Screening mammograms: Interpretation with computer-aided detection-prospective evaluation

Marilyn J. Morton, Dana H. Whaley, Kathleen R Brandt, Kimberly K. Amrami

Research output: Contribution to journalArticle

182 Citations (Scopus)

Abstract

Purpose: To prospectively determine the effect of a commercially available computer-aided detection (CAD) system on interpretations of screening mammograms. Materials and Methods: Institutional review board approval was granted; informed consent and HIPAA compliance were waived. A total of 21 349 screening mammograms obtained in 18 096 women were interpreted first without and then with review of CAD images to determine the effect of CAD analysis on the screening breast cancer detection rate, recall rate, and positive predictive value (PPV) for biopsy. The percentage of total cancers detected by the radiologists independent of CAD and the percentage correctly marked by the CAD system were determined. Results: On the basis of pre-CAD interpretations, 2101 patients were recalled for diagnostic evaluation, 256 biopsies were performed, and 105 breast cancers were diagnosed. The breast cancer detection rate per 1000 screening mammograms was 4.92 (105 of 21 349 mammograms), the recall rate was 9.84% (2101 of 21 349 mammograms), and the PPV for biopsy was 41.0% (105 of 256 biopsies). After CAD image review, 199 additional patients were recalled, 21 additional biopsies were performed, and eight additional cancers were detected. The effect was a 7.62% (eight of 105) increase in the number of breast cancers detected, an increase in the recall rate to 10.77% (2300 of 21 349 mammograms), and a slight decrease in the PPV to 40.8% (113 of 277 biopsies). Radiologists detected 92.9% (105 of 113 cancers) of the total cancers, and CAD correctly marked 76.1% (86 of 113 cancers). Conclusion: The use of CAD improved the detection of breast cancer, with an acceptable increase in the recall rate and a minimal increase in the number of biopsies with benign results.

Original languageEnglish (US)
Pages (from-to)375-383
Number of pages9
JournalRadiology
Volume239
Issue number2
DOIs
StatePublished - May 2006

Fingerprint

Biopsy
Breast Neoplasms
Neoplasms
Health Insurance Portability and Accountability Act
Research Ethics Committees
Informed Consent
Compliance
Radiologists

ASJC Scopus subject areas

  • Radiological and Ultrasound Technology

Cite this

Screening mammograms : Interpretation with computer-aided detection-prospective evaluation. / Morton, Marilyn J.; Whaley, Dana H.; Brandt, Kathleen R; Amrami, Kimberly K.

In: Radiology, Vol. 239, No. 2, 05.2006, p. 375-383.

Research output: Contribution to journalArticle

Morton, Marilyn J. ; Whaley, Dana H. ; Brandt, Kathleen R ; Amrami, Kimberly K. / Screening mammograms : Interpretation with computer-aided detection-prospective evaluation. In: Radiology. 2006 ; Vol. 239, No. 2. pp. 375-383.
@article{5cd0f9fd18b647a3a768448fcd921dab,
title = "Screening mammograms: Interpretation with computer-aided detection-prospective evaluation",
abstract = "Purpose: To prospectively determine the effect of a commercially available computer-aided detection (CAD) system on interpretations of screening mammograms. Materials and Methods: Institutional review board approval was granted; informed consent and HIPAA compliance were waived. A total of 21 349 screening mammograms obtained in 18 096 women were interpreted first without and then with review of CAD images to determine the effect of CAD analysis on the screening breast cancer detection rate, recall rate, and positive predictive value (PPV) for biopsy. The percentage of total cancers detected by the radiologists independent of CAD and the percentage correctly marked by the CAD system were determined. Results: On the basis of pre-CAD interpretations, 2101 patients were recalled for diagnostic evaluation, 256 biopsies were performed, and 105 breast cancers were diagnosed. The breast cancer detection rate per 1000 screening mammograms was 4.92 (105 of 21 349 mammograms), the recall rate was 9.84{\%} (2101 of 21 349 mammograms), and the PPV for biopsy was 41.0{\%} (105 of 256 biopsies). After CAD image review, 199 additional patients were recalled, 21 additional biopsies were performed, and eight additional cancers were detected. The effect was a 7.62{\%} (eight of 105) increase in the number of breast cancers detected, an increase in the recall rate to 10.77{\%} (2300 of 21 349 mammograms), and a slight decrease in the PPV to 40.8{\%} (113 of 277 biopsies). Radiologists detected 92.9{\%} (105 of 113 cancers) of the total cancers, and CAD correctly marked 76.1{\%} (86 of 113 cancers). Conclusion: The use of CAD improved the detection of breast cancer, with an acceptable increase in the recall rate and a minimal increase in the number of biopsies with benign results.",
author = "Morton, {Marilyn J.} and Whaley, {Dana H.} and Brandt, {Kathleen R} and Amrami, {Kimberly K.}",
year = "2006",
month = "5",
doi = "10.1148/radiol.2392042121",
language = "English (US)",
volume = "239",
pages = "375--383",
journal = "Radiology",
issn = "0033-8419",
publisher = "Radiological Society of North America Inc.",
number = "2",

