Industry News

New AI Method Predicts Breast Cancer Five Years in Advance

By Medimaging International staff writers
18 May 2019

Image: A new AI method for detecting breast cancer is expected to surpass existing methods that fall short in their predictions (Photo courtesy of MIT).Researchers from two major institutions have developed a new tool with advanced artificial intelligence (AI) methods to predict a woman’s future risk of breast cancer. The currently available models that use factors such as family history and genetics fall far short in predicting an individual woman’s likelihood of being diagnosed with breast cancer.

In some models, breast density—the amount of dense tissue compared to the amount of fatty tissue in the breast on a mammogram— has been added to improve risk assessment as it is an independent risk factor for breast cancer. Since it is based on subjective assessment that can vary across radiologists, deep learning, a subset of AI in which computers learn by example, has been studied as a way to standardize and automate these measurements.

Adam Yala, a Ph.D. candidate at the Massachusetts Institute of Technology (MIT), in collaboration with Regina Barzilay, Ph.D., an AI expert and professor at MIT, and Constance Lehman, M.D, Ph.D., chief of breast imaging at Massachusetts General Hospital and professor of radiology at Harvard Medical School, recently compared three different risk assessment approaches.

The first model relied on traditional risk factors, the second on deep learning that used the mammogram alone, and the third on a hybrid approach that incorporated both the mammogram and traditional risk factors into the deep learning model. The researchers used nearly 90,000 full-resolution screening mammograms from about 40,000 women to train, validate and test the deep learning model. They were able to obtain cancer outcomes through linkage to a regional tumor registry.

The deep learning models yielded substantially improved risk discrimination over the Tyrer-Cuzick model, a current clinical standard that uses breast density in factoring risk. When comparing the hybrid deep learning model against breast density, the researchers found that patients with non-dense breasts and model-assessed high risk had 3.9 times the cancer incidence of patients with dense breasts and model-assessed low risk. The advantages held across different subgroups of women.

“There’s much more information in a mammogram than just the four categories of breast density. By using the deep learning model, we learn subtle cues that are indicative of future cancer,” said Yala. “There’s a very large amount of information in a full-resolution mammogram that breast cancer risk models have not been able to use until recently. Using deep learning, we can learn to leverage that information directly from the data and create models that are significantly more accurate across diverse populations.”

“Unlike traditional models, our deep learning model performs equally well across diverse races, ages and family histories,” Dr. Barzilay said. “Until now, African-American women were at a distinct disadvantage in having accurate risk assessment of future breast cancer. Our AI model has changed that.”

“A missing element to support more effective, more personalized screening programs has been risk-assessment tools that are easy to implement and that work across the full diversity of women whom we serve,” Dr. Lehman said. “We are thrilled with our results and eager to work closely with our health care systems, our providers and, most importantly, our patients to incorporate this discovery into improved outcomes for all women.”

Related Links:
MIT



E-mail Print
FaceBook Twitter Google+ Linked in

Additional news

01 Jun 2019
Ultrasound Scanners Market Driven by AI, Cloud and Portable Systems
The global ultrasound market is expected to have achieved revenues of USD 6.12 billion from 115,592 units in 2018, driven by its offer of fusion imaging, wearable ultrasound, and Artificial Intelligence (AI)-powered systems in the established markets and contrast-enhanced ultrasound and elastography in the emerging markets.
Read More
01 Jun 2019
Global Diagnostic Imaging Market Projected to Reach USD 33 Billion by 2024
The global diagnostic imaging market is projected to grow at a CAGR of 5.5% from USD 25.7 billion in 2019 to USD 33.5 billion by 2024.
Read More
01 Jun 2019
World's First AI Solution for Flagging PE Receives FDA Approval
An artificial intelligence (AI) solution for flagging pulmonary embolism (PE) has been granted clearance by the US FDA.
Read More
01 Jun 2019
New VR Technology Puts Interventional Radiologists Inside 3D Blood Vessels
A team of researchers from the University of Washington has pioneered virtual reality (VR) technology that puts the operator inside 3D blood vessels.
Read More
01 Jun 2019
Google Shows AI Can Predict Lung Cancer from CT Scans
Google LLC has shared new research demonstrating how artificial intelligence (AI) can predict lung cancer to boost the chances of survival for people at risk across the world.
Read More
01 Jun 2019
Multi-Parameter Monitoring Market Driven by Home-Based Patients
The global multi-parameter patient monitoring market is projected to register a CAGR of 5% over 2019-2024, driven mainly by rapid growth of the aging population across the world that is directly contributing to the growth of these devices.
Read More
20 May 2019
Beckman Coulter Introduces New Total Laboratory Automation Solution
Beckman Coulter’s latest addition to its automation portfolio, the DxA 5000 total laboratory automation solution has achieved European CE Mark and China Food and Drug Administration approval.
Read More
20 May 2019
Ortho Clinical Diagnostics Presents Cardiac Advances at EuroMedLab 2019
Ortho Clinical Diagnostics sponsored an educational workshop on high-sensitivity troponin assays and presented five scientific posters at EuroMedLab 2019, the 23rd IFCC-EFLM European Congress of Clinical Chemistry and Laboratory Medicine, which took place from May 19-23, 2019, at the CCIB - Centre Convencions Internacional in Barcelona.
Read More
18 May 2019
AI More Accurate at Predicting Heart Attacks than Physicians
Researchers from the Turku PET Centre have developed an algorithm that “learned” how imaging data interacts by repeatedly analyzing 85 variables in 950 patients with known six-year outcomes.
Read More
Copyright © 2000-2019 TradeMed.com. All rights reserved. | Terms And Conditions