An adaptive Fuzzy C-means method utilizing neighboring information for breast tumor segmentation in ultrasound images

Yuan Feng, Fenglin Dong, Xiaolong Xia, Chun Hong Hu, Qianmin Fan, Yanle Hu, Mingyuan Gao, Sasa Mutic

Research output: Contribution to journalArticle

9 Citations (Scopus)

Abstract

Purpose: Ultrasound (US) imaging has been widely used in breast tumor diagnosis and treatment intervention. Automatic delineation of the tumor is a crucial first step, especially for the computer-aided diagnosis (CAD) and US-guided breast procedure. However, the intrinsic properties of US images such as low contrast and blurry boundaries pose challenges to the automatic segmentation of the breast tumor. Therefore, the purpose of this study is to propose a segmentation algorithm that can contour the breast tumor in US images. Methods: To utilize the neighbor information of each pixel, a Hausdorff distance based fuzzy c-means (FCM) method was adopted. The size of the neighbor region was adaptively updated by comparing the mutual information between them. The objective function of the clustering process was updated by a combination of Euclid distance and the adaptively calculated Hausdorff distance. Segmentation results were evaluated by comparing with three experts' manual segmentations. The results were also compared with a kernel-induced distance based FCM with spatial constraints, the method without adaptive region selection, and conventional FCM. Results: Results from segmenting 30 patient images showed the adaptive method had a value of sensitivity, specificity, Jaccard similarity, and Dice coefficient of 93.60 ± 5.33%, 97.83 ± 2.17%, 86.38 ± 5.80%, and 92.58 ± 3.68%, respectively. The region-based metrics of average symmetric surface distance (ASSD), root mean square symmetric distance (RMSD), and maximum symmetric surface distance (MSSD) were 0.03 ± 0.04 mm, 0.04 ± 0.03 mm, and 1.18 ± 1.01 mm, respectively. All the metrics except sensitivity were better than that of the non-adaptive algorithm and the conventional FCM. Only three region-based metrics were better than that of the kernel-induced distance based FCM with spatial constraints. Conclusion: Inclusion of the pixel neighbor information adaptively in segmenting US images improved the segmentation performance. The results demonstrate the potential application of the method in breast tumor CAD and other US-guided procedures.

Original languageEnglish (US)
Pages (from-to)3752-3760
Number of pages9
JournalMedical Physics
Volume44
Issue number7
DOIs
StatePublished - Jul 1 2017

Fingerprint

Breast Neoplasms
Cluster Analysis
Ultrasonography
Breast
Sensitivity and Specificity
Neoplasms
Therapeutics

Keywords

  • adaptive selection
  • breast tumor
  • FCM
  • image segmentation
  • ultrasound imaging

ASJC Scopus subject areas

  • Biophysics
  • Radiology Nuclear Medicine and imaging

Cite this

An adaptive Fuzzy C-means method utilizing neighboring information for breast tumor segmentation in ultrasound images. / Feng, Yuan; Dong, Fenglin; Xia, Xiaolong; Hu, Chun Hong; Fan, Qianmin; Hu, Yanle; Gao, Mingyuan; Mutic, Sasa.

In: Medical Physics, Vol. 44, No. 7, 01.07.2017, p. 3752-3760.

Research output: Contribution to journalArticle

Feng, Y, Dong, F, Xia, X, Hu, CH, Fan, Q, Hu, Y, Gao, M & Mutic, S 2017, 'An adaptive Fuzzy C-means method utilizing neighboring information for breast tumor segmentation in ultrasound images', Medical Physics, vol. 44, no. 7, pp. 3752-3760. https://doi.org/10.1002/mp.12350
Feng, Yuan ; Dong, Fenglin ; Xia, Xiaolong ; Hu, Chun Hong ; Fan, Qianmin ; Hu, Yanle ; Gao, Mingyuan ; Mutic, Sasa. / An adaptive Fuzzy C-means method utilizing neighboring information for breast tumor segmentation in ultrasound images. In: Medical Physics. 2017 ; Vol. 44, No. 7. pp. 3752-3760.
@article{2aa0e7962db8498085e8969e6b00f5ba,
title = "An adaptive Fuzzy C-means method utilizing neighboring information for breast tumor segmentation in ultrasound images",
abstract = "Purpose: Ultrasound (US) imaging has been widely used in breast tumor diagnosis and treatment intervention. Automatic delineation of the tumor is a crucial first step, especially for the computer-aided diagnosis (CAD) and US-guided breast procedure. However, the intrinsic properties of US images such as low contrast and blurry boundaries pose challenges to the automatic segmentation of the breast tumor. Therefore, the purpose of this study is to propose a segmentation algorithm that can contour the breast tumor in US images. Methods: To utilize the neighbor information of each pixel, a Hausdorff distance based fuzzy c-means (FCM) method was adopted. The size of the neighbor region was adaptively updated by comparing the mutual information between them. The objective function of the clustering process was updated by a combination of Euclid distance and the adaptively calculated Hausdorff distance. Segmentation results were evaluated by comparing with three experts' manual segmentations. The results were also compared with a kernel-induced distance based FCM with spatial constraints, the method without adaptive region selection, and conventional FCM. Results: Results from segmenting 30 patient images showed the adaptive method had a value of sensitivity, specificity, Jaccard similarity, and Dice coefficient of 93.60 ± 5.33{\%}, 97.83 ± 2.17{\%}, 86.38 ± 5.80{\%}, and 92.58 ± 3.68{\%}, respectively. The region-based metrics of average symmetric surface distance (ASSD), root mean square symmetric distance (RMSD), and maximum symmetric surface distance (MSSD) were 0.03 ± 0.04 mm, 0.04 ± 0.03 mm, and 1.18 ± 1.01 mm, respectively. All the metrics except sensitivity were better than that of the non-adaptive algorithm and the conventional FCM. Only three region-based metrics were better than that of the kernel-induced distance based FCM with spatial constraints. Conclusion: Inclusion of the pixel neighbor information adaptively in segmenting US images improved the segmentation performance. The results demonstrate the potential application of the method in breast tumor CAD and other US-guided procedures.",
keywords = "adaptive selection, breast tumor, FCM, image segmentation, ultrasound imaging",
author = "Yuan Feng and Fenglin Dong and Xiaolong Xia and Hu, {Chun Hong} and Qianmin Fan and Yanle Hu and Mingyuan Gao and Sasa Mutic",
year = "2017",
month = "7",
day = "1",
doi = "10.1002/mp.12350",
language = "English (US)",
volume = "44",
pages = "3752--3760",
journal = "Medical Physics",
issn = "0094-2405",
publisher = "AAPM - American Association of Physicists in Medicine",
number = "7",

