Tumor detection in automated breast ultrasound images using quantitative tissue clustering

Woo Kyung Moon, Chung Ming Lo, Rong Tai Chen, Yi Wei Shen, Jung Min Chang, Chiun Sheng Huang, Jeon Hor Chen, Wei Wen Hsu, Ruey Feng Chang

Research output: Contribution to journalArticle

13 Citations (Scopus)

Abstract

Purpose: A computer-aided detection (CADe) system based on quantitative tissue clustering algorithm was proposed to identify potential tumors in automated breast ultrasound (ABUS) images. Methods: Our three-dimensional (3D) ABUS images database included 148 biopsy-verified lesions (size 0.4-7.9 cm; mean 1.76 cm). An ABUS volume was comprised of 229-282 slices of two-dimensional (2D) images. For tumor detection, the fast 3D mean shift method was used to remove the speckle noise and the segment tissues with similar properties. The hypoechogenic regions, i.e., the tumor candidates, were extracted using fuzzy c-means clustering. Seven features related to echogenicity and morphology were quantified and used to predict the likelihood of identifying a tumor and filtering out the false-positive (FP) regions. Results: The sensitivity of the proposed CADe system achieved 89.19% (132/148) with 2.00 FPs per volume. For the volumes without lesion, the FP rate was 1.27. The sensitivity was 92.50% (74/80) for malignant tumors and 85.29% (58/68) for benign tumors. Conclusions: The proposed CADe system provides an automatic and quantitative procedure for tumor detection in ABUS images. Further studies are needed to reduce the FP rate of the CADe algorithm.

Original languageEnglish
Article number042901
JournalMedical Physics
Volume41
Issue number4
DOIs
Publication statusPublished - 2014
Externally publishedYes

Fingerprint

Cluster Analysis
Breast
Neoplasms
Databases
Biopsy

Keywords

  • automated breast ultrasound
  • breast cancer
  • clustering
  • computer-aided detection

ASJC Scopus subject areas

  • Biophysics
  • Radiology Nuclear Medicine and imaging
  • Medicine(all)

Cite this

Moon, W. K., Lo, C. M., Chen, R. T., Shen, Y. W., Chang, J. M., Huang, C. S., ... Chang, R. F. (2014). Tumor detection in automated breast ultrasound images using quantitative tissue clustering. Medical Physics, 41(4), [042901]. https://doi.org/10.1118/1.4869264

Tumor detection in automated breast ultrasound images using quantitative tissue clustering. / Moon, Woo Kyung; Lo, Chung Ming; Chen, Rong Tai; Shen, Yi Wei; Chang, Jung Min; Huang, Chiun Sheng; Chen, Jeon Hor; Hsu, Wei Wen; Chang, Ruey Feng.

In: Medical Physics, Vol. 41, No. 4, 042901, 2014.

Research output: Contribution to journalArticle

Moon, WK, Lo, CM, Chen, RT, Shen, YW, Chang, JM, Huang, CS, Chen, JH, Hsu, WW & Chang, RF 2014, 'Tumor detection in automated breast ultrasound images using quantitative tissue clustering', Medical Physics, vol. 41, no. 4, 042901. https://doi.org/10.1118/1.4869264
Moon, Woo Kyung ; Lo, Chung Ming ; Chen, Rong Tai ; Shen, Yi Wei ; Chang, Jung Min ; Huang, Chiun Sheng ; Chen, Jeon Hor ; Hsu, Wei Wen ; Chang, Ruey Feng. / Tumor detection in automated breast ultrasound images using quantitative tissue clustering. In: Medical Physics. 2014 ; Vol. 41, No. 4.
@article{da14bde7180c4b41b0de6231d533c008,
title = "Tumor detection in automated breast ultrasound images using quantitative tissue clustering",
abstract = "Purpose: A computer-aided detection (CADe) system based on quantitative tissue clustering algorithm was proposed to identify potential tumors in automated breast ultrasound (ABUS) images. Methods: Our three-dimensional (3D) ABUS images database included 148 biopsy-verified lesions (size 0.4-7.9 cm; mean 1.76 cm). An ABUS volume was comprised of 229-282 slices of two-dimensional (2D) images. For tumor detection, the fast 3D mean shift method was used to remove the speckle noise and the segment tissues with similar properties. The hypoechogenic regions, i.e., the tumor candidates, were extracted using fuzzy c-means clustering. Seven features related to echogenicity and morphology were quantified and used to predict the likelihood of identifying a tumor and filtering out the false-positive (FP) regions. Results: The sensitivity of the proposed CADe system achieved 89.19{\%} (132/148) with 2.00 FPs per volume. For the volumes without lesion, the FP rate was 1.27. The sensitivity was 92.50{\%} (74/80) for malignant tumors and 85.29{\%} (58/68) for benign tumors. Conclusions: The proposed CADe system provides an automatic and quantitative procedure for tumor detection in ABUS images. Further studies are needed to reduce the FP rate of the CADe algorithm.",
keywords = "automated breast ultrasound, breast cancer, clustering, computer-aided detection",
author = "Moon, {Woo Kyung} and Lo, {Chung Ming} and Chen, {Rong Tai} and Shen, {Yi Wei} and Chang, {Jung Min} and Huang, {Chiun Sheng} and Chen, {Jeon Hor} and Hsu, {Wei Wen} and Chang, {Ruey Feng}",
year = "2014",
doi = "10.1118/1.4869264",
language = "English",
volume = "41",
journal = "Medical Physics",
issn = "0094-2405",
publisher = "AAPM - American Association of Physicists in Medicine",
number = "4",

