Computer-aided diagnosis of breast tumors using textures from intensity transformed sonographic images

Chung Ming Lo, R. F. Chang, C. S. Huang, W. K. Moon

Research output: Chapter in Book/Report/Conference proceedingConference contribution

2 Citations (Scopus)

Abstract

The malignancy of breast tumors are evaluated via ultrasound images on clinical examination. As a second viewer, a computer-aided diagnosis (CAD) system was developed to classify the breast tumors using texture features to avoid misclassifying carcinomas. A total of 69 cases including 21 malignant and 48 benign masses were acquired. For intensity- invariant texture extraction, the ultrasound images were first transformed into ranklet images to reduce the effect of brightness variability. From the ranklet images, tumor texture and speckle texture were extracted and compared to those from the original ultrasound images for tumor diagnosis. In the trade-offs between sensitivity and specificity, the rankletbased tumor texture and speckle texture were all significantly better than those of the original US images (Az: 0.83 vs. 0.58, p-value=0.0009 and Az=0.80 vs. 0.56, p-value=0.02). The proposed CAD system using textures from intensity transformed sonographic images is robust to various gray-scale distributions and is more suitable in clinical use.

Original languageEnglish
Title of host publicationIFMBE Proceedings
PublisherSpringer Verlag
Pages124-127
Number of pages4
Volume47
ISBN (Print)9783319122618
DOIs
Publication statusPublished - 2015
Externally publishedYes
Event1st Global Conference on Biomedical Engineering, GCBME 2014 and 9th Asian-Pacific Conference on Medical and Biological Engineering, APCMBE 2014 - Tainan, Taiwan
Duration: Oct 9 2014Oct 12 2014

Other

Other1st Global Conference on Biomedical Engineering, GCBME 2014 and 9th Asian-Pacific Conference on Medical and Biological Engineering, APCMBE 2014
CountryTaiwan
CityTainan
Period10/9/1410/12/14

Fingerprint

Computer aided diagnosis
Tumors
Textures
Ultrasonics
Speckle
Luminance

Keywords

  • Breast cancer
  • Computer-aided diagnosis
  • Texture
  • Ultrasound

ASJC Scopus subject areas

  • Biomedical Engineering
  • Bioengineering

Cite this

Lo, C. M., Chang, R. F., Huang, C. S., & Moon, W. K. (2015). Computer-aided diagnosis of breast tumors using textures from intensity transformed sonographic images. In IFMBE Proceedings (Vol. 47, pp. 124-127). Springer Verlag. https://doi.org/10.1007/978-3-319-11128-5_35

Computer-aided diagnosis of breast tumors using textures from intensity transformed sonographic images. / Lo, Chung Ming; Chang, R. F.; Huang, C. S.; Moon, W. K.

IFMBE Proceedings. Vol. 47 Springer Verlag, 2015. p. 124-127.

Research output: Chapter in Book/Report/Conference proceedingConference contribution

