Reduction of False-Positive Markings on Mammograms: a Retrospective Comparison Study Using an Artificial Intelligence-Based CAD

Research output: Contribution to journalArticle

2 Citations (Scopus)

Abstract

The aim was to determine whether an artificial intelligence (AI)-based, computer-aided detection (CAD) software can be used to reduce false positive per image (FPPI) on mammograms as compared to an FDA-approved conventional CAD. A retrospective study was performed on a set of 250 full-field digital mammograms between January 1, 2013, and March 31, 2013, and the number of marked regions of interest of two different systems was compared for sensitivity and specificity in cancer detection. The count of false-positive marks per image (FPPI) of the two systems was also evaluated as well as the number of cases that were completely mark-free. All results showed statistically significant reductions in false marks with the use of AI-CAD vs CAD (confidence interval = 95%) with no reduction in sensitivity. There is an overall 69% reduction in FPPI using the AI-based CAD as compared to CAD, consisting of 83% reduction in FPPI for calcifications and 56% reduction for masses. Almost half (48%) of cases showed no AI-CAD markings while only 17% show no conventional CAD marks. There was a significant reduction in FPPI with AI-CAD as compared to CAD for both masses and calcifications at all tissue densities. A 69% decrease in FPPI could result in a 17% decrease in radiologist reading time per case based on prior literature of CAD reading times. Additionally, decreasing false-positive recalls in screening mammography has many direct social and economic benefits.

Original languageEnglish (US)
Pages (from-to)618-624
Number of pages7
JournalJournal of Digital Imaging
Volume32
Issue number4
DOIs
StatePublished - Aug 15 2019

Fingerprint

Artificial Intelligence
Artificial intelligence
Retrospective Studies
Reading
Mammography
Screening
Software
Economics
Confidence Intervals
Tissue
Sensitivity and Specificity

Keywords

  • Artificial intelligence
  • Breast imaging
  • Computer-aided detection
  • False-positive exam
  • Mammogram

ASJC Scopus subject areas

  • Radiological and Ultrasound Technology
  • Radiology Nuclear Medicine and imaging
  • Computer Science Applications

Cite this

@article{cd9254b94c0946038248f701da81edb4,
title = "Reduction of False-Positive Markings on Mammograms: a Retrospective Comparison Study Using an Artificial Intelligence-Based CAD",
abstract = "The aim was to determine whether an artificial intelligence (AI)-based, computer-aided detection (CAD) software can be used to reduce false positive per image (FPPI) on mammograms as compared to an FDA-approved conventional CAD. A retrospective study was performed on a set of 250 full-field digital mammograms between January 1, 2013, and March 31, 2013, and the number of marked regions of interest of two different systems was compared for sensitivity and specificity in cancer detection. The count of false-positive marks per image (FPPI) of the two systems was also evaluated as well as the number of cases that were completely mark-free. All results showed statistically significant reductions in false marks with the use of AI-CAD vs CAD (confidence interval = 95{\%}) with no reduction in sensitivity. There is an overall 69{\%} reduction in FPPI using the AI-based CAD as compared to CAD, consisting of 83{\%} reduction in FPPI for calcifications and 56{\%} reduction for masses. Almost half (48{\%}) of cases showed no AI-CAD markings while only 17{\%} show no conventional CAD marks. There was a significant reduction in FPPI with AI-CAD as compared to CAD for both masses and calcifications at all tissue densities. A 69{\%} decrease in FPPI could result in a 17{\%} decrease in radiologist reading time per case based on prior literature of CAD reading times. Additionally, decreasing false-positive recalls in screening mammography has many direct social and economic benefits.",
keywords = "Artificial intelligence, Breast imaging, Computer-aided detection, False-positive exam, Mammogram",
author = "Mayo, {Ray Cody} and Daniel Kent and Sen, {Lauren Chang} and Megha Kapoor and Leung, {Jessica W.T.} and Watanabe, {Alyssa T.}",
year = "2019",
month = "8",
day = "15",
doi = "10.1007/s10278-018-0168-6",
language = "English (US)",
volume = "32",
pages = "618--624",
journal = "Journal of Digital Imaging",
issn = "0897-1889",
publisher = "Springer New York",
number = "4",

