A Mass Detection System in Mammograms Using Grey Level Co-occurrence Matrix and Optical Density Features

Shen-Chuan Tai, Zih Siou Chen, Wei Ting Tsai, Chin Peng Lin, Li-Li Cheng

Research output: Chapter in Book/Report/Conference proceedingChapter

2 Citations (Scopus)

Abstract

For the radiologists, it is difficult to identify the mass on a mammo-gram since the masses are surrounded by the mammary gland and blood vessel. In current breast cancer screening, about 10%-30% of tumors are often missed by radiologists owing to the ambiguous margins of lesions and the visual fatigue of radiologists resulting from the long-time diagnosis. For these reasons, many computer-aided detection (CADe) systems have been developed to aid radiolo-gists in detecting mammographic lesions that may indicate the presence of breast cancer. The purpose of this study is to construct an automated CADe system us-ing a new feature extraction method for mammographic mass detection. In this system, some adaptive square regions of interest (ROIs) are segmented according to the size of suspicious areas. Then a new feature extraction method adopting grey level co-occurrence matrix and optical density features called GLCM-OD features is applied to each ROI. The GLCM-OD features describe local grey level texture characteristics and the whole photometric distribution of the ROI. Finally, the stepwise linear discriminant analysis is applied to classify abnormal regions by selecting and rating individual performance of each feature. This sys-tem is trained and tested by 358 mammographic cases from the digital database of screening mammography (DDSM). The proposed system averagely provides sensitivityof 97.3% with4.9falsepositives per image andtheAzis0.981. There-sults prove that the proposed system achieves satisfactory detection performance.

Original languageEnglish
Title of host publicationAdvances in Intelligent Systems and Applications - Volume 2
Subtitle of host publicationProceedings of the International Computer
EditorsChang Ruay-Shiung, Peng Sheng-Lung, Lin Chia-Chen
Pages369-376
Number of pages8
DOIs
Publication statusPublished - 2013 Jun 28

Publication series

NameSmart Innovation, Systems and Technologies
Volume21
ISSN (Print)2190-3018
ISSN (Electronic)2190-3026

Fingerprint

Density (optical)
Feature extraction
Screening
Mammography
Adaptive systems
Blood vessels
Discriminant analysis
Tumors
Textures
Fatigue of materials

All Science Journal Classification (ASJC) codes

  • Decision Sciences(all)
  • Computer Science(all)

Cite this

Tai, S-C., Chen, Z. S., Tsai, W. T., Lin, C. P., & Cheng, L-L. (2013). A Mass Detection System in Mammograms Using Grey Level Co-occurrence Matrix and Optical Density Features. In C. Ruay-Shiung, P. Sheng-Lung, & L. Chia-Chen (Eds.), Advances in Intelligent Systems and Applications - Volume 2: Proceedings of the International Computer (pp. 369-376). (Smart Innovation, Systems and Technologies; Vol. 21). https://doi.org/10.1007/978-3-642-35473-1_37
Tai, Shen-Chuan ; Chen, Zih Siou ; Tsai, Wei Ting ; Lin, Chin Peng ; Cheng, Li-Li. / A Mass Detection System in Mammograms Using Grey Level Co-occurrence Matrix and Optical Density Features. Advances in Intelligent Systems and Applications - Volume 2: Proceedings of the International Computer. editor / Chang Ruay-Shiung ; Peng Sheng-Lung ; Lin Chia-Chen. 2013. pp. 369-376 (Smart Innovation, Systems and Technologies).
@inbook{2c963dd712474b89b7a1f94638bed9ec,
title = "A Mass Detection System in Mammograms Using Grey Level Co-occurrence Matrix and Optical Density Features",
abstract = "For the radiologists, it is difficult to identify the mass on a mammo-gram since the masses are surrounded by the mammary gland and blood vessel. In current breast cancer screening, about 10{\%}-30{\%} of tumors are often missed by radiologists owing to the ambiguous margins of lesions and the visual fatigue of radiologists resulting from the long-time diagnosis. For these reasons, many computer-aided detection (CADe) systems have been developed to aid radiolo-gists in detecting mammographic lesions that may indicate the presence of breast cancer. The purpose of this study is to construct an automated CADe system us-ing a new feature extraction method for mammographic mass detection. In this system, some adaptive square regions of interest (ROIs) are segmented according to the size of suspicious areas. Then a new feature extraction method adopting grey level co-occurrence matrix and optical density features called GLCM-OD features is applied to each ROI. The GLCM-OD features describe local grey level texture characteristics and the whole photometric distribution of the ROI. Finally, the stepwise linear discriminant analysis is applied to classify abnormal regions by selecting and rating individual performance of each feature. This sys-tem is trained and tested by 358 mammographic cases from the digital database of screening mammography (DDSM). The proposed system averagely provides sensitivityof 97.3{\%} with4.9falsepositives per image andtheAzis0.981. There-sults prove that the proposed system achieves satisfactory detection performance.",
author = "Shen-Chuan Tai and Chen, {Zih Siou} and Tsai, {Wei Ting} and Lin, {Chin Peng} and Li-Li Cheng",
year = "2013",
month = "6",
day = "28",
doi = "10.1007/978-3-642-35473-1_37",
language = "English",
isbn = "9783642354724",
series = "Smart Innovation, Systems and Technologies",
pages = "369--376",
editor = "Chang Ruay-Shiung and Peng Sheng-Lung and Lin Chia-Chen",
booktitle = "Advances in Intelligent Systems and Applications - Volume 2",

