Automatic tissue classification for high-resolution breast CT images based on bilateral filtering

Xiaofeng Yang, Ioannis Sechopoulos, Baowei Fei

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

12 Citations (Scopus)

Abstract

Breast tissue classification can provide quantitative measurements of breast composition, density and tissue distribution for diagnosis and identification of high-risk patients. In this study, we present an automatic classification method to classify high-resolution dedicated breast CT images. The breast is classified into skin, fat and glandular tissue. First, we use a multiscale bilateral filter to reduce noise and at the same time keep edges on the images. As skin and glandular tissue have similar CT values in breast CT images, we use morphologic operations to get the mask of the skin based on information of its position. Second, we use a modified fuzzy C-mean classification method twice, one for the skin and the other for the fatty and glandular tissue. We compared our classified results with manually segmentation results and used Dice overlap ratios to evaluate our classification method. We also tested our method using added noise in the images. The overlap ratios for glandular tissue were above 94.7% for data from five patients. Evaluation results showed that our method is robust and accurate.

Original languageEnglish (US)
Title of host publicationMedical Imaging 2011
Subtitle of host publicationImage Processing
DOIs
StatePublished - Jun 9 2011
Externally publishedYes
EventMedical Imaging 2011: Image Processing - Lake Buena Vista, FL, United States
Duration: Feb 14 2011Feb 16 2011

Publication series

NameProgress in Biomedical Optics and Imaging - Proceedings of SPIE
Volume7962
ISSN (Print)1605-7422

Other

OtherMedical Imaging 2011: Image Processing
CountryUnited States
CityLake Buena Vista, FL
Period2/14/112/16/11

Fingerprint

breast
Breast
Tissue
high resolution
Skin
Noise
Tissue Distribution
Masks
fats
Adipose Tissue
Oils and fats
Fats
density distribution
masks
filters
evaluation
Chemical analysis

Keywords

  • bias correction
  • breast cancer
  • Breast CT
  • breast tissue classification
  • fuzzy C-Mean classification
  • image classification
  • multiscale filter

ASJC Scopus subject areas

  • Electronic, Optical and Magnetic Materials
  • Biomaterials
  • Atomic and Molecular Physics, and Optics
  • Radiology Nuclear Medicine and imaging

Cite this

Yang, X., Sechopoulos, I., & Fei, B. (2011). Automatic tissue classification for high-resolution breast CT images based on bilateral filtering. In Medical Imaging 2011: Image Processing [79623H] (Progress in Biomedical Optics and Imaging - Proceedings of SPIE; Vol. 7962). https://doi.org/10.1117/12.877881

Automatic tissue classification for high-resolution breast CT images based on bilateral filtering. / Yang, Xiaofeng; Sechopoulos, Ioannis; Fei, Baowei.

Medical Imaging 2011: Image Processing. 2011. 79623H (Progress in Biomedical Optics and Imaging - Proceedings of SPIE; Vol. 7962).

