The interplay of attention economics and computer-aided detection marks in screening mammography

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

Research output: Chapter in Book/Report/Conference proceedingConference contribution

1 Citation (Scopus)

Abstract

Introduction: According to attention economists, overabundant information leads to decreased attention for individual pieces of information. Computer-aided detection (CAD) alerts radiologists to findings potentially associated with breast cancer but is notorious for creating an abundance of false-positive marks. We suspected that increased CAD marks do not lengthen mammogram interpretation time, as radiologists will selectively disregard these marks when present in larger numbers. We explore the relevance of attention economics in mammography by examining how the number of CAD marks affects interpretation time. Methods: We performed a retrospective review of bilateral digital screening mammograms obtained between January 1, 2011 and February 28, 2014, using only weekend interpretations to decrease distractions and the likelihood of trainee participation. We stratified data according to reader and used ANOVA to assess the relationship between number of CAD marks and interpretation time. Results: Ten radiologists, with median experience after residency of 12.5 years (range 6 to 24,) interpreted 1849 mammograms. When accounting for number of images, Breast Imaging Reporting and Data System category, and breast density, increasing numbers of CAD marks was correlated with longer interpretation time only for the three radiologists with the fewest years of experience (median 7 years.) Conclusion: For the 7 most experienced readers, increasing CAD marks did not lengthen interpretation time. We surmise that as CAD marks increase, the attention given to individual marks decreases. Experienced radiologists may rapidly dismiss larger numbers of CAD marks as false-positive, having learned that devoting extra attention to such marks does not improve clinical detection.

Original languageEnglish
Title of host publicationMedical Imaging 2016: Image Perception, Observer Performance, and Technology Assessment
PublisherSPIE
Volume9787
ISBN (Electronic)9781510600225
DOIs
Publication statusPublished - 2016
Externally publishedYes
EventMedical Imaging 2016: Image Perception, Observer Performance, and Technology Assessment - San Diego, United States
Duration: 2 Mar 20163 Mar 2016

Other

OtherMedical Imaging 2016: Image Perception, Observer Performance, and Technology Assessment
CountryUnited States
CitySan Diego
Period2/3/163/3/16

Fingerprint

Mammography
economics
Screening
screening
Economics
breast
readers
Internship and Residency
data systems
Analysis of variance (ANOVA)
Information Systems
students
Analysis of Variance
Breast
Radiologists
Breast Neoplasms
cancer
Imaging techniques

Keywords

  • Attention Economics
  • Computer-Aided Detection
  • Image Perception
  • Observer Performance Evaluation
  • Technology Impact

ASJC Scopus subject areas

  • Atomic and Molecular Physics, and Optics
  • Electronic, Optical and Magnetic Materials
  • Biomaterials
  • Radiology Nuclear Medicine and imaging

Cite this

Schwartz, T. M., Sridharan, R., Wei, W., Lukyanchenko, O., Geiser, W., Whitman, G. J., & Haygood, T. M. (2016). The interplay of attention economics and computer-aided detection marks in screening mammography. In Medical Imaging 2016: Image Perception, Observer Performance, and Technology Assessment (Vol. 9787). [978711] SPIE. https://doi.org/10.1117/12.2208253

The interplay of attention economics and computer-aided detection marks in screening mammography. / Schwartz, Tayler M.; Sridharan, Radhika; Wei, Wei; Lukyanchenko, Olga; Geiser, William; Whitman, Gary J.; Haygood, Tamara Miner.

Medical Imaging 2016: Image Perception, Observer Performance, and Technology Assessment. Vol. 9787 SPIE, 2016. 978711.

Research output: Chapter in Book/Report/Conference proceedingConference contribution

Schwartz, TM, Sridharan, R, Wei, W, Lukyanchenko, O, Geiser, W, Whitman, GJ & Haygood, TM 2016, The interplay of attention economics and computer-aided detection marks in screening mammography. in Medical Imaging 2016: Image Perception, Observer Performance, and Technology Assessment. vol. 9787, 978711, SPIE, Medical Imaging 2016: Image Perception, Observer Performance, and Technology Assessment, San Diego, United States, 2/3/16. https://doi.org/10.1117/12.2208253
Schwartz TM, Sridharan R, Wei W, Lukyanchenko O, Geiser W, Whitman GJ et al. The interplay of attention economics and computer-aided detection marks in screening mammography. In Medical Imaging 2016: Image Perception, Observer Performance, and Technology Assessment. Vol. 9787. SPIE. 2016. 978711 https://doi.org/10.1117/12.2208253
Schwartz, Tayler M. ; Sridharan, Radhika ; Wei, Wei ; Lukyanchenko, Olga ; Geiser, William ; Whitman, Gary J. ; Haygood, Tamara Miner. / The interplay of attention economics and computer-aided detection marks in screening mammography. Medical Imaging 2016: Image Perception, Observer Performance, and Technology Assessment. Vol. 9787 SPIE, 2016.
@inproceedings{8b9da3908379498190398b6e2140415f,
title = "The interplay of attention economics and computer-aided detection marks in screening mammography",
abstract = "Introduction: According to attention economists, overabundant information leads to decreased attention for individual pieces of information. Computer-aided detection (CAD) alerts radiologists to findings potentially associated with breast cancer but is notorious for creating an abundance of false-positive marks. We suspected that increased CAD marks do not lengthen mammogram interpretation time, as radiologists will selectively disregard these marks when present in larger numbers. We explore the relevance of attention economics in mammography by examining how the number of CAD marks affects interpretation time. Methods: We performed a retrospective review of bilateral digital screening mammograms obtained between January 1, 2011 and February 28, 2014, using only weekend interpretations to decrease distractions and the likelihood of trainee participation. We stratified data according to reader and used ANOVA to assess the relationship between number of CAD marks and interpretation time. Results: Ten radiologists, with median experience after residency of 12.5 years (range 6 to 24,) interpreted 1849 mammograms. When accounting for number of images, Breast Imaging Reporting and Data System category, and breast density, increasing numbers of CAD marks was correlated with longer interpretation time only for the three radiologists with the fewest years of experience (median 7 years.) Conclusion: For the 7 most experienced readers, increasing CAD marks did not lengthen interpretation time. We surmise that as CAD marks increase, the attention given to individual marks decreases. Experienced radiologists may rapidly dismiss larger numbers of CAD marks as false-positive, having learned that devoting extra attention to such marks does not improve clinical detection.",
keywords = "Attention Economics, Computer-Aided Detection, Image Perception, Observer Performance Evaluation, Technology Impact",
author = "Schwartz, {Tayler M.} and Radhika Sridharan and Wei Wei and Olga Lukyanchenko and William Geiser and Whitman, {Gary J.} and Haygood, {Tamara Miner}",
year = "2016",
doi = "10.1117/12.2208253",
language = "English",
volume = "9787",
booktitle = "Medical Imaging 2016: Image Perception, Observer Performance, and Technology Assessment",
publisher = "SPIE",

