News | Breast Imaging | November 07, 2016

Dutch Researchers Compare Consistency of Breast Density in Serial Screening Mammograms

Results show VolparaDensity grades provide more consistent readings

mammography, VolparaDensity grades, breast density, fibroglandular breast density, Radboud University Medical Center, Netherlands study

November 7, 2016 — Researchers from the Netherlands recently completed a study that explored the variation between radiologists when judging fibroglandular breast density visually on serially-acquired mammograms, and whether an automated density assessment would provide better consistency. Results of the study, “Consistency of breast density categories in serial screening mammograms: A comparison between automated and human assessment,” recently published in the Breast Journal, suggest that an automated computer measurement, VolparaDensity, provides better consistency than density readings performed visually by radiologists.

In the study, Katharina Holland and a team from the Radboud University Medical Center in The Netherlands, investigated the categorization of pairs of subsequent screening mammograms into density classes by human readers and by an automated breast density assessment system. One thousand mammograms belonging to 500 pairs of subsequent screening exams were randomly selected from the Dutch breast screening program. The serial mammograms, which had an average 30-month interval between them, were categorized into either two-category (“fatty” versus “dense”) or a four-category (BI-RADS 4th Edition: 1, 2, 3 or 4) density classes by four readers, including three specialized breast radiologists, and by using Volpara Density Grades (VDG), which are analogous to the BI-RADS (Breast Imaging-Reporting and Data System) density categories.

In addition, to better replicate clinical practice, a “group reading” was performed. In these group readings, each mammogram set was scored by randomly selecting one of the four radiologists’ scores and assigning it to the study; the intention here was to emulate the fact that serial mammograms are usually read by different radiologists.

Volpara identified a significantly higher percentage of women who did not exhibit a change between two-point density categories (90.4 percent) compared to the group reading of radiologists (86.8 percent). Volpara’s agreement to its own readings between serial exams was significantly higher than the group radiologist readings were to each other. Volpara maintained higher kappa agreement values on both two- and four- category scales, prompting researchers to suggest that Volpara produced more consistent density readings than the radiologists.

When women did exhibit a density change between screens, most of the instances of change were from the “dense” to “fatty” category (this happened in approximately 70 percent of cases of density change). Change in the other direction (“dense” to “fatty”) occurred as well, though less frequently — this could potentially be caused by use of hormone replacement therapy, weight loss or measurement error. There was no significant difference between the direction of density change between Volpara measurements and those of the radiologists.

Overall, the indication was that an automated computer measurement such as Volpara provides better consistency than density readings done by radiologists, when emulating clinical screening practice. “These results are particularly important given the recent work presented by Sprague et al. The use of an automated density measurement algorithm could prove desirable in screening practice — not only because of improved efficiency in terms of time and cost, but also because of enhanced reliability. Furthermore, the results indicate that Volpara could prove useful in temporal measurements of breast density,” noted Prof. Nico Karssemeijer, Radboud University Nijmegen. “These could be valuable for examining breast cancer risk, by looking at the occurrence of age-related involution or looking at response to adjuvant or neoadjuvant hormonal therapy, which can be reflected in breast density.”

For more information: www.onlinelibrary.wiley.com

Related Content

IBM collected a dataset of 52,936 images from 13,234 women who underwent at least one mammogram between 2013 and 2017.

IBM collected a dataset of 52,936 images from 13,234 women who underwent at least one mammogram between 2013 and 2017, and who had health records for at least one year prior to the mammogram. The algorithm was trained on 9,611 mammograms. Image courtesy of Radiology.

Feature | Artificial Intelligence | July 19, 2019 | Michal Chorev
Breast cancer is the global leading cause of cancer-related deaths in women, and the most commonly diagnosed cancer...
Paragon Biosciences Launches Qlarity Imaging to Advance FDA-cleared AI Breast Cancer Diagnosis System

Qlarity Imaging’s software is used to assist radiologists in the assessment and characterization of breast lesions. Imaging features are synthesized by an artificial intelligence algorithm into a single value, the QI score, which is analyzed relative to a database of reference abnormalities with known ground truth. Image courtesy of Business Wire.

Technology | Artificial Intelligence | July 18, 2019
Paragon Biosciences LLC announced the launch of its seventh portfolio company, Qlarity Imaging LLC, which was founded...
FDA Clears Koios DS Breast 2.0 AI-based Software
News | Ultrasound Women's Health | July 11, 2019
Koios Medical announced its second 510(k) clearance from the U.S. Food and Drug Administration (FDA).
SimonMed Imaging Implements ProFound AI for 3-D Tomosynthesis
News | Mammography | July 10, 2019
Arizona-based SimonMed Imaging announced their implementation of the first U.S. Food and Drug Administration (FDA)-...
Therapixel Appoints Matthieu Leclerc-Chalvet as CEO
News | Artificial Intelligence | July 03, 2019
Artificial intelligence (AI) breast cancer screening specialist Therapixel announced the appointment of Matthieu...
GE Healthcare showcases Senographe Pristina Serena featuring its add-on-biopsy kit at the Breast Imaging Symposium. Photo by Greg Freiherr

GE Healthcare showcases Senographe Pristina Serena featuring its add-on-biopsy kit at the Breast Imaging Symposium. Photo by Greg Freiherr

Feature | Breast Imaging | July 03, 2019 | By Greg Freiherr
Productivity and its enabler — efficiency — guided the display of products at the April...
Countless possibilities can impact the future of global healthcare and AI is the first step toward breakthrough that will change the landscape of personalized medicine
Feature | Women's Health | July 03, 2019 | By Samir Parikh
Contrary to what many people believe,...

Image courtesy of GE Healthcare

Feature | Radiology Business | July 03, 2019 | By Jeffrey Hoffmeister, M.D.
Burnout in the medical profession is not uncommon, particularly as clinicians have become more overwhelmed by growing
iCAD ProFound AI

Image courtesy of iCAD

News | Breast Imaging | June 25, 2019
Use of...