The adaptive computer-aided diagnosis system based on tumor sizes for the classification of breast tumors detected at screening ultrasound

Woo Kyung Moon, I. Ling Chen, Jung Min Chang, Sung Ui Shin, Chung Ming Lo, Ruey Feng Chang

Research output: Contribution to journalArticle

14 Citations (Scopus)

Abstract

Screening ultrasound (US) is increasingly used as a supplement to mammography in women with dense breasts, and more than 80% of cancers detected by US alone are 1 cm or smaller. An adaptive computer-aided diagnosis (CAD) system based on tumor size was proposed to classify breast tumors detected at screening US images using quantitative morphological and textural features. In the present study, a database containing 156 tumors (78 benign and 78 malignant) was separated into two subsets of different tumor sizes (<1 cm and ⩾1 cm) to explore the improvement in the performance of the CAD system. After adaptation, the accuracies, sensitivities, specificities and Az values of the CAD for the entire database increased from 73.1% (114/156), 73.1% (57/78), 73.1% (57/78), and 0.790 to 81.4% (127/156), 83.3% (65/78), 79.5% (62/78), and 0.852, respectively. In the data subset of tumors larger than 1 cm, the performance improved from 66.2% (51/77), 68.3% (28/41), 63.9% (23/36), and 0.703 to 81.8% (63/77), 85.4% (35/41), 77.8% (28/36), and 0.855, respectively. The proposed CAD system can be helpful to classify breast tumors detected at screening US.

Original languageEnglish
Pages (from-to)70-77
Number of pages8
JournalUltrasonics
Volume76
DOIs
Publication statusPublished - Apr 1 2017

Fingerprint

breast
tumors
screening
Breast Neoplasms
Neoplasms
set theory
Databases
Mammography
supplements
Breast
Sensitivity and Specificity
cancer
sensitivity

Keywords

  • Breast cancer
  • Computer-aided diagnosis
  • Screening ultrasound

ASJC Scopus subject areas

  • Medicine(all)
  • Acoustics and Ultrasonics

Cite this

The adaptive computer-aided diagnosis system based on tumor sizes for the classification of breast tumors detected at screening ultrasound. / Moon, Woo Kyung; Chen, I. Ling; Chang, Jung Min; Shin, Sung Ui; Lo, Chung Ming; Chang, Ruey Feng.

In: Ultrasonics, Vol. 76, 01.04.2017, p. 70-77.

Research output: Contribution to journalArticle

Moon, Woo Kyung ; Chen, I. Ling ; Chang, Jung Min ; Shin, Sung Ui ; Lo, Chung Ming ; Chang, Ruey Feng. / The adaptive computer-aided diagnosis system based on tumor sizes for the classification of breast tumors detected at screening ultrasound. In: Ultrasonics. 2017 ; Vol. 76. pp. 70-77.
@article{58f85f24223d4f8ca46a5ca7d4814911,
title = "The adaptive computer-aided diagnosis system based on tumor sizes for the classification of breast tumors detected at screening ultrasound",
abstract = "Screening ultrasound (US) is increasingly used as a supplement to mammography in women with dense breasts, and more than 80{\%} of cancers detected by US alone are 1 cm or smaller. An adaptive computer-aided diagnosis (CAD) system based on tumor size was proposed to classify breast tumors detected at screening US images using quantitative morphological and textural features. In the present study, a database containing 156 tumors (78 benign and 78 malignant) was separated into two subsets of different tumor sizes (<1 cm and ⩾1 cm) to explore the improvement in the performance of the CAD system. After adaptation, the accuracies, sensitivities, specificities and Az values of the CAD for the entire database increased from 73.1{\%} (114/156), 73.1{\%} (57/78), 73.1{\%} (57/78), and 0.790 to 81.4{\%} (127/156), 83.3{\%} (65/78), 79.5{\%} (62/78), and 0.852, respectively. In the data subset of tumors larger than 1 cm, the performance improved from 66.2{\%} (51/77), 68.3{\%} (28/41), 63.9{\%} (23/36), and 0.703 to 81.8{\%} (63/77), 85.4{\%} (35/41), 77.8{\%} (28/36), and 0.855, respectively. The proposed CAD system can be helpful to classify breast tumors detected at screening US.",
keywords = "Breast cancer, Computer-aided diagnosis, Screening ultrasound",
author = "Moon, {Woo Kyung} and Chen, {I. Ling} and Chang, {Jung Min} and Shin, {Sung Ui} and Lo, {Chung Ming} and Chang, {Ruey Feng}",
year = "2017",
month = "4",
day = "1",
doi = "10.1016/j.ultras.2016.12.017",
language = "English",
volume = "76",
pages = "70--77",
journal = "Ultrasonics",
issn = "0041-624X",
publisher = "Elsevier",

