Multi-dimensional tumor detection in automated whole breast ultrasound using topographic watershed

Chung Ming Lo, Rong Tai Chen, Yeun Chung Chang, Ya Wen Yang, Ming Jen Hung, Chiun Sheng Huang, Ruey Feng Chang

Research output: Contribution to journalArticle

33 Citations (Scopus)

Abstract

Automated whole breast ultrasound (ABUS) is becoming a popular screening modality for whole breast examination. Compared to conventional handheld ultrasound, ABUS achieves operator-independent and is feasible for mass screening. However, reviewing hundreds of slices in an ABUS image volume is time-consuming. A computer-aided detection (CADe) system based on watershed transform was proposed in this study to accelerate the reviewing. The watershed transform was applied to gather similar tissues around local minima to be homogeneous regions. The likelihoods of being tumors of the regions were estimated using the quantitative morphology, intensity, and texture features in the 2-D/3-D false positive reduction (FPR). The collected database comprised 68 benign and 65 malignant tumors. As a result, the proposed system achieved sensitivities of 100% (133/133), 90% (121/133), and 80% (107/133) with FPs/pass of 9.44, 5.42, and 3.33, respectively. The figure of merit of the combination of three feature sets is 0.46 which is significantly better than that of other feature sets (p-value <0.05). In summary, the proposed CADe system based on the multi-dimensional FPR using the integrated feature set is promising in detecting tumors in ABUS images.

Original languageEnglish
Article number6782644
Pages (from-to)1503-1511
Number of pages9
JournalIEEE Transactions on Medical Imaging
Volume33
Issue number7
DOIs
Publication statusPublished - 2014
Externally publishedYes

Fingerprint

Watersheds
Tumors
Breast
Ultrasonics
Neoplasms
Screening
Mass Screening
Textures
Databases
Tissue

Keywords

  • Automated whole breast ultrasound
  • breast cancer
  • computer-aided detection
  • multi-dimensional false positive reduction
  • watershed segmentation

ASJC Scopus subject areas

  • Electrical and Electronic Engineering
  • Computer Science Applications
  • Radiological and Ultrasound Technology
  • Software
  • Medicine(all)

Cite this

Lo, C. M., Chen, R. T., Chang, Y. C., Yang, Y. W., Hung, M. J., Huang, C. S., & Chang, R. F. (2014). Multi-dimensional tumor detection in automated whole breast ultrasound using topographic watershed. IEEE Transactions on Medical Imaging, 33(7), 1503-1511. [6782644]. https://doi.org/10.1109/TMI.2014.2315206

Multi-dimensional tumor detection in automated whole breast ultrasound using topographic watershed. / Lo, Chung Ming; Chen, Rong Tai; Chang, Yeun Chung; Yang, Ya Wen; Hung, Ming Jen; Huang, Chiun Sheng; Chang, Ruey Feng.

In: IEEE Transactions on Medical Imaging, Vol. 33, No. 7, 6782644, 2014, p. 1503-1511.

Research output: Contribution to journalArticle

Lo, CM, Chen, RT, Chang, YC, Yang, YW, Hung, MJ, Huang, CS & Chang, RF 2014, 'Multi-dimensional tumor detection in automated whole breast ultrasound using topographic watershed', IEEE Transactions on Medical Imaging, vol. 33, no. 7, 6782644, pp. 1503-1511. https://doi.org/10.1109/TMI.2014.2315206
Lo, Chung Ming ; Chen, Rong Tai ; Chang, Yeun Chung ; Yang, Ya Wen ; Hung, Ming Jen ; Huang, Chiun Sheng ; Chang, Ruey Feng. / Multi-dimensional tumor detection in automated whole breast ultrasound using topographic watershed. In: IEEE Transactions on Medical Imaging. 2014 ; Vol. 33, No. 7. pp. 1503-1511.
@article{6a703200775a4aa49136778bb3bff365,
title = "Multi-dimensional tumor detection in automated whole breast ultrasound using topographic watershed",
abstract = "Automated whole breast ultrasound (ABUS) is becoming a popular screening modality for whole breast examination. Compared to conventional handheld ultrasound, ABUS achieves operator-independent and is feasible for mass screening. However, reviewing hundreds of slices in an ABUS image volume is time-consuming. A computer-aided detection (CADe) system based on watershed transform was proposed in this study to accelerate the reviewing. The watershed transform was applied to gather similar tissues around local minima to be homogeneous regions. The likelihoods of being tumors of the regions were estimated using the quantitative morphology, intensity, and texture features in the 2-D/3-D false positive reduction (FPR). The collected database comprised 68 benign and 65 malignant tumors. As a result, the proposed system achieved sensitivities of 100{\%} (133/133), 90{\%} (121/133), and 80{\%} (107/133) with FPs/pass of 9.44, 5.42, and 3.33, respectively. The figure of merit of the combination of three feature sets is 0.46 which is significantly better than that of other feature sets (p-value <0.05). In summary, the proposed CADe system based on the multi-dimensional FPR using the integrated feature set is promising in detecting tumors in ABUS images.",
keywords = "Automated whole breast ultrasound, breast cancer, computer-aided detection, multi-dimensional false positive reduction, watershed segmentation",
author = "Lo, {Chung Ming} and Chen, {Rong Tai} and Chang, {Yeun Chung} and Yang, {Ya Wen} and Hung, {Ming Jen} and Huang, {Chiun Sheng} and Chang, {Ruey Feng}",
year = "2014",
doi = "10.1109/TMI.2014.2315206",
language = "English",
volume = "33",
pages = "1503--1511",
journal = "IEEE Transactions on Medical Imaging",
issn = "0278-0062",
publisher = "Institute of Electrical and Electronics Engineers Inc.",
number = "7",

