News | Breast Biopsy Systems | January 17, 2019

Novel Technique May Significantly Reduce Breast Biopsies

Combining three-compartment breast imaging with radiomics improves positive predictive value and reduces biopsies with 97 percent sensitivity

Novel Technique May Significantly Reduce Breast Biopsies

January 17, 2019 — A novel technique that uses mammography to determine the biological tissue composition of a tumor could help reduce unnecessary breast biopsies, according to a new study appearing in the journal Radiology.1

Mammography has been effective at reducing deaths from breast cancer by detecting cancers in their earliest, most treatable stages. However, many women are called back for additional diagnostic imaging and, in many cases, biopsies, for abnormal findings that are ultimately proven benign. Research estimates this recall rate to be more than 10 percent in the United States.

“The callback rate with mammography is much higher than ideal,” said the study’s first author, Karen Drukker, Ph.D., research associate professor from the Department of Radiology at the University of Chicago. “There are costs and anxiety associated with recalls, and our goal is to reduce these costs but not miss anything that should be biopsied.”

Drukker and colleagues recently studied a new technique called three-compartment breast (3CB) imaging. John Shepherd, Ph.D., currently at the University of Hawaii in Honolulu, and his team developed 3CB while he was at the University of California in San Francisco. By measuring the water, lipid and protein tissue composition throughout the breast, 3CB might provide a biological signature for a tumor. For instance, more water in the tumor tissue might indicate angiogenesis, or the production of new blood vessels, an early sign of cancer development.

For the study, the researchers acquired dual-energy mammograms from 109 women with breast masses that were suspicious or highly suggestive of a malignancy — the types of lesions that typically would be biopsied — immediately prior to biopsy, and the ensuing biopsies showed 35 masses to be invasive cancers, while the remaining 74 were benign.

3CB images were derived from the dual-energy mammograms and analyzed along with mammography radiomics, a method that uses artificial intelligence algorithms to analyze features and patterns in images — some of which are difficult for human perception — developed by Maryellen L. Giger, Ph.D., and her team at the University of Chicago for use in computer-aided diagnosis on breast images.

The combination of 3CB image analysis and radiomics improved the positive predictive value, or the ability to predict cancer, in breast masses deemed suspicious by the breast radiologist. The combined method improved positive predictive value from 32 percent for visual interpretation alone to almost 50 percent, with an almost 36 percent reduction in biopsies. The 3CB-radiomics method missed one of the 35 cancers, for a 97 percent sensitivity rate.

“These results are very promising,” Drukker said. “Combining 3CB image analysis with mammography radiomics, the reduction in recalls was substantial.”

Drukker said the combined 3CB-radiomics approach has the potential to play an increasingly prominent role in breast cancer diagnosis and perhaps also screening. She noted that 3CB can easily be added to mammography without requiring extensive modifications of existing equipment.

“The patient is already getting the mammography, plus we get all this extra information with only a 10 percent additional dose of radiation,” she said.

This approach is still experimental at this stage, and further work is needed to make it available to patients. The researchers plan to study how the combined approach will help radiologists make their final determinations. They also want to study the approach using digital breast tomosynthesis, sometimes called 3-D mammography, which reduces the problem of overlapping breast tissue inherent to regular mammography. A tumor’s unique water-lipid-protein signature might be even clearer with tomosynthesis, Drukker said.

For more information: www.pubs.rsna.org/journal/radiology

 

Reference

1. Drukker K., Giger M.L., Joe B.N., et al. Combined Benefit of Quantitative Three-Compartment Breast Image Analysis and Mammography Radiomics in the Classification of Breast Masses in a Clinical Data Set. Radiology, Dec. 11, 2018. https://doi.org/10.1148/radiol.2018180608

Related Content

Amazon Comprehend Medical Brings Medical Language Processing to Healthcare
News | Artificial Intelligence | February 15, 2019
Amazon recently announced Amazon Comprehend Medical, a new HIPAA-eligible machine learning service that allows...
Fujifilm Exhibits Enterprise Imaging Solutions and Artificial Intelligence Initiative at HIMSS 2019
News | Enterprise Imaging | February 15, 2019
Fujifilm Medical Systems U.S.A. Inc. and Fujifilm SonoSite Inc. showcased their enterprise imaging and informatics...
IBM Watson Health Announces New AI Collaborations With Leading Medical Centers
News | Artificial Intelligence | February 14, 2019
IBM Watson Health announced plans to make a 10-year, $50 million investment in research collaborations with two...
Densitas Enters Partnership Agreement With TeleMammography Specialists
News | Breast Density | February 14, 2019
Breast imaging analytics company Densitas Inc. announced a new collaboration partnership with TeleMammography...
Sponsored Content | Webinar | Artificial Intelligence | February 14, 2019
This Nuance-sponsored ITN webinar will be held at 1 p.m. Eastern time, Tuesday, Feb. 26, 2019.
Siemens Healthineers Demonstrates Artificial Intelligence, Healthcare Digitalization at HIMSS19
News | Artificial Intelligence | February 13, 2019
February 13, 2019 — At the 2019 Healthcare Information and Management Systems Society (HIMSS) global conference and e
NVIDIA Explores Role of AI, Analytics and Virtualization in Healthcare at HIMSS19
News | Artificial Intelligence | February 13, 2019
Digital technology company NVIDIA will highlight its newest partnerships to advance the digital transformation of...
Survey Finds Personalized Patient Engagement Improving But Still Lacking
News | Patient Engagement | February 12, 2019
Software company Pegasystems Inc. announced new survey data revealing the positive impact of quality patient engagement...
Hologic Launches Unifi Analytics Business Intelligence Tool
Technology | Analytics Software | February 12, 2019
Hologic Inc. announced the U.S. launch of Unifi Analytics, a business intelligence tool that allows healthcare...
Micro-Ultrasound and Artificial Intelligence Combining to Detect Prostate Cancer
News | Prostate Cancer | February 12, 2019
Cambridge Consultants has partnered with Exact Imaging, makers of the ExactVu micro-ultrasound platform, as the two...