Deep learning predicts woman's risk for breast cancer

November 30, 2020

OAK BROOK, Ill. - Researchers at Massachusetts General Hospital (MGH) have developed a deep learning model that identifies imaging biomarkers on screening mammograms to predict a patient's risk for developing breast cancer with greater accuracy than traditional risk assessment tools. Results of the study are being presented at the annual meeting of the Radiological Society of North America (RSNA).

"Traditional risk assessment models do not leverage the level of detail that is contained within a mammogram," said Leslie Lamb, M.D., M.Sc., breast radiologist at MGH. "Even the best existing traditional risk models may separate sub-groups of patients but are not as precise on the individual level."

Currently available risk assessment models incorporate only a small fraction of patient data such as family history, prior breast biopsies, and hormonal and reproductive history. Only one feature from the screening mammogram itself, breast density, is incorporated into traditional models.

"Why should we limit ourselves to only breast density when there is such rich digital data embedded in every woman's mammogram?" said senior author Constance D. Lehman, M.D., Ph.D., division chief of breast imaging at MGH. "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."

Dr. Lamb and a team of researchers developed the new deep learning algorithm to predict breast cancer risk using data from five MGH breast cancer screening sites. The model was developed on a population that included women with a personal history of breast cancer, implants or prior biopsies.

The study included 245,753 consecutive 2D digital bilateral screening mammograms performed in 80,818 patients between 2009 and 2016. From the total mammograms, 210,819 exams in 56,831 patients were used for training, 25,644 exams from 7,021 patients for testing, and 9,290 exams from 3,961 patients for validation.

Using statistical analysis, the researchers compared the accuracy of the deep learning image-only model to a commercially available risk assessment model (Tyrer-Cuzick version 8) in predicting future breast cancer within five years of the index mammogram. The deep learning model achieved a predictive rate of 0.71, significantly outperforming the traditional risk model, which achieved a rate of 0.61.

"Our deep learning model is able to translate the full diversity of subtle imaging biomarkers in the mammogram that can predict a woman's future risk for breast cancer," Dr. Lamb said.

Dr. Lamb said the new deep learning model has been externally validated in Sweden and Taiwan, and additional studies are planned for larger African-American and minority populations.

At MGH, deep learning risk information is available on reporting software when the radiologist reads a patient's screening mammogram.

"Traditional risk models can be time-consuming to acquire and rely on inconsistent or missing data," Dr. Lamb said. "A deep learning image-only risk model can provide increased access to more accurate, less costly risk assessment and help deliver on the promise of precision medicine."
-end-
Co-authors are Adam Yala, M.Eng., Peter Mikhael, B.S., and Regina Barzilay, Ph.D.

For more information and images, visit RSNA.org/press20. Press account required to view embargoed materials.

RSNA is an association of radiologists, radiation oncologists, medical physicists and related scientists promoting excellence in patient care and health care delivery through education, research and technologic innovation. The Society is based in Oak Brook, Illinois. (RSNA.org)

Editor's note:
The data in these releases may differ from those in the published abstract and those actually presented at the meeting, as researchers continue to update their data right up until the meeting. To ensure you are using the most up-to-date information, please call the RSNA media relations team at Newsroom at 1-630-590-7762.

For patient-friendly information on mammography, visit RadiologyInfo.org.

Radiological Society of North America

Related Breast Cancer Articles from Brightsurf:

Oncotarget: IGF2 expression in breast cancer tumors and in breast cancer cells
The Oncotarget authors propose that methylation of DVDMR represents a novel epigenetic biomarker that determines the levels of IGF2 protein expression in breast cancer.

Breast cancer: AI predicts which pre-malignant breast lesions will progress to advanced cancer
New research at Case Western Reserve University in Cleveland, Ohio, could help better determine which patients diagnosed with the pre-malignant breast cancer commonly as stage 0 are likely to progress to invasive breast cancer and therefore might benefit from additional therapy over and above surgery alone.

Partial breast irradiation effective treatment option for low-risk breast cancer
Partial breast irradiation produces similar long-term survival rates and risk for recurrence compared with whole breast irradiation for many women with low-risk, early stage breast cancer, according to new clinical data from a national clinical trial involving researchers from The Ohio State University Comprehensive Cancer Center - Arthur G.

Breast screening linked to 60 per cent lower risk of breast cancer death in first 10 years
Women who take part in breast screening have a significantly greater benefit from treatments than those who are not screened, according to a study of more than 50,000 women.

More clues revealed in link between normal breast changes and invasive breast cancer
A research team, led by investigators from Georgetown Lombardi Comprehensive Cancer Center, details how a natural and dramatic process -- changes in mammary glands to accommodate breastfeeding -- uses a molecular process believed to contribute to survival of pre-malignant breast cells.

Breast tissue tumor suppressor PTEN: A potential Achilles heel for breast cancer cells
A highly collaborative team of researchers at the Medical University of South Carolina and Ohio State University report in Nature Communications that they have identified a novel pathway for connective tissue PTEN in breast cancer cell response to radiotherapy.

Computers equal radiologists in assessing breast density and associated breast cancer risk
Automated breast-density evaluation was just as accurate in predicting women's risk of breast cancer, found and not found by mammography, as subjective evaluation done by radiologists, in a study led by researchers at UC San Francisco and Mayo Clinic.

Blood test can effectively rule out breast cancer, regardless of breast density
A new study published in PLOS ONE demonstrates that Videssa® Breast, a multi-protein biomarker blood test for breast cancer, is unaffected by breast density and can reliably rule out breast cancer in women with both dense and non-dense breast tissue.

Study shows influence of surgeons on likelihood of removal of healthy breast after breast cancer dia
Attending surgeons can have a strong influence on whether a patient undergoes contralateral prophylactic mastectomy after a diagnosis of breast cancer, according to a study published by JAMA Surgery.

Young breast cancer patients undergoing breast conserving surgery see improved prognosis
A new analysis indicates that breast cancer prognoses have improved over time in young women treated with breast conserving surgery.

Read More: Breast Cancer News and Breast Cancer Current Events
Brightsurf.com is a participant in the Amazon Services LLC Associates Program, an affiliate advertising program designed to provide a means for sites to earn advertising fees by advertising and linking to Amazon.com.