}

TY - JOUR

T1 - The adaptive computer-aided diagnosis system based on tumor sizes for the classification of breast tumors detected at screening ultrasound

AU - Moon, Woo Kyung

AU - Chen, I. Ling

AU - Chang, Jung Min

AU - Shin, Sung Ui

AU - Lo, Chung Ming

AU - Chang, Ruey Feng

PY - 2017/4/1

Y1 - 2017/4/1

N2 - Screening ultrasound (US) is increasingly used as a supplement to mammography in women with dense breasts, and more than 80% of cancers detected by US alone are 1 cm or smaller. An adaptive computer-aided diagnosis (CAD) system based on tumor size was proposed to classify breast tumors detected at screening US images using quantitative morphological and textural features. In the present study, a database containing 156 tumors (78 benign and 78 malignant) was separated into two subsets of different tumor sizes (<1 cm and ⩾1 cm) to explore the improvement in the performance of the CAD system. After adaptation, the accuracies, sensitivities, specificities and Az values of the CAD for the entire database increased from 73.1% (114/156), 73.1% (57/78), 73.1% (57/78), and 0.790 to 81.4% (127/156), 83.3% (65/78), 79.5% (62/78), and 0.852, respectively. In the data subset of tumors larger than 1 cm, the performance improved from 66.2% (51/77), 68.3% (28/41), 63.9% (23/36), and 0.703 to 81.8% (63/77), 85.4% (35/41), 77.8% (28/36), and 0.855, respectively. The proposed CAD system can be helpful to classify breast tumors detected at screening US.

AB - Screening ultrasound (US) is increasingly used as a supplement to mammography in women with dense breasts, and more than 80% of cancers detected by US alone are 1 cm or smaller. An adaptive computer-aided diagnosis (CAD) system based on tumor size was proposed to classify breast tumors detected at screening US images using quantitative morphological and textural features. In the present study, a database containing 156 tumors (78 benign and 78 malignant) was separated into two subsets of different tumor sizes (<1 cm and ⩾1 cm) to explore the improvement in the performance of the CAD system. After adaptation, the accuracies, sensitivities, specificities and Az values of the CAD for the entire database increased from 73.1% (114/156), 73.1% (57/78), 73.1% (57/78), and 0.790 to 81.4% (127/156), 83.3% (65/78), 79.5% (62/78), and 0.852, respectively. In the data subset of tumors larger than 1 cm, the performance improved from 66.2% (51/77), 68.3% (28/41), 63.9% (23/36), and 0.703 to 81.8% (63/77), 85.4% (35/41), 77.8% (28/36), and 0.855, respectively. The proposed CAD system can be helpful to classify breast tumors detected at screening US.

KW - Breast cancer

KW - Computer-aided diagnosis

KW - Screening ultrasound

UR - http://www.scopus.com/inward/record.url?scp=85008870606&partnerID=8YFLogxK

UR - http://www.scopus.com/inward/citedby.url?scp=85008870606&partnerID=8YFLogxK

U2 - 10.1016/j.ultras.2016.12.017

DO - 10.1016/j.ultras.2016.12.017

M3 - Article

C2 - 28086107

AN - SCOPUS:85008870606

VL - 76

SP - 70

EP - 77

JO - Ultrasonics

JF - Ultrasonics

SN - 0041-624X

ER -