}

TY - JOUR

T1 - An adaptive Fuzzy C-means method utilizing neighboring information for breast tumor segmentation in ultrasound images

AU - Feng, Yuan

AU - Dong, Fenglin

AU - Xia, Xiaolong

AU - Hu, Chun Hong

AU - Fan, Qianmin

AU - Hu, Yanle

AU - Gao, Mingyuan

AU - Mutic, Sasa

PY - 2017/7/1

Y1 - 2017/7/1

N2 - Purpose: Ultrasound (US) imaging has been widely used in breast tumor diagnosis and treatment intervention. Automatic delineation of the tumor is a crucial first step, especially for the computer-aided diagnosis (CAD) and US-guided breast procedure. However, the intrinsic properties of US images such as low contrast and blurry boundaries pose challenges to the automatic segmentation of the breast tumor. Therefore, the purpose of this study is to propose a segmentation algorithm that can contour the breast tumor in US images. Methods: To utilize the neighbor information of each pixel, a Hausdorff distance based fuzzy c-means (FCM) method was adopted. The size of the neighbor region was adaptively updated by comparing the mutual information between them. The objective function of the clustering process was updated by a combination of Euclid distance and the adaptively calculated Hausdorff distance. Segmentation results were evaluated by comparing with three experts' manual segmentations. The results were also compared with a kernel-induced distance based FCM with spatial constraints, the method without adaptive region selection, and conventional FCM. Results: Results from segmenting 30 patient images showed the adaptive method had a value of sensitivity, specificity, Jaccard similarity, and Dice coefficient of 93.60 ± 5.33%, 97.83 ± 2.17%, 86.38 ± 5.80%, and 92.58 ± 3.68%, respectively. The region-based metrics of average symmetric surface distance (ASSD), root mean square symmetric distance (RMSD), and maximum symmetric surface distance (MSSD) were 0.03 ± 0.04 mm, 0.04 ± 0.03 mm, and 1.18 ± 1.01 mm, respectively. All the metrics except sensitivity were better than that of the non-adaptive algorithm and the conventional FCM. Only three region-based metrics were better than that of the kernel-induced distance based FCM with spatial constraints. Conclusion: Inclusion of the pixel neighbor information adaptively in segmenting US images improved the segmentation performance. The results demonstrate the potential application of the method in breast tumor CAD and other US-guided procedures.

AB - Purpose: Ultrasound (US) imaging has been widely used in breast tumor diagnosis and treatment intervention. Automatic delineation of the tumor is a crucial first step, especially for the computer-aided diagnosis (CAD) and US-guided breast procedure. However, the intrinsic properties of US images such as low contrast and blurry boundaries pose challenges to the automatic segmentation of the breast tumor. Therefore, the purpose of this study is to propose a segmentation algorithm that can contour the breast tumor in US images. Methods: To utilize the neighbor information of each pixel, a Hausdorff distance based fuzzy c-means (FCM) method was adopted. The size of the neighbor region was adaptively updated by comparing the mutual information between them. The objective function of the clustering process was updated by a combination of Euclid distance and the adaptively calculated Hausdorff distance. Segmentation results were evaluated by comparing with three experts' manual segmentations. The results were also compared with a kernel-induced distance based FCM with spatial constraints, the method without adaptive region selection, and conventional FCM. Results: Results from segmenting 30 patient images showed the adaptive method had a value of sensitivity, specificity, Jaccard similarity, and Dice coefficient of 93.60 ± 5.33%, 97.83 ± 2.17%, 86.38 ± 5.80%, and 92.58 ± 3.68%, respectively. The region-based metrics of average symmetric surface distance (ASSD), root mean square symmetric distance (RMSD), and maximum symmetric surface distance (MSSD) were 0.03 ± 0.04 mm, 0.04 ± 0.03 mm, and 1.18 ± 1.01 mm, respectively. All the metrics except sensitivity were better than that of the non-adaptive algorithm and the conventional FCM. Only three region-based metrics were better than that of the kernel-induced distance based FCM with spatial constraints. Conclusion: Inclusion of the pixel neighbor information adaptively in segmenting US images improved the segmentation performance. The results demonstrate the potential application of the method in breast tumor CAD and other US-guided procedures.

KW - adaptive selection

KW - breast tumor

KW - FCM

KW - image segmentation

KW - ultrasound imaging

UR - http://www.scopus.com/inward/record.url?scp=85020531186&partnerID=8YFLogxK

UR - http://www.scopus.com/inward/citedby.url?scp=85020531186&partnerID=8YFLogxK

U2 - 10.1002/mp.12350

DO - 10.1002/mp.12350

M3 - Article

VL - 44

SP - 3752

EP - 3760

JO - Medical Physics

JF - Medical Physics

SN - 0094-2405

IS - 7

ER -