}

TY - JOUR

T1 - Screening mammograms

T2 - Interpretation with computer-aided detection-prospective evaluation

AU - Morton, Marilyn J.

AU - Whaley, Dana H.

AU - Brandt, Kathleen R

AU - Amrami, Kimberly K.

PY - 2006/5

Y1 - 2006/5

N2 - Purpose: To prospectively determine the effect of a commercially available computer-aided detection (CAD) system on interpretations of screening mammograms. Materials and Methods: Institutional review board approval was granted; informed consent and HIPAA compliance were waived. A total of 21 349 screening mammograms obtained in 18 096 women were interpreted first without and then with review of CAD images to determine the effect of CAD analysis on the screening breast cancer detection rate, recall rate, and positive predictive value (PPV) for biopsy. The percentage of total cancers detected by the radiologists independent of CAD and the percentage correctly marked by the CAD system were determined. Results: On the basis of pre-CAD interpretations, 2101 patients were recalled for diagnostic evaluation, 256 biopsies were performed, and 105 breast cancers were diagnosed. The breast cancer detection rate per 1000 screening mammograms was 4.92 (105 of 21 349 mammograms), the recall rate was 9.84% (2101 of 21 349 mammograms), and the PPV for biopsy was 41.0% (105 of 256 biopsies). After CAD image review, 199 additional patients were recalled, 21 additional biopsies were performed, and eight additional cancers were detected. The effect was a 7.62% (eight of 105) increase in the number of breast cancers detected, an increase in the recall rate to 10.77% (2300 of 21 349 mammograms), and a slight decrease in the PPV to 40.8% (113 of 277 biopsies). Radiologists detected 92.9% (105 of 113 cancers) of the total cancers, and CAD correctly marked 76.1% (86 of 113 cancers). Conclusion: The use of CAD improved the detection of breast cancer, with an acceptable increase in the recall rate and a minimal increase in the number of biopsies with benign results.

AB - Purpose: To prospectively determine the effect of a commercially available computer-aided detection (CAD) system on interpretations of screening mammograms. Materials and Methods: Institutional review board approval was granted; informed consent and HIPAA compliance were waived. A total of 21 349 screening mammograms obtained in 18 096 women were interpreted first without and then with review of CAD images to determine the effect of CAD analysis on the screening breast cancer detection rate, recall rate, and positive predictive value (PPV) for biopsy. The percentage of total cancers detected by the radiologists independent of CAD and the percentage correctly marked by the CAD system were determined. Results: On the basis of pre-CAD interpretations, 2101 patients were recalled for diagnostic evaluation, 256 biopsies were performed, and 105 breast cancers were diagnosed. The breast cancer detection rate per 1000 screening mammograms was 4.92 (105 of 21 349 mammograms), the recall rate was 9.84% (2101 of 21 349 mammograms), and the PPV for biopsy was 41.0% (105 of 256 biopsies). After CAD image review, 199 additional patients were recalled, 21 additional biopsies were performed, and eight additional cancers were detected. The effect was a 7.62% (eight of 105) increase in the number of breast cancers detected, an increase in the recall rate to 10.77% (2300 of 21 349 mammograms), and a slight decrease in the PPV to 40.8% (113 of 277 biopsies). Radiologists detected 92.9% (105 of 113 cancers) of the total cancers, and CAD correctly marked 76.1% (86 of 113 cancers). Conclusion: The use of CAD improved the detection of breast cancer, with an acceptable increase in the recall rate and a minimal increase in the number of biopsies with benign results.

UR - http://www.scopus.com/inward/record.url?scp=33646124032&partnerID=8YFLogxK

UR - http://www.scopus.com/inward/citedby.url?scp=33646124032&partnerID=8YFLogxK

U2 - 10.1148/radiol.2392042121

DO - 10.1148/radiol.2392042121

M3 - Article

C2 - 16569779

AN - SCOPUS:33646124032

VL - 239

SP - 375

EP - 383

JO - Radiology

JF - Radiology

SN - 0033-8419

IS - 2

ER -