast-cancer-risk-5-years-in-advance","status":"publish","type":"post","link":"https:\/\/serbiantimes.info\/en\/artificial-intelligence-saves-lives-new-ai-model-predicts-breast-cancer-risk-5-years-in-advance\/","title":{"rendered":"ARTIFICIAL INTELLIGENCE SAVES LIVES: New AI model predicts breast cancer risk 5 years in advance!"},"content":{"rendered":"\n

Researchers have developed a new, interpretable model for predicting five-year breast cancer risk based on mammograms, according to a recent study published in the journal Radiology<\/em>.<\/p>\n\n\n\n

One in eight women, approximately 13% of the female population in the U.S., develops invasive breast cancer during their lifetime, and one in 39 women (3%) dies from the disease, according to the American Cancer Society. Regular mammogram screenings can significantly reduce the risk of death from breast cancer. However, accurately predicting which women will develop breast cancer based solely on screening remains a challenge.<\/p>\n\n\n\n

Mirai<\/strong>, a state-of-the-art deep learning algorithm, has shown promise as a tool for breast cancer prediction. However, due to the limited understanding of its decision-making process, there is a risk that radiologists might over-rely on it, potentially leading to misdiagnoses.<\/p>\n\n\n\n

\u201cMirai is a black box\u2014a very large and complex neural network, similar in construction to ChatGPT\u2014and no one knows exactly how it makes its decisions,\u201d said Jon Donnelly, BS, lead author of the study and a PhD candidate in the Department of Computer Science at Duke University in Durham, NC. \u201cWe developed an interpretable artificial intelligence method that allows us to predict breast cancer from mammograms 1 to 5 years in advance. AsymMirai is much simpler and easier to understand than Mirai.\u201d<\/p>\n\n\n\n

For this study, Donnelly and his colleagues compared their newly developed deep learning model, called AsymMirai<\/strong>, with Mirai\u2019s predictions of breast cancer risk over 1 to 5 years. AsymMirai is built on the “front end” of Mirai’s deep learning framework, but the rest of the complex method has been replaced with an interpretable module: local bilateral dissimilarity.<\/p>\n\n\n\n

\u201cPreviously, differences between left and right breast tissue were used only to assist in detecting cancer, not in predicting it,\u201d Donnelly said. \u201cWe found that Mirai relies on comparisons between the left and right sides, which allowed us to design a much simpler network that also makes side-by-side comparisons.\u201d<\/p>\n\n\n\n

FOLLOW US ON FACEBOOK:<\/mark><\/h4>\n\n\n\t
\n\t\t
\n\t\t\t<\/iframe>\n\t\t<\/div>\n\t<\/figure>\n\n\t