}

TY - JOUR

T1 - Tumor detection in automated breast ultrasound images using quantitative tissue clustering

AU - Moon, Woo Kyung

AU - Lo, Chung Ming

AU - Chen, Rong Tai

AU - Shen, Yi Wei

AU - Chang, Jung Min

AU - Huang, Chiun Sheng

AU - Chen, Jeon Hor

AU - Hsu, Wei Wen

AU - Chang, Ruey Feng

PY - 2014

Y1 - 2014

N2 - Purpose: A computer-aided detection (CADe) system based on quantitative tissue clustering algorithm was proposed to identify potential tumors in automated breast ultrasound (ABUS) images. Methods: Our three-dimensional (3D) ABUS images database included 148 biopsy-verified lesions (size 0.4-7.9 cm; mean 1.76 cm). An ABUS volume was comprised of 229-282 slices of two-dimensional (2D) images. For tumor detection, the fast 3D mean shift method was used to remove the speckle noise and the segment tissues with similar properties. The hypoechogenic regions, i.e., the tumor candidates, were extracted using fuzzy c-means clustering. Seven features related to echogenicity and morphology were quantified and used to predict the likelihood of identifying a tumor and filtering out the false-positive (FP) regions. Results: The sensitivity of the proposed CADe system achieved 89.19% (132/148) with 2.00 FPs per volume. For the volumes without lesion, the FP rate was 1.27. The sensitivity was 92.50% (74/80) for malignant tumors and 85.29% (58/68) for benign tumors. Conclusions: The proposed CADe system provides an automatic and quantitative procedure for tumor detection in ABUS images. Further studies are needed to reduce the FP rate of the CADe algorithm.

AB - Purpose: A computer-aided detection (CADe) system based on quantitative tissue clustering algorithm was proposed to identify potential tumors in automated breast ultrasound (ABUS) images. Methods: Our three-dimensional (3D) ABUS images database included 148 biopsy-verified lesions (size 0.4-7.9 cm; mean 1.76 cm). An ABUS volume was comprised of 229-282 slices of two-dimensional (2D) images. For tumor detection, the fast 3D mean shift method was used to remove the speckle noise and the segment tissues with similar properties. The hypoechogenic regions, i.e., the tumor candidates, were extracted using fuzzy c-means clustering. Seven features related to echogenicity and morphology were quantified and used to predict the likelihood of identifying a tumor and filtering out the false-positive (FP) regions. Results: The sensitivity of the proposed CADe system achieved 89.19% (132/148) with 2.00 FPs per volume. For the volumes without lesion, the FP rate was 1.27. The sensitivity was 92.50% (74/80) for malignant tumors and 85.29% (58/68) for benign tumors. Conclusions: The proposed CADe system provides an automatic and quantitative procedure for tumor detection in ABUS images. Further studies are needed to reduce the FP rate of the CADe algorithm.

KW - automated breast ultrasound

KW - breast cancer

KW - clustering

KW - computer-aided detection

UR - http://www.scopus.com/inward/record.url?scp=84897136745&partnerID=8YFLogxK

UR - http://www.scopus.com/inward/citedby.url?scp=84897136745&partnerID=8YFLogxK

U2 - 10.1118/1.4869264

DO - 10.1118/1.4869264

M3 - Article

VL - 41

JO - Medical Physics

JF - Medical Physics

SN - 0094-2405

IS - 4

M1 - 042901

ER -