Interpretation time for screening mammography as a function of the number of computer-aided detection marks.

Tayler M Schwartz,Tamara Miner Haygood,Stephen L Hillis,Gary J Whitman,William Geiser,Olga Lukyanchenko,Radhika Sridharan,Wei Wei

doi:10.1117/1.jmi.7.2.022408

Abstract

.Purpose: Computer-aided detection (CAD) alerts radiologists to findings potentially associated with breast cancer but is notorious for creating false-positive marks. Although a previous paper found that radiologists took more time to interpret mammograms with more CAD marks, our impression was that this was not true in actual interpretation. We hypothesized that radiologists would selectively disregard these marks when present in larger numbers.Approach: We performed a retrospective review of bilateral digital screening mammograms. We use a mixed linear regression model to assess the relationship between number of CAD marks and ln (interpretation time) after adjustment for covariates. Both readers and mammograms were treated as random sampling units.Results: Ten radiologists, with median experience after residency of 12.5 years (range 6 to 24) interpreted 1832 mammograms. After accounting for number of images, Breast Imaging Reporting and Data System category, and breast density, the number of CAD marks was positively associated with longer interpretation time, with each additional CAD mark proportionally increasing median interpretation time by 4.35% for a typical reader.Conclusions: We found no support for our hypothesis that radiologists will selectively disregard CAD marks when they are present in larger numbers.

Highlights

Mammography is the gold standard for breast cancer screening
We found no support for our hypothesis that radiologists will selectively disregard computer-aided detection (CAD) marks when they are present in larger numbers
We suspected that in actual clinical practice, interpretation time may not change with increasing numbers of CAD marks. This suspicion, which we developed based on our own thoughts about how we interpreted images, has been voiced, albeit indirectly, by Fenton,[13] who suggested that experienced radiologists may ignore CAD marks

Summary

Introduction

Mammography is the gold standard for breast cancer screening. It is not without shortcomings as a screening tool. 25% to 33% of visible cancers may be overlooked during a mammographic interpretation because of overlying dense breast tissue, variability in reader experience, and reader fatigue.[1] To help prevent cancers from being overlooked, computer-aided detection (CAD) programs review mammograms using software designed to alert the radiologist to findings potentially associated with breast cancer, such as microcalcifications, masses, and regions of architectural distortion. CAD is notorious for creating a large number of false-positive marks.[2,3,4] Its overall value in screening has been questioned, with a study in 2011 finding that in a large cohort of women undergoing screening mammography, the use of CAD

Methods

Results

Discussion

Conclusion