HealthDay operates under the strictest editorial standards. Our syndicated news content is completely independent of any financial interests, is based solely on industry-respected sources and the latest scientific research, and is carefully fact-checked by a team of industry experts to ensure accuracy.
- All articles are edited and checked for factual accuracy by our Editorial Team prior to being published.
- Unless otherwise noted, all articles focusing on new research are based on studies published in peer-reviewed journals or issued from independent and respected medical associations, academic groups and governmental organizations.
- Each article includes a link or reference to the original source.
- Any known potential conflicts of interest associated with a study or source are made clear to the reader.
Please see our Editorial and Fact-Checking Policy for more detail.Editorial and Fact-Checking Policy
HealthDay Editorial Commitment
HeathDay is committed to maintaining the highest possible levels of impartial editorial standards in the content that we present on our website. All of our articles are chosen independent of any financial interests. Editors and writers make all efforts to clarify any financial ties behind the studies on which we report.
THURSDAY, Dec. 3, 2020 (HealthDay News) -- A deep learning (DL) model using screening mammography imaging biomarkers can improve accuracy for predicting future breast cancer risk, according to a study presented at the annual meeting of the Radiological Society of North America, held virtually from Nov. 29 to Dec. 5.
Leslie Lamb, M.D., from Massachusetts General Hospital in Boston, and colleagues designed a new DL algorithm to predict a patient's risk for developing breast cancer using mammographic image biomarkers. The model was developed using consecutive bilateral screening mammograms from 80,818 patients between 2009 and 2016. Overall, 210,819 examinations in 56,831 patients, 25,644 in 7,021 patients, and 9,290 in 3,961 patients were used for the training, validation, and testing sets, respectively.
The researchers found that in the test set, 70.5 and 29.5 percent of the patients were postmenopausal and premenopausal, respectively; 55.7 and 44.3 percent had nondense and dense breasts, respectively. The area under the receiver operating characteristic curve was 0.71 for the DL model compared with 0.61 for the Tyrer-Cuzick (version 8) model.
"Why should we limit ourselves to only breast density when there is such rich digital data embedded in every woman's mammogram?" a coauthor said in a statement. "Every woman's mammogram is unique to her just like her thumbprint. It contains imaging biomarkers that are highly predictive of future cancer risk, but until we had the tools of deep learning, we were not able to extract this information to improve patient care."
This story may be outdated. We suggest some alternatives.
The content contained in this article is over two years old. As such our recommendation is that you reference the articles below for the latest updates on this topic. This article has been left on our site as a matter of historic record. Please contact us at email@example.com with any questions.
Updated on May 25, 2022