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

The Caption Guidance software uses artificial intelligence to guide users to get optimal cardiac ultrasound images in a point of care ultrasound (POCUS) setting.

The Caption Guidance software uses artificial intelligence to guide users to get optimal cardiac ultrasound images in a point of care ultrasound (POCUS) setting.

News | Artificial Intelligence | February 13, 2020
February 13, 2020 — The U.S.
Varian announced it has received FDA 510(k) clearance for its Ethos therapy, an Adaptive Intelligence solution. Ethos therapy is an artificial intelligence (AI)-driven holistic solution that provides an opportunity to transform cancer care.
News | Image Guided Radiation Therapy (IGRT) | February 11, 2020
February 11, 2020 — Varian announced it has received FDA 510(k) c
PaxeraHealth enterprise imaging, PACS, VNA solutions
News | Enterprise Imaging | February 11, 2020
February 11, 2020 — Enterprise Imaging developer PaxeraHealth
Mammograms of a 49-year-old woman with invasive lobular carcinoma on the right-side breast

Mammograms of a 49-year-old woman with invasive lobular carcinoma on the right-side breast. A small mass with micro-calcifications on the right-side breast was detected correctly by AI with an abnormality score of 96%. This case was recalled by 7 out of 14 radiologists (4 breast radiologists and 3 general radiologists) initially (without AI) and all 14 radiologists recalled this case correctly with the assistance of AI.

News | Artificial Intelligence | February 11, 2020
February 11, 2020 — A new study, published in...
An example of artificial intelligence (AI) being developed by Hitachi to automatically review and identify nodules on lung CT scans. This is part of a suite of AI apps Hitachi is developing. This example was being shown as a work in progress at RSNA 2019.

An example of artificial intelligence (AI) being developed by Hitachi to automatically review and identify nodules on lung CT scans. This is part of a suite of AI apps Hitachi is developing. This example was being shown as a work in progress at RSNA 2019. Photo by Dave Fornell.

Feature | Artificial Intelligence | February 07, 2020 | Sanjay Parekh, Ph.D. 
February 7, 2020 – At the 2019 Radiological Society...
Sponsored Content | Videos | Artificial Intelligence | February 07, 2020
At RSNA19, GE Healthcare introduced its...
Accuray TomoTherapy total body irradiation
News | Radiation Therapy | February 07, 2020
February 7, 2020 — Accuray Incorporated announced that two new studies demonstrate the benefits of the ...
Sponsored Content | Videos | Artificial Intelligence | February 06, 2020
ProFound AI is an FDA-cleared artificial intelligence (AI) system for reading 3-D breast tomosynthesis images.
Infervision’s deep learning medical imaging platform is helping screen patients for the coronavirus in China. It acts as second pair of eyes to identify multiple diseases from one set of chest scans. The artificial intelligence (AI) can provide a complete view of the nodule, including volume and density.

Infervision’s deep learning medical imaging platform is helping screen patients for the coronavirus in China. It acts as second pair of eyes to identify multiple diseases from one set of chest scans. The artificial intelligence (AI) can provide a complete view of the nodule, including volume and density.

News | Artificial Intelligence | February 04, 2020
February 4, 2020 — Since January 2020, the...
Feature | Breast Imaging | February 03, 2020 | By Barbara Smith
Women in the United States have a 1 in 8 (or about 13 percent) lifetime risk of being diagnosed with breast cancer du