}

TY - JOUR

T1 - Reduction of False-Positive Markings on Mammograms

T2 - a Retrospective Comparison Study Using an Artificial Intelligence-Based CAD

AU - Mayo, Ray Cody

AU - Kent, Daniel

AU - Sen, Lauren Chang

AU - Kapoor, Megha

AU - Leung, Jessica W.T.

AU - Watanabe, Alyssa T.

PY - 2019/8/15

Y1 - 2019/8/15

N2 - The aim was to determine whether an artificial intelligence (AI)-based, computer-aided detection (CAD) software can be used to reduce false positive per image (FPPI) on mammograms as compared to an FDA-approved conventional CAD. A retrospective study was performed on a set of 250 full-field digital mammograms between January 1, 2013, and March 31, 2013, and the number of marked regions of interest of two different systems was compared for sensitivity and specificity in cancer detection. The count of false-positive marks per image (FPPI) of the two systems was also evaluated as well as the number of cases that were completely mark-free. All results showed statistically significant reductions in false marks with the use of AI-CAD vs CAD (confidence interval = 95%) with no reduction in sensitivity. There is an overall 69% reduction in FPPI using the AI-based CAD as compared to CAD, consisting of 83% reduction in FPPI for calcifications and 56% reduction for masses. Almost half (48%) of cases showed no AI-CAD markings while only 17% show no conventional CAD marks. There was a significant reduction in FPPI with AI-CAD as compared to CAD for both masses and calcifications at all tissue densities. A 69% decrease in FPPI could result in a 17% decrease in radiologist reading time per case based on prior literature of CAD reading times. Additionally, decreasing false-positive recalls in screening mammography has many direct social and economic benefits.

AB - The aim was to determine whether an artificial intelligence (AI)-based, computer-aided detection (CAD) software can be used to reduce false positive per image (FPPI) on mammograms as compared to an FDA-approved conventional CAD. A retrospective study was performed on a set of 250 full-field digital mammograms between January 1, 2013, and March 31, 2013, and the number of marked regions of interest of two different systems was compared for sensitivity and specificity in cancer detection. The count of false-positive marks per image (FPPI) of the two systems was also evaluated as well as the number of cases that were completely mark-free. All results showed statistically significant reductions in false marks with the use of AI-CAD vs CAD (confidence interval = 95%) with no reduction in sensitivity. There is an overall 69% reduction in FPPI using the AI-based CAD as compared to CAD, consisting of 83% reduction in FPPI for calcifications and 56% reduction for masses. Almost half (48%) of cases showed no AI-CAD markings while only 17% show no conventional CAD marks. There was a significant reduction in FPPI with AI-CAD as compared to CAD for both masses and calcifications at all tissue densities. A 69% decrease in FPPI could result in a 17% decrease in radiologist reading time per case based on prior literature of CAD reading times. Additionally, decreasing false-positive recalls in screening mammography has many direct social and economic benefits.

KW - Artificial intelligence

KW - Breast imaging

KW - Computer-aided detection

KW - False-positive exam

KW - Mammogram

UR - http://www.scopus.com/inward/record.url?scp=85064241425&partnerID=8YFLogxK

UR - http://www.scopus.com/inward/citedby.url?scp=85064241425&partnerID=8YFLogxK

U2 - 10.1007/s10278-018-0168-6

DO - 10.1007/s10278-018-0168-6

M3 - Article

C2 - 30963339

AN - SCOPUS:85064241425

VL - 32

SP - 618

EP - 624

JO - Journal of Digital Imaging

JF - Journal of Digital Imaging

SN - 0897-1889

IS - 4

ER -