}

TY - JOUR

T1 - Multi-dimensional tumor detection in automated whole breast ultrasound using topographic watershed

AU - Lo, Chung Ming

AU - Chen, Rong Tai

AU - Chang, Yeun Chung

AU - Yang, Ya Wen

AU - Hung, Ming Jen

AU - Huang, Chiun Sheng

AU - Chang, Ruey Feng

PY - 2014

Y1 - 2014

N2 - Automated whole breast ultrasound (ABUS) is becoming a popular screening modality for whole breast examination. Compared to conventional handheld ultrasound, ABUS achieves operator-independent and is feasible for mass screening. However, reviewing hundreds of slices in an ABUS image volume is time-consuming. A computer-aided detection (CADe) system based on watershed transform was proposed in this study to accelerate the reviewing. The watershed transform was applied to gather similar tissues around local minima to be homogeneous regions. The likelihoods of being tumors of the regions were estimated using the quantitative morphology, intensity, and texture features in the 2-D/3-D false positive reduction (FPR). The collected database comprised 68 benign and 65 malignant tumors. As a result, the proposed system achieved sensitivities of 100% (133/133), 90% (121/133), and 80% (107/133) with FPs/pass of 9.44, 5.42, and 3.33, respectively. The figure of merit of the combination of three feature sets is 0.46 which is significantly better than that of other feature sets (p-value <0.05). In summary, the proposed CADe system based on the multi-dimensional FPR using the integrated feature set is promising in detecting tumors in ABUS images.

AB - Automated whole breast ultrasound (ABUS) is becoming a popular screening modality for whole breast examination. Compared to conventional handheld ultrasound, ABUS achieves operator-independent and is feasible for mass screening. However, reviewing hundreds of slices in an ABUS image volume is time-consuming. A computer-aided detection (CADe) system based on watershed transform was proposed in this study to accelerate the reviewing. The watershed transform was applied to gather similar tissues around local minima to be homogeneous regions. The likelihoods of being tumors of the regions were estimated using the quantitative morphology, intensity, and texture features in the 2-D/3-D false positive reduction (FPR). The collected database comprised 68 benign and 65 malignant tumors. As a result, the proposed system achieved sensitivities of 100% (133/133), 90% (121/133), and 80% (107/133) with FPs/pass of 9.44, 5.42, and 3.33, respectively. The figure of merit of the combination of three feature sets is 0.46 which is significantly better than that of other feature sets (p-value <0.05). In summary, the proposed CADe system based on the multi-dimensional FPR using the integrated feature set is promising in detecting tumors in ABUS images.

KW - Automated whole breast ultrasound

KW - breast cancer

KW - computer-aided detection

KW - multi-dimensional false positive reduction

KW - watershed segmentation

UR - http://www.scopus.com/inward/record.url?scp=84903782536&partnerID=8YFLogxK

UR - http://www.scopus.com/inward/citedby.url?scp=84903782536&partnerID=8YFLogxK

U2 - 10.1109/TMI.2014.2315206

DO - 10.1109/TMI.2014.2315206

M3 - Article

VL - 33

SP - 1503

EP - 1511

JO - IEEE Transactions on Medical Imaging

JF - IEEE Transactions on Medical Imaging

SN - 0278-0062

IS - 7

M1 - 6782644

ER -