Lo, CM, Chang, RF, Huang, CS & Moon, WK 2015, Computer-aided diagnosis of breast tumors using textures from intensity transformed sonographic images. in IFMBE Proceedings. vol. 47, Springer Verlag, pp. 124-127, 1st Global Conference on Biomedical Engineering, GCBME 2014 and 9th Asian-Pacific Conference on Medical and Biological Engineering, APCMBE 2014, Tainan, Taiwan, 10/9/14. https://doi.org/10.1007/978-3-319-11128-5_35
Lo CM, Chang RF, Huang CS, Moon WK. Computer-aided diagnosis of breast tumors using textures from intensity transformed sonographic images. In IFMBE Proceedings. Vol. 47. Springer Verlag. 2015. p. 124-127 https://doi.org/10.1007/978-3-319-11128-5_35
Lo, Chung Ming ; Chang, R. F. ; Huang, C. S. ; Moon, W. K. / Computer-aided diagnosis of breast tumors using textures from intensity transformed sonographic images. IFMBE Proceedings. Vol. 47 Springer Verlag, 2015. pp. 124-127
@inproceedings{b75684178cb64962bf90828fcb2ddfee,
title = "Computer-aided diagnosis of breast tumors using textures from intensity transformed sonographic images",
abstract = "The malignancy of breast tumors are evaluated via ultrasound images on clinical examination. As a second viewer, a computer-aided diagnosis (CAD) system was developed to classify the breast tumors using texture features to avoid misclassifying carcinomas. A total of 69 cases including 21 malignant and 48 benign masses were acquired. For intensity- invariant texture extraction, the ultrasound images were first transformed into ranklet images to reduce the effect of brightness variability. From the ranklet images, tumor texture and speckle texture were extracted and compared to those from the original ultrasound images for tumor diagnosis. In the trade-offs between sensitivity and specificity, the rankletbased tumor texture and speckle texture were all significantly better than those of the original US images (Az: 0.83 vs. 0.58, p-value=0.0009 and Az=0.80 vs. 0.56, p-value=0.02). The proposed CAD system using textures from intensity transformed sonographic images is robust to various gray-scale distributions and is more suitable in clinical use.",
keywords = "Breast cancer, Computer-aided diagnosis, Texture, Ultrasound",
author = "Lo, {Chung Ming} and Chang, {R. F.} and Huang, {C. S.} and Moon, {W. K.}",
year = "2015",
doi = "10.1007/978-3-319-11128-5_35",
language = "English",
isbn = "9783319122618",
volume = "47",
pages = "124--127",
booktitle = "IFMBE Proceedings",
publisher = "Springer Verlag",

}

TY - GEN

T1 - Computer-aided diagnosis of breast tumors using textures from intensity transformed sonographic images

AU - Lo, Chung Ming

AU - Chang, R. F.

AU - Huang, C. S.

AU - Moon, W. K.

PY - 2015

Y1 - 2015

N2 - The malignancy of breast tumors are evaluated via ultrasound images on clinical examination. As a second viewer, a computer-aided diagnosis (CAD) system was developed to classify the breast tumors using texture features to avoid misclassifying carcinomas. A total of 69 cases including 21 malignant and 48 benign masses were acquired. For intensity- invariant texture extraction, the ultrasound images were first transformed into ranklet images to reduce the effect of brightness variability. From the ranklet images, tumor texture and speckle texture were extracted and compared to those from the original ultrasound images for tumor diagnosis. In the trade-offs between sensitivity and specificity, the rankletbased tumor texture and speckle texture were all significantly better than those of the original US images (Az: 0.83 vs. 0.58, p-value=0.0009 and Az=0.80 vs. 0.56, p-value=0.02). The proposed CAD system using textures from intensity transformed sonographic images is robust to various gray-scale distributions and is more suitable in clinical use.

AB - The malignancy of breast tumors are evaluated via ultrasound images on clinical examination. As a second viewer, a computer-aided diagnosis (CAD) system was developed to classify the breast tumors using texture features to avoid misclassifying carcinomas. A total of 69 cases including 21 malignant and 48 benign masses were acquired. For intensity- invariant texture extraction, the ultrasound images were first transformed into ranklet images to reduce the effect of brightness variability. From the ranklet images, tumor texture and speckle texture were extracted and compared to those from the original ultrasound images for tumor diagnosis. In the trade-offs between sensitivity and specificity, the rankletbased tumor texture and speckle texture were all significantly better than those of the original US images (Az: 0.83 vs. 0.58, p-value=0.0009 and Az=0.80 vs. 0.56, p-value=0.02). The proposed CAD system using textures from intensity transformed sonographic images is robust to various gray-scale distributions and is more suitable in clinical use.

KW - Breast cancer

KW - Computer-aided diagnosis

KW - Texture

KW - Ultrasound

UR - http://www.scopus.com/inward/record.url?scp=84914818786&partnerID=8YFLogxK

UR - http://www.scopus.com/inward/citedby.url?scp=84914818786&partnerID=8YFLogxK

U2 - 10.1007/978-3-319-11128-5_35

DO - 10.1007/978-3-319-11128-5_35

M3 - Conference contribution

AN - SCOPUS:84914818786

SN - 9783319122618

VL - 47

SP - 124

EP - 127

BT - IFMBE Proceedings

PB - Springer Verlag

ER -