}

Tai, S-C, Chen, ZS, Tsai, WT, Lin, CP & Cheng, L-L 2013, A Mass Detection System in Mammograms Using Grey Level Co-occurrence Matrix and Optical Density Features. in C Ruay-Shiung, P Sheng-Lung & L Chia-Chen (eds), Advances in Intelligent Systems and Applications - Volume 2: Proceedings of the International Computer. Smart Innovation, Systems and Technologies, vol. 21, pp. 369-376. https://doi.org/10.1007/978-3-642-35473-1_37

A Mass Detection System in Mammograms Using Grey Level Co-occurrence Matrix and Optical Density Features. / Tai, Shen-Chuan; Chen, Zih Siou; Tsai, Wei Ting; Lin, Chin Peng; Cheng, Li-Li.

Advances in Intelligent Systems and Applications - Volume 2: Proceedings of the International Computer. ed. / Chang Ruay-Shiung; Peng Sheng-Lung; Lin Chia-Chen. 2013. p. 369-376 (Smart Innovation, Systems and Technologies; Vol. 21).

Research output: Chapter in Book/Report/Conference proceedingChapter

TY - CHAP

T1 - A Mass Detection System in Mammograms Using Grey Level Co-occurrence Matrix and Optical Density Features

AU - Tai, Shen-Chuan

AU - Chen, Zih Siou

AU - Tsai, Wei Ting

AU - Lin, Chin Peng

AU - Cheng, Li-Li

PY - 2013/6/28

Y1 - 2013/6/28

N2 - For the radiologists, it is difficult to identify the mass on a mammo-gram since the masses are surrounded by the mammary gland and blood vessel. In current breast cancer screening, about 10%-30% of tumors are often missed by radiologists owing to the ambiguous margins of lesions and the visual fatigue of radiologists resulting from the long-time diagnosis. For these reasons, many computer-aided detection (CADe) systems have been developed to aid radiolo-gists in detecting mammographic lesions that may indicate the presence of breast cancer. The purpose of this study is to construct an automated CADe system us-ing a new feature extraction method for mammographic mass detection. In this system, some adaptive square regions of interest (ROIs) are segmented according to the size of suspicious areas. Then a new feature extraction method adopting grey level co-occurrence matrix and optical density features called GLCM-OD features is applied to each ROI. The GLCM-OD features describe local grey level texture characteristics and the whole photometric distribution of the ROI. Finally, the stepwise linear discriminant analysis is applied to classify abnormal regions by selecting and rating individual performance of each feature. This sys-tem is trained and tested by 358 mammographic cases from the digital database of screening mammography (DDSM). The proposed system averagely provides sensitivityof 97.3% with4.9falsepositives per image andtheAzis0.981. There-sults prove that the proposed system achieves satisfactory detection performance.

AB - For the radiologists, it is difficult to identify the mass on a mammo-gram since the masses are surrounded by the mammary gland and blood vessel. In current breast cancer screening, about 10%-30% of tumors are often missed by radiologists owing to the ambiguous margins of lesions and the visual fatigue of radiologists resulting from the long-time diagnosis. For these reasons, many computer-aided detection (CADe) systems have been developed to aid radiolo-gists in detecting mammographic lesions that may indicate the presence of breast cancer. The purpose of this study is to construct an automated CADe system us-ing a new feature extraction method for mammographic mass detection. In this system, some adaptive square regions of interest (ROIs) are segmented according to the size of suspicious areas. Then a new feature extraction method adopting grey level co-occurrence matrix and optical density features called GLCM-OD features is applied to each ROI. The GLCM-OD features describe local grey level texture characteristics and the whole photometric distribution of the ROI. Finally, the stepwise linear discriminant analysis is applied to classify abnormal regions by selecting and rating individual performance of each feature. This sys-tem is trained and tested by 358 mammographic cases from the digital database of screening mammography (DDSM). The proposed system averagely provides sensitivityof 97.3% with4.9falsepositives per image andtheAzis0.981. There-sults prove that the proposed system achieves satisfactory detection performance.

UR - http://www.scopus.com/inward/record.url?scp=84879308934&partnerID=8YFLogxK

UR - http://www.scopus.com/inward/citedby.url?scp=84879308934&partnerID=8YFLogxK

U2 - 10.1007/978-3-642-35473-1_37

DO - 10.1007/978-3-642-35473-1_37

M3 - Chapter

AN - SCOPUS:84879308934

SN - 9783642354724

T3 - Smart Innovation, Systems and Technologies

SP - 369

EP - 376

BT - Advances in Intelligent Systems and Applications - Volume 2

A2 - Ruay-Shiung, Chang

A2 - Sheng-Lung, Peng

A2 - Chia-Chen, Lin

ER -

Tai S-C, Chen ZS, Tsai WT, Lin CP, Cheng L-L. A Mass Detection System in Mammograms Using Grey Level Co-occurrence Matrix and Optical Density Features. In Ruay-Shiung C, Sheng-Lung P, Chia-Chen L, editors, Advances in Intelligent Systems and Applications - Volume 2: Proceedings of the International Computer. 2013. p. 369-376. (Smart Innovation, Systems and Technologies). https://doi.org/10.1007/978-3-642-35473-1_37