}

TY - GEN

T1 - The interplay of attention economics and computer-aided detection marks in screening mammography

AU - Schwartz, Tayler M.

AU - Sridharan, Radhika

AU - Wei, Wei

AU - Lukyanchenko, Olga

AU - Geiser, William

AU - Whitman, Gary J.

AU - Haygood, Tamara Miner

PY - 2016

Y1 - 2016

N2 - Introduction: According to attention economists, overabundant information leads to decreased attention for individual pieces of information. Computer-aided detection (CAD) alerts radiologists to findings potentially associated with breast cancer but is notorious for creating an abundance of false-positive marks. We suspected that increased CAD marks do not lengthen mammogram interpretation time, as radiologists will selectively disregard these marks when present in larger numbers. We explore the relevance of attention economics in mammography by examining how the number of CAD marks affects interpretation time. Methods: We performed a retrospective review of bilateral digital screening mammograms obtained between January 1, 2011 and February 28, 2014, using only weekend interpretations to decrease distractions and the likelihood of trainee participation. We stratified data according to reader and used ANOVA to assess the relationship between number of CAD marks and interpretation time. Results: Ten radiologists, with median experience after residency of 12.5 years (range 6 to 24,) interpreted 1849 mammograms. When accounting for number of images, Breast Imaging Reporting and Data System category, and breast density, increasing numbers of CAD marks was correlated with longer interpretation time only for the three radiologists with the fewest years of experience (median 7 years.) Conclusion: For the 7 most experienced readers, increasing CAD marks did not lengthen interpretation time. We surmise that as CAD marks increase, the attention given to individual marks decreases. Experienced radiologists may rapidly dismiss larger numbers of CAD marks as false-positive, having learned that devoting extra attention to such marks does not improve clinical detection.

AB - Introduction: According to attention economists, overabundant information leads to decreased attention for individual pieces of information. Computer-aided detection (CAD) alerts radiologists to findings potentially associated with breast cancer but is notorious for creating an abundance of false-positive marks. We suspected that increased CAD marks do not lengthen mammogram interpretation time, as radiologists will selectively disregard these marks when present in larger numbers. We explore the relevance of attention economics in mammography by examining how the number of CAD marks affects interpretation time. Methods: We performed a retrospective review of bilateral digital screening mammograms obtained between January 1, 2011 and February 28, 2014, using only weekend interpretations to decrease distractions and the likelihood of trainee participation. We stratified data according to reader and used ANOVA to assess the relationship between number of CAD marks and interpretation time. Results: Ten radiologists, with median experience after residency of 12.5 years (range 6 to 24,) interpreted 1849 mammograms. When accounting for number of images, Breast Imaging Reporting and Data System category, and breast density, increasing numbers of CAD marks was correlated with longer interpretation time only for the three radiologists with the fewest years of experience (median 7 years.) Conclusion: For the 7 most experienced readers, increasing CAD marks did not lengthen interpretation time. We surmise that as CAD marks increase, the attention given to individual marks decreases. Experienced radiologists may rapidly dismiss larger numbers of CAD marks as false-positive, having learned that devoting extra attention to such marks does not improve clinical detection.

KW - Attention Economics

KW - Computer-Aided Detection

KW - Image Perception

KW - Observer Performance Evaluation

KW - Technology Impact

UR - http://www.scopus.com/inward/record.url?scp=84976312695&partnerID=8YFLogxK

UR - http://www.scopus.com/inward/citedby.url?scp=84976312695&partnerID=8YFLogxK

U2 - 10.1117/12.2208253

DO - 10.1117/12.2208253

M3 - Conference contribution

AN - SCOPUS:84976312695

VL - 9787

BT - Medical Imaging 2016: Image Perception, Observer Performance, and Technology Assessment

PB - SPIE

ER -