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

Yang, X, Sechopoulos, I & Fei, B 2011, Automatic tissue classification for high-resolution breast CT images based on bilateral filtering. in Medical Imaging 2011: Image Processing., 79623H, Progress in Biomedical Optics and Imaging - Proceedings of SPIE, vol. 7962, Medical Imaging 2011: Image Processing, Lake Buena Vista, FL, United States, 2/14/11. https://doi.org/10.1117/12.877881
Yang X, Sechopoulos I, Fei B. Automatic tissue classification for high-resolution breast CT images based on bilateral filtering. In Medical Imaging 2011: Image Processing. 2011. 79623H. (Progress in Biomedical Optics and Imaging - Proceedings of SPIE). https://doi.org/10.1117/12.877881
Yang, Xiaofeng ; Sechopoulos, Ioannis ; Fei, Baowei. / Automatic tissue classification for high-resolution breast CT images based on bilateral filtering. Medical Imaging 2011: Image Processing. 2011. (Progress in Biomedical Optics and Imaging - Proceedings of SPIE).
@inproceedings{a5f2f507e5a44b1694ad10727428793a,
title = "Automatic tissue classification for high-resolution breast CT images based on bilateral filtering",
abstract = "Breast tissue classification can provide quantitative measurements of breast composition, density and tissue distribution for diagnosis and identification of high-risk patients. In this study, we present an automatic classification method to classify high-resolution dedicated breast CT images. The breast is classified into skin, fat and glandular tissue. First, we use a multiscale bilateral filter to reduce noise and at the same time keep edges on the images. As skin and glandular tissue have similar CT values in breast CT images, we use morphologic operations to get the mask of the skin based on information of its position. Second, we use a modified fuzzy C-mean classification method twice, one for the skin and the other for the fatty and glandular tissue. We compared our classified results with manually segmentation results and used Dice overlap ratios to evaluate our classification method. We also tested our method using added noise in the images. The overlap ratios for glandular tissue were above 94.7{\%} for data from five patients. Evaluation results showed that our method is robust and accurate.",
keywords = "bias correction, breast cancer, Breast CT, breast tissue classification, fuzzy C-Mean classification, image classification, multiscale filter",
author = "Xiaofeng Yang and Ioannis Sechopoulos and Baowei Fei",
year = "2011",
month = "6",
day = "9",
doi = "10.1117/12.877881",
language = "English (US)",
isbn = "9780819485045",
series = "Progress in Biomedical Optics and Imaging - Proceedings of SPIE",
booktitle = "Medical Imaging 2011",

}

TY - GEN

T1 - Automatic tissue classification for high-resolution breast CT images based on bilateral filtering

AU - Yang, Xiaofeng

AU - Sechopoulos, Ioannis

AU - Fei, Baowei

PY - 2011/6/9

Y1 - 2011/6/9

N2 - Breast tissue classification can provide quantitative measurements of breast composition, density and tissue distribution for diagnosis and identification of high-risk patients. In this study, we present an automatic classification method to classify high-resolution dedicated breast CT images. The breast is classified into skin, fat and glandular tissue. First, we use a multiscale bilateral filter to reduce noise and at the same time keep edges on the images. As skin and glandular tissue have similar CT values in breast CT images, we use morphologic operations to get the mask of the skin based on information of its position. Second, we use a modified fuzzy C-mean classification method twice, one for the skin and the other for the fatty and glandular tissue. We compared our classified results with manually segmentation results and used Dice overlap ratios to evaluate our classification method. We also tested our method using added noise in the images. The overlap ratios for glandular tissue were above 94.7% for data from five patients. Evaluation results showed that our method is robust and accurate.

AB - Breast tissue classification can provide quantitative measurements of breast composition, density and tissue distribution for diagnosis and identification of high-risk patients. In this study, we present an automatic classification method to classify high-resolution dedicated breast CT images. The breast is classified into skin, fat and glandular tissue. First, we use a multiscale bilateral filter to reduce noise and at the same time keep edges on the images. As skin and glandular tissue have similar CT values in breast CT images, we use morphologic operations to get the mask of the skin based on information of its position. Second, we use a modified fuzzy C-mean classification method twice, one for the skin and the other for the fatty and glandular tissue. We compared our classified results with manually segmentation results and used Dice overlap ratios to evaluate our classification method. We also tested our method using added noise in the images. The overlap ratios for glandular tissue were above 94.7% for data from five patients. Evaluation results showed that our method is robust and accurate.

KW - bias correction

KW - breast cancer

KW - Breast CT

KW - breast tissue classification

KW - fuzzy C-Mean classification

KW - image classification

KW - multiscale filter

UR - http://www.scopus.com/inward/record.url?scp=79958015524&partnerID=8YFLogxK

UR - http://www.scopus.com/inward/citedby.url?scp=79958015524&partnerID=8YFLogxK

U2 - 10.1117/12.877881

DO - 10.1117/12.877881

M3 - Conference contribution

C2 - 24027608

AN - SCOPUS:79958015524

SN - 9780819485045

T3 - Progress in Biomedical Optics and Imaging - Proceedings of SPIE

BT - Medical Imaging 2011

ER -