News | Breast Biopsy Systems | May 08, 2018

New Analytics Approach Offers Potential of Reducing Unnecessary Breast Biopsies

Study defines advanced statistical methods that can be used with diagnostic imaging output to downgrade breast mass risk classification

New Analytics Approach Offers Potential of Reducing Unnecessary Breast Biopsies

May 8, 2018 — The American Journal of Roentgenology recently published findings on statistical methods for downgrading the risk classification of breast masses to reduce the need for unnecessary breast biopsies. Clinicians from Seno Medical and medical center collaborators from The University of Texas co-authored the report.1  

"The perceived risk of missing a breast cancer diagnosis with breast imaging studies is much higher than the risk of a false-positive diagnosis, leading to breast imagers recommending a breast biopsy whenever the risk of cancer is greater than 2 percent. Sometimes ancillary diagnostic breast imaging studies are performed to reduce risk to less than 2 percent, but it is difficult to know exactly how much risks are reduced even after a negative ancillary diagnostic imaging examination," said Thomas Stavros, M.D., chief medical officer of Seno Medical and a co-author of the report. "However, the use of the Negative Likelihood Ratio (NLR) along with BI-RADS [Breast Imaging-Reporting and Data System] 4 subcategories can help to reduce the number of false-positives without experiencing excessive negative results that would lead to cancer going undiagnosed."

The report explores the use of a statistical calculation known as the Negative Likelihood Ratio (NLR). It shows how NLR can be calculated from a diagnostic test's sensitivity and specificity and also show the NLRs of some currently available diagnostic imaging modalities. It outlines how the BI-RADS 4A sub-category has low enough and narrow enough range of pre-test probabilities (see Table 1) to allow downgrading to a post-test probability of 2 percent or less after a negative diagnostic imaging test with an adequately low NLR.

 

FINAL ASSESSMENT CATEGORIES

Category

Management

Likelihood of cancer

0

Need Additional Imaging or Prior Examinations

Recall for Additional Imaging and/or Await Prior Examinations

n/a

1

Negative

Routine Screening

Essentially 0%

2

Benign

Routing Screening

Essentially 0%

3

Probably Benign

Short Interval Follow-up (6 month) or Continued

>0% but < 2%

4

Suspicious

Tissue Diagnosis

  • 4a. low suspicion for malignancy (>2% to < 10%)
  • 4b. moderate suspicion for malignancy (>10% to < 50%)
  • 4c. high suspicion for malignancy (>50% to <95%)

5

Highly Suggestive of Malignancy

Tissue Diagnosis

>95%

6

Known Biopsy-Proven

Surgical Excision when Clinically Appropriate

n/a

Table 1. BI-RADS Categories

Source: http://www.radiologyassistant.nl/data/bin/a53b4293920e94_TAB-Birads

"Reducing the number of unnecessary breast biopsies is an essential advancement toward improving women's healthcare and protecting breast health," said Pam Otto, M.D., Department of Radiology, The University of Texas Health Science Center at San Antonio and co-author. "I would encourage breast imagers to consider using BI-RADS 4 subcategories and NLR as important tools for helping them minimize false positive studies with minimum adverse effect on sensitivity, optimizing their patients' breast health. The availability of web-based programs for automating the NLR calculations should help to facilitate routine use of this important statistical tool."

For more information: www.ajronline.org

References

1. Yang WT, Parikh JR, Stavros AT, Otto P and Maislin G. Exploring the Negative Likelihood Ratio and How It Can Be Used to Minimize False-Positives in Breast Imaging. AJR 2018;210:301-306.

 

 

Related Content

Imago Systems Announces Collaboration With Mayo Clinic for Breast Imaging

Image courtesy of Imago Systems

News | Mammography | August 14, 2019
Image visualization company Imago Systems announced it has signed a know-how license with Mayo Clinic. The multi-year...
Artificial Intelligence Could Yield More Accurate Breast Cancer Diagnoses
News | Artificial Intelligence | August 13, 2019
University of California Los Angeles (UCLA) researchers have developed an artificial intelligence (AI) system that...
Lake Medical Imaging Selects Infinitt for Multi-site RIS/PACS
News | PACS | August 09, 2019
Infinitt North America will be implementing Infinitt RIS (radiology information system)/PACS (picture archiving and...
Volpara to Distribute Screenpoint Medical's Transpara AI Solution
News | Breast Imaging | August 02, 2019
Volpara Solutions and ScreenPoint Medical BV signed an agreement under which Volpara will sell ScreenPoint's Transpara...
Ikonopedia Releases Automated Combined Reporting Package at AHRA
News | Mammography Reporting Software | July 26, 2019
Ikonopedia showcased its recently released Automated Combined Reporting package and its entire suite of structured...
Hologic Partners With MagView to Develop Unifi EQUIP Solution
Technology | Mammography Reporting Software | July 25, 2019
Hologic announced a partnership with mammography information solutions provider MagView to develop Unifi EQUIP, an...
Fujifilm Releases Tomosynthesis Biopsy Option for Aspire Cristalle Mammography System
Technology | Breast Biopsy Systems | July 24, 2019
Fujifilm Medical Systems U.S.A. Inc. recently expanded its breast imaging solutions